From 1e6504b4a240a55b491a4b6d66ae967935b10365 Mon Sep 17 00:00:00 2001 From: Longtail Date: Sat, 31 Oct 2026 16:15:04 +0800 Subject: [PATCH] first commit --- .gitignore | 10 + README.md | 97 +++ app.py | 205 ++++++ articles.py | 116 ++++ browser/auto-news.user.js | 850 ++++++++++++++++++++++++ browser/formatter-original.user.js | 397 +++++++++++ browser/formatter.js | 195 ++++++ browser/importer.js | 480 +++++++++++++ browser/local-bridge.user.js | 73 ++ browser/runner.js | 173 +++++ build_browser.py | 23 + modules/downloader/README.md | 57 ++ modules/downloader/app.py | 299 +++++++++ modules/downloader/article_writer.py | 212 ++++++ modules/downloader/requirements.txt | 3 + modules/downloader/static/app.js | 79 +++ modules/downloader/static/index.html | 14 + modules/downloader/static/style.css | 1 + modules/package.py | 63 ++ requirements.txt | 3 + start.command | 8 + static/app.js | 51 ++ static/index.html | 26 + static/style.css | 1 + store.py | 294 ++++++++ test/README.md | 12 + test/bridge.test.cjs | 13 + test/browser.test.cjs | 91 +++ test/fixtures/article/image001.png | Bin 0 -> 69 bytes test/fixtures/article/image002.png | Bin 0 -> 69 bytes test/fixtures/article/image003.png | Bin 0 -> 69 bytes test/fixtures/article/原创导入测试稿.md | 15 + test/importer.test.cjs | 172 +++++ test/serve_fixture.py | 19 + test/test_controller.py | 75 +++ test/test_download_core.py | 165 +++++ test/test_queue.py | 155 +++++ test/验证记录.md | 22 + 发布流程操作记录与自动化规范.md | 167 +++++ 实施计划.md | 178 +++++ 流程检查与Git文件清单.md | 150 +++++ 41 files changed, 4964 insertions(+) create mode 100644 .gitignore create mode 100644 README.md create mode 100644 app.py create mode 100644 articles.py create mode 100644 browser/auto-news.user.js create mode 100644 browser/formatter-original.user.js create mode 100644 browser/formatter.js create mode 100644 browser/importer.js create mode 100644 browser/local-bridge.user.js create mode 100644 browser/runner.js create mode 100644 build_browser.py create mode 100644 modules/downloader/README.md create mode 100644 modules/downloader/app.py create mode 100644 modules/downloader/article_writer.py create mode 100644 modules/downloader/requirements.txt create mode 100644 modules/downloader/static/app.js create mode 100644 modules/downloader/static/index.html create mode 100644 modules/downloader/static/style.css create mode 100644 modules/package.py create mode 100644 requirements.txt create mode 100755 start.command create mode 100644 static/app.js create mode 100644 static/index.html create mode 100644 static/style.css create mode 100644 store.py create mode 100644 test/README.md create mode 100644 test/bridge.test.cjs create mode 100644 test/browser.test.cjs create mode 100644 test/fixtures/article/image001.png create mode 100644 test/fixtures/article/image002.png create mode 100644 test/fixtures/article/image003.png create mode 100644 test/fixtures/article/原创导入测试稿.md create mode 100644 test/importer.test.cjs create mode 100644 test/serve_fixture.py create mode 100644 test/test_controller.py create mode 100644 test/test_download_core.py create mode 100644 test/test_queue.py create mode 100644 test/验证记录.md create mode 100644 发布流程操作记录与自动化规范.md create mode 100644 实施计划.md create mode 100644 流程检查与Git文件清单.md diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..036ea74 --- /dev/null +++ b/.gitignore @@ -0,0 +1,10 @@ +data/ +downloads/ +local-records/ +test/history/ +test/artifacts/ +发布去重记录.json +__pycache__/ +*.py[cod] +.venv/ +.DS_Store diff --git a/README.md b/README.md new file mode 100644 index 0000000..a1f62f0 --- /dev/null +++ b/README.md @@ -0,0 +1,97 @@ +# 新闻工作台 + +将新闻下载、文章打包、浏览器导入、排版与换号联动整合到本地控制台。 + +**当前版本：0.1。可完成下载 → 入队 → 导入 → 排版 → 等待人工发表。结果页自动核对按用户决定暂留待接入；人工提交后会记录候选结果并暂停，不会自动计数、换号或处理下一篇。** 换号调度和计数接口已完成离线验证，完整在线链路仍需补齐结果页 HTML 后验证。 + +## 启动 + +双击本目录的 `start.command`，或在本目录运行： + +```sh +uv run --no-project --python 3.12 --with-requirements requirements.txt python app.py +``` + +默认打开 http://127.0.0.1:8770/ 。保留启动窗口，按 Ctrl+C 停止本地服务。修改端口使用 `--port 8772`；不自动打开浏览器使用 `--no-browser`。首次运行 uv 可能下载 Python 或依赖，后续可以复用缓存。 + +页面必须通过本地服务打开，不要直接双击 `static/index.html`。Python 依赖仅用于下载和内容处理；浏览器脚本没有远程脚本依赖。 + +## 浏览器安装与配对 + +1. 在油猴安装控制台“浏览器连接”区域的两个脚本： + - `browser/local-bridge.user.js`：本地连接、配对与常驻终止按钮。 + - `browser/auto-news.user.js`：导入、排版和任务执行。它由 `importer.js`、`formatter.js`、`runner.js` 构建。 +2. 停用旧的独立导入与排版油猴脚本，避免同一编辑器重复挂载。 +3. 换号插件仍由用户安装，位于项目根目录的 `dww11-account-switch-browser-extension/`，没有复制到本目录。本次在其 `content.js` 中增加了不含凭据的状态属性及终止事件监听。请在浏览器扩展管理页重新加载**这个原安装目录**，再刷新网站。旧 ZIP 未重新打包，不包含本次修改。 +4. 在控制台点击“显示本次连接码”。在论坛左下角“新闻工作台 · 本地连接”展开设置，填写端口和连接码并保存。 +5. 服务重启后连接码会改变，需要重新配对；任务和计数保留，但服务不会自动恢复运行。 + +本机 HTTP 通信通过油猴特权请求完成，不要求论坛跨域开放本地服务。真实浏览器的脚本管理器配置、本地网络权限和网站编辑器兼容性仍需首次实机验证。配对码保存在油猴存储，不写入页面全局变量。下载 API Key 不进入文章包，不发给论坛。 + +## 操作流程 + +1. 填写 Key，获取频道、选择数量并下载。完整保存的文章会自动校验并进入队列；下载失败和入队失败分别显示，已保存的文章不因入队失败而删除。 +2. 也可展开“导入已有文章目录”，填写单篇目录或含多个文章子目录的根目录，点击检查。留空表示扫描本工具的 `downloads/`。扫描只处理根目录的一层文章子目录；文件须已完整落盘。 +3. 填写目标版块 `fid`、每账号最少/最多篇数和处理间隔。先核对历史发帖记录，再勾选确认并保存。版块和篇数不会替用户选择。 +4. 登录论坛，建议只保留一个执行标签。点击控制台“开始 / 继续”。执行器识别账号后领取一篇任务，进入指定新帖页、导入、排版，停止在人工审核阶段。 +5. 在论坛检查账号、版块、标题、图片位置、正文和来源，并亲手点击“发表帖子”。程序不调用发帖提交函数，不发送发帖请求，也不自动保存草稿。 +6. 当前版本会记录人工点击和提交快照，在跳转后的候选页面或等待超时后标记“发布结果待核对”并暂停。**需要补充结果页 HTML 后，才能自动核对受理结果并接续下一篇。** + +待补齐结果页自动核对后：审核中算网站已受理一次，但不算已确认公开；达到账号随机目标篇数且仍有待处理文章时，回首页调用插件换号，核对新 UID 与插件空闲状态后创建下一账号批次。没有待处理文章时直接结束，不为达到数量重发。 + +## 终止、恢复与冲突 + +- 网站左下角常驻“终止流程”，点击后立即取消本标签可取消的导入，并通知其他安装脚本的标签和换号插件；持久状态禁止继续领取任务。 +- 控制台“终止流程”还会停止下载，浏览器在下一次连接检查时停止（正常轮询约 2 秒）。网络断开时无法承诺固定延迟；网站按钮可立即停止本标签。已到达网站的图片、登录或发帖请求无法撤回。 +- 暂停/终止后必须明确点击“开始 / 继续”。下载停止等待当前网络请求/单篇保存结束，不伪装成已经撤回在途请求。 +- 非空编辑器、人工修改、账号变化、缺图、未知来源或上传失败会停在“需要处理”，不弹自动确认覆盖旧稿。 +- 导入中刷新后不会重新上传。先核对网站附件和草稿，再决定如何处理。若需要换标签，先在控制台暂停，再在目标标签点击“接管已暂停任务”。接管不会自动重新导入内容。 +- 只有人工确认网站**未受理**且已清理编辑器/草稿后，才能通过队列“人工核对 / 处理”重新排队或移出。审核中、已受理和结果不明不应重试。 +- 换号插件暂停后需要通过插件现有“继续未完成流程”恢复，不重复抽号。若账号未发生变化，调度器不会猜测换号成功。 + +## 文件与数据 + +```text +app.py / store.py / articles.py 本地接口、任务队列、文章校验 +modules/downloader/ 下载器副本与成功保存回调 +modules/package.py 文章包生成器副本 +browser/ 页面执行器、排版和连接脚本 +static/ 操作前端 +start.command 启动入口 +build_browser.py 重建合并油猴脚本 +test/ 离线测试、模拟素材、历史测试截图 +data/queue.sqlite3 运行任务、计数、受理去重记录（本地） +downloads/ 本工具下载结果（本地） +``` + +- `test/history/` 保存从本目录移入的两张演示截图与演示任务 JSON。根目录其他测试文件未搬动。 +- `发布去重记录.json` 是实际受理证据，继续留在原处，并在服务启动时迁入去重库。它不代表完整历史已对账。原文件可找到时还建立内容指纹；原文件丢失时仍保留原 Markdown 摘要。 +- 原始下载文件不改写。长标题生成保守 UTF-16 长度不超过 80 的派生标题并加 `...`，原题仍展示在队列；网站真实计数规则尚需实测。 +- 排版仅处理与文章来源一致的末尾标准尾注，保留正文中的其他“来源”文字。图片顺序、标识改变会回滚排版。 +- WebP/AVIF/SVG 当前明确拦截，需用户另存支持格式并更新 Markdown；没有静默丢图或自动转码。单图须小于 20 MiB，图片 base64 总大小不超过 48 MiB。 +- 本地库含文章内容快照和账号标识，不含账号密码、Cookie 或上传凭据。运行数据和历史截图已加入忽略规则。 + +## 验证 + +不连接新闻 API 或真实论坛： + +```sh +uv run --no-project --python 3.12 --with-requirements requirements.txt python -m unittest discover -s test -p 'test_*.py' -v +node --test test/importer.test.cjs test/bridge.test.cjs +python3 build_browser.py +``` + +浏览器回归需要 Playwright 和本机 Chrome，使用临时独立浏览器，不使用用户配置或账号： + +```sh +# 终端一：临时模拟数据服务，端口 8771 +uv run --no-project --python 3.12 --with-requirements requirements.txt python test/serve_fixture.py +# 终端二：Node 环境需能加载 playwright；CHROME_PATH 可指定浏览器可执行文件 +node test/browser.test.cjs +``` + +浏览器回归拦截所有真实论坛请求，仅使用模拟 HTML。截图输出到 `test/artifacts/`。本轮离线通过不代表已在用户登录态的真实网站上完成上传、换号或发布。 + +## 下一步需要的页面资料 + +按用户决定，等待结果页 HTML：帖子标题、首帖作者及 UID 链接、版块及 fid 链接、“审核中”提示、公开帖子与失败提示。不要提供 Cookie、密码或表单令牌。将据此完成 `runner.js` 的结果观察适配，调用已经实现的受理记录接口，联通后续计数和换号。 diff --git a/app.py b/app.py new file mode 100644 index 0000000..2c0e5e9 --- /dev/null +++ b/app.py @@ -0,0 +1,205 @@ +#!/usr/bin/env python3 +"""Local controller: serves UI and authenticated browser bridge on loopback only.""" +import argparse +import hmac +import importlib.util +import json +from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer +from pathlib import Path +import secrets +import sys +import threading +from urllib.parse import urlsplit +import webbrowser + +ROOT = Path(__file__).resolve().parent +sys.path.insert(0, str(ROOT / 'modules/downloader')) +spec = importlib.util.spec_from_file_location('news_downloader', ROOT / 'modules/downloader/app.py') +downloader = importlib.util.module_from_spec(spec) +spec.loader.exec_module(downloader) +from store import Store + + +class Controller: + def __init__(self, data=ROOT / 'data', downloads=ROOT / 'downloads', ledger=ROOT / '发布去重记录.json'): + self.store = Store(Path(data) / 'queue.sqlite3', ledger) + self.ui_token, self.bridge_token = secrets.token_urlsafe(32), secrets.token_urlsafe(32) + self.manager = downloader.Downloader(downloads, on_saved=self.saved) + self.scan_lock = threading.Lock() + + def saved(self, article, result, keys): + directory = Path(result.directory) + marker = directory / '.article.json' + pending = directory / '.article.json.tmp' + pending.write_text(json.dumps({'fingerprints': keys, 'source_url': result.source_url}, ensure_ascii=False), encoding='utf-8') + pending.replace(marker) + self.store.enqueue(directory) + + def scan(self, root): + if self.manager.thread and self.manager.thread.is_alive(): + raise ValueError('下载进行中，请等待完成后扫描；新下载文章会自动入队') + root = Path(root).expanduser().resolve(strict=True) + if not root.is_dir(): + raise ValueError('文章根目录不存在') + if not self.scan_lock.acquire(blocking=False): + raise ValueError('正在扫描，请稍候') + try: + directories = [root] if list(root.glob('*.md')) else sorted(p for p in root.iterdir() if p.is_dir() and not p.name.startswith('.')) + result = [] + for directory in directories: + try: + status = self.store.enqueue(directory) + except (ValueError, OSError) as error: + status = str(error) + result.append({'directory': directory.name, 'status': status}) + return {'results': result} + finally: + self.scan_lock.release() + + def ui(self, route, body): + if route == 'state': + return {**self.store.state(), 'download': self.manager.snapshot()} + if route == 'pair': + return {'token': self.bridge_token} + if route == 'channels': + key = str(body.get('key', '')).strip() + if not key or len(key) > 512: + raise ValueError('请填写 API Key') + items = downloader.result_list(downloader.api_request(key, 'channel')) + if not items or not all(isinstance(x, str) and x for x in items): + raise ValueError('频道响应格式不正确') + return {'channels': items} + if route == 'download': + key, channel, target = str(body.get('key', '')).strip(), body.get('channel'), body.get('target') + if not key or len(key) > 512 or not isinstance(channel, str) or not channel.strip() or type(target) is not int or not 1 <= target <= 100000: + raise ValueError('请填写 Key、频道和有效下载数量') + self.manager.start(key, channel, target) + return {'ok': True} + if route == 'download-stop': + self.manager.stop.set() + return {'ok': True} + if route == 'scan': + return self.scan(body.get('root', '')) if body.get('root') else self.scan(self.manager.root) + if route == 'configure': + self.store.configure(body) + return {'ok': True} + if route in ('start', 'pause', 'stop'): + if route == 'stop': + self.manager.stop.set() + return self.store.control(route) + if route == 'resolve': + return self.store.resolve(body) + if route == 'history': + records = body.get('records') + if not isinstance(records, list): + raise ValueError('历史记录需包含 records 数组') + self.store.import_history(records) + return {'ok': True} + raise ValueError('未知操作') + + def bridge(self, route, body): + methods = {'heartbeat': self.store.heartbeat, 'next': self.store.next, 'package': self.store.package, + 'event': self.store.event, 'accept': self.store.accept, 'switch-begin': self.store.switch_begin, + 'takeover': self.store.takeover, 'current': self.store.current} + if route == 'stop': + self.manager.stop.set() + return self.store.control('stop') + if route not in methods: + raise ValueError('未知浏览器操作') + return methods[route](body) + + +def make_handler(controller): + class Handler(BaseHTTPRequestHandler): + def log_message(self, *args): + pass # Never echo request bodies, API keys or pairing tokens. + + def send(self, code, payload, mime='application/json; charset=utf-8'): + content = payload if isinstance(payload, bytes) else json.dumps(payload, ensure_ascii=False).encode() + self.send_response(code) + self.send_header('Content-Type', mime) + self.send_header('Content-Length', str(len(content))) + self.send_header('Cache-Control', 'no-store') + self.send_header('X-Content-Type-Options', 'nosniff') + self.send_header('Content-Security-Policy', "default-src 'self'; script-src 'self'; style-src 'self'; connect-src 'self'; frame-ancestors 'none'; base-uri 'none'") + self.end_headers() + try: + self.wfile.write(content) + except (BrokenPipeError, ConnectionResetError): + pass + + def local(self): + return self.headers.get('Host') in (f'127.0.0.1:{self.server.server_port}', f'localhost:{self.server.server_port}') + + def origin_ok(self): + origin = self.headers.get('Origin') + return not origin or origin in (f'http://127.0.0.1:{self.server.server_port}', f'http://localhost:{self.server.server_port}') + + def do_GET(self): + if not self.local() or not self.origin_ok(): + return self.send(403, {'error': '仅允许本机控制台访问'}) + route = urlsplit(self.path).path + if route == '/api/session': + return self.send(200, {'token': controller.ui_token}) + files = {'/': ('static/index.html', 'text/html; charset=utf-8'), + '/app.js': ('static/app.js', 'text/javascript; charset=utf-8'), + '/style.css': ('static/style.css', 'text/css; charset=utf-8'), + '/browser/auto-news.user.js': ('browser/auto-news.user.js', 'text/javascript; charset=utf-8'), + '/browser/local-bridge.user.js': ('browser/local-bridge.user.js', 'text/javascript; charset=utf-8')} + if route not in files: + return self.send(404, {'error': '不存在'}) + name, mime = files[route] + file = ROOT / name + if not file.exists(): + return self.send(404, {'error': '请先运行 build_browser.py'}) + return self.send(200, file.read_bytes(), mime) + + def do_POST(self): + if not self.local(): + return self.send(403, {'error': 'Host 不匹配'}) + route = urlsplit(self.path).path + bridge = route.startswith('/bridge/') + expected = controller.bridge_token if bridge else controller.ui_token + provided = self.headers.get('X-Session-Token', '') + if not hmac.compare_digest(expected, provided) or (not bridge and not self.origin_ok()): + return self.send(403, {'error': '连接凭据无效，请重新配对'}) + if not bridge and not route.startswith('/api/'): + return self.send(404, {'error': '不存在'}) + try: + length = int(self.headers.get('Content-Length', 0)) + if not 0 < length <= 2 * 1024 * 1024: + raise ValueError('请求大小无效') + body = json.loads(self.rfile.read(length)) + if not isinstance(body, dict): + raise ValueError('请求必须是对象') + result = (controller.bridge if bridge else controller.ui)(route.rsplit('/', 1)[1], body) + self.send(200, result) + except (ValueError, KeyError, OSError) as error: + self.send(400, {'error': str(error)[:1000]}) + except Exception: + self.send(500, {'error': '内部错误；请停止当前任务并检查本地服务'}) + return Handler + + +def main(): + parser = argparse.ArgumentParser() + parser.add_argument('--port', type=int, default=8770) + parser.add_argument('--no-browser', action='store_true') + args = parser.parse_args() + controller = Controller() + server = ThreadingHTTPServer(('127.0.0.1', args.port), make_handler(controller)) + url = f'http://127.0.0.1:{args.port}/' + print('新闻工作台：' + url, flush=True) + if not args.no_browser: + webbrowser.open(url) + try: + server.serve_forever() + except KeyboardInterrupt: + controller.manager.stop.set() + controller.store.control('stop') + finally: + server.server_close() + + +if __name__ == '__main__': + main() diff --git a/articles.py b/articles.py new file mode 100644 index 0000000..53d5023 --- /dev/null +++ b/articles.py @@ -0,0 +1,116 @@ +"""Local article validation and portable packages. Never changes downloaded files.""" +import hashlib +import json +from pathlib import Path +import re +import unicodedata +from urllib.parse import unquote + +from modules.package import make_package + +MAX_PACKAGE_BYTES = 48 * 1024 * 1024 +FOOTER = re.compile(r'(?:^|\n)来源：([^\n]+)，如有侵权，请联系删除。\s*$') + + +def validate_images(body, directory): + """Conservative inline-image preflight; the importer remains the final parser.""" + if re.search(r'!\[[^\]]*\]\s*\[', body): + raise ValueError('不支持引用式图片，请改成内联图片路径') + for start in re.finditer(r'!\[[^\]]*\]\(', body): + pos, depth, quote, angle = start.end(), 1, '', False + begin = pos + while pos < len(body): + ch = body[pos] + if ch == '\\': + pos += 2 + continue + if quote: + if ch == quote: + quote = '' + elif not angle and depth == 1 and body[pos - 1].isspace() and ch in ('"', "'"): + quote = ch + elif ch == '<': + angle = True + elif ch == '>': + angle = False + elif not angle and ch == '(': + depth += 1 + elif not angle and ch == ')': + depth -= 1 + if not depth: + break + pos += 1 + if depth: + raise ValueError('图片引用括号不完整') + target = body[begin:pos].strip() + target = target[1:target.index('>')] if target.startswith('<') and '>' in target else re.sub(r'\s+["\'][\s\S]*["\']\s*$', '', target) + target = unquote(re.sub(r'\\([()\\ ])', r'\1', target)) + if re.match(r'^(?:[a-zA-Z][\w+.-]*:|/|\\)', target): + raise ValueError('图片必须使用目录内相对路径：' + target) + image = (directory / target).resolve() + if not image.is_relative_to(directory) or not image.is_file(): + raise ValueError('缺图或图片路径超出目录：' + target) + if image.suffix.lower() not in ('.jpg', '.jpeg', '.png', '.gif'): + raise ValueError('不支持的配图格式：' + target) + if not 0 < image.stat().st_size < 20 * 1024 * 1024: + raise ValueError('配图为空或达到 20 MiB：' + target) + + +def short_title(title, budget=80): + # Conservative UTF-16 budget: do not split astral characters / surrogate pairs. + if len(title.encode('utf-16-le')) // 2 <= budget: + return title + out = '' + for ch in title: + if len((out + ch).encode('utf-16-le')) // 2 > budget - 3: + break + out += ch + return out + '...' + + +def inspect_article(directory): + directory = Path(directory).resolve(strict=True) + candidates = sorted(directory.glob('*.md')) + if len(candidates) != 1: + raise ValueError('每个文章目录必须恰好包含一个 Markdown 文件') + md = candidates[0] + if not md.resolve().is_relative_to(directory): + raise ValueError('Markdown 不得链接到目录外') + raw = md.read_text(encoding='utf-8-sig') + heading = re.match(r'^\s*#\s+([^\n]+)\n?', raw) + title = (heading[1] if heading else md.stem).strip() + body = raw[heading.end():].strip() if heading else raw.strip() + footer = FOOTER.search(body) + if not footer: + raise ValueError('文末缺少标准来源尾注，请补充来源后再扫描') + source = footer[1].strip() + body = body[:footer.start()].strip() + if not title or not body: + raise ValueError('标题或正文为空') + validate_images(body, directory) + for file in directory.rglob('*'): + if file.suffix.lower() in ('.webp', '.avif', '.svg'): + raise ValueError('发现暂不支持的图片格式：' + file.name + '；请另存为 JPG/PNG/GIF 并更新引用') + pack = make_package(directory) + if sum(len(i['base64']) for i in pack['images']) > MAX_PACKAGE_BYTES: + raise ValueError('文章包超过 48 MiB，请减少单篇图片体积') + pack['title'] = short_title(title) + # Preserve body and exact final footer for the formatter; the original file stays intact. + pack['markdown'] = '# ' + pack['title'] + '\n\n' + body + '\n\n来源：' + source + '，如有侵权，请联系删除。\n' + content = unicodedata.normalize('NFC', body) + # Hash file contents, not directory/title; renamed copies share their article identity. + image_hashes = [] + for item in pack['images']: + import base64 + digest = hashlib.sha256(base64.b64decode(item['base64'])).hexdigest() + content = content.replace(item['path'], 'image:' + digest) + image_hashes.append(digest) + identity = hashlib.sha256((content + '\n' + '\n'.join(sorted(set(image_hashes)))).encode()).hexdigest() + metadata = {} + marker = directory / '.article.json' + if marker.is_file(): + metadata = json.loads(marker.read_text()) + return dict(article_key=identity, markdown_sha256=hashlib.sha256(md.read_bytes()).hexdigest(), + directory=str(directory), original_title=title, title=pack['title'], source=source, + image_count=len(pack['images']), package=pack, + source_keys=metadata.get('fingerprints', [])) diff --git a/browser/auto-news.user.js b/browser/auto-news.user.js new file mode 100644 index 0000000..b005c44 --- /dev/null +++ b/browser/auto-news.user.js @@ -0,0 +1,850 @@ +// ==UserScript== +// @name 新闻工作台 · 导入排版与流程 +// @namespace local.dww11.auto-news +// @version 0.1.0 +// @match https://www.dww11.com/* +// @match https://dww11.com/* +// @match https://house.dww11.com/* +// @grant none +// @run-at document-idle +// @noframes +// ==/UserScript== + + +(function (root, factory) { + 'use strict'; + const core = factory(); + if (typeof module === 'object' && module.exports) module.exports = core; + else core.mount(root); +})(typeof window === 'undefined' ? null : window, function () { + 'use strict'; + const VERSION = '1.0.0'; + const MAX_IMAGE_SIZE = 20 * 1024 * 1024; + const IMAGE_EXT = /\.(?:jpe?g|png|gif)$/i; + + function normalizePath(path) { + const parts = []; + const value = String(path).replace(/\\/g, '/').normalize('NFC'); + if (/^(?:\/|[a-z]:|[a-z]+:)/i.test(value)) throw new Error('请使用目录内的相对路径：' + path); + for (const part of value.split('/')) { + if (!part || part === '.') continue; + if (part === '..') { + if (!parts.length) throw new Error('图片路径超出所选目录：' + path); + parts.pop(); + } else parts.push(part); + } + return parts.join('/'); + } + + function imagePath(mdPath, target) { + if (/^(?:[a-z][\w+.-]*:|\/\/|\/)/i.test(target)) throw new Error('图片必须在所选目录内，请先下载：' + target); + let decoded; + try { decoded = decodeURIComponent(target); } catch { throw new Error('图片路径编码无效：' + target); } + return normalizePath(mdPath.slice(0, mdPath.lastIndexOf('/') + 1) + decoded); + } + + // A small, intentionally bounded Markdown reader. Raw HTML is never executed. + // Links/images support balanced parentheses, angle destinations and optional titles. + function readLink(text, start) { + const image = text.startsWith('![', start); + if (!image && text[start] !== '[') return null; + const left = start + (image ? 2 : 1); + let end = left; + for (; end < text.length; end++) { + if (text[end] === '\\') { end++; continue; } + if (text[end] === ']') break; + } + if (text.slice(end, end + 2) !== '](') return null; + let pos = end + 2, depth = 1, quoted = '', angle = false; + for (; pos < text.length; pos++) { + const ch = text[pos]; + if (ch === '\\') { pos++; continue; } + if (quoted) { if (ch === quoted) quoted = ''; continue; } + if (!angle && depth === 1 && /\s/.test(text[pos - 1]) && (ch === '"' || ch === "'")) { quoted = ch; continue; } + if (ch === '<') { angle = true; continue; } + if (ch === '>') { angle = false; continue; } + if (!angle && ch === '(') depth++; + if (!angle && ch === ')' && --depth === 0) break; + } + if (depth) return null; + let target = text.slice(end + 2, pos).trim(); + const destination = target.match(/^<([^>]+)>\s*(?:["'][\s\S]*["'])?$/); + target = destination ? destination[1] : target.replace(/\s+["'][\s\S]*["']\s*$/, ''); + target = target.replace(/\\([()\\ ])/g, '$1'); + return { image, label: text.slice(left, end), target, end: pos + 1 }; + } + + function inline(text, onImage) { + let out = ''; + for (let pos = 0; pos < text.length;) { + if (text[pos] === '\\' && pos + 1 < text.length) { out += text[pos + 1]; pos += 2; continue; } + const link = readLink(text, pos); + if (link) { + if (link.image) out += onImage(link.target, link.label); + else if (/^(https?:\/\/|mailto:)/i.test(link.target) && !/[\[\]\r\n"']/.test(link.target)) { + out += '[url=' + link.target + ']' + inline(link.label, onImage) + '[/url]'; + } else out += link.label + ' (' + link.target + ')'; + pos = link.end; + continue; + } + if (text[pos] === '`') { + const end = text.indexOf('`', pos + 1); + if (end > pos + 1) { out += text.slice(pos + 1, end); pos = end + 1; continue; } + } + let matched = false; + for (const [mark, tag] of [['**', 'b'], ['__', 'b'], ['~~', 's'], ['*', 'i'], ['_', 'i']]) { + if (!text.startsWith(mark, pos) || (mark === '_' && /\w/.test(text[pos - 1] || ''))) continue; + const end = text.indexOf(mark, pos + mark.length); + if (end <= pos + mark.length) continue; + out += '[' + tag + ']' + inline(text.slice(pos + mark.length, end), onImage) + '[/' + tag + ']'; + pos = end + mark.length; matched = true; break; + } + if (!matched) out += text[pos++]; + } + return out; + } + + function markdownToBBCode(markdown, onImage) { + const lines = markdown.replace(/\r\n?/g, '\n').split('\n'); + const output = []; + let list = '', quote = false, code = false, fence = ''; + const closeList = () => { if (list) output.push('[/list]'); list = ''; }; + for (let index = 0; index < lines.length; index++) { + const line = lines[index]; + const codeMark = line.match(/^\s*(`{3,}|~{3,})/); + if (codeMark && (!code || codeMark[1][0] === fence)) { + closeList(); + output.push(code ? '[/code]' : '[code]'); + code = !code; fence = codeMark[1][0]; continue; + } + if (code) { output.push(line.replace(/\[\/code\]/gi, '［/code］')); continue; } + const quoted = /^\s*>\s?/.test(line); + if (quoted !== quote) { closeList(); output.push(quoted ? '[quote]' : '[/quote]'); quote = quoted; } + const content = quoted ? line.replace(/^\s*>\s?/, '') : line; + const item = content.match(/^\s*(?:([-+*])|\d+[.)])\s+(.+)$/); + if (item) { + const type = item[1] ? '[list]' : '[list=1]'; + if (list !== type) { closeList(); output.push(type); list = type; } + output.push('[*]' + inline(item[2], onImage)); continue; + } + closeList(); + const heading = content.match(/^\s{0,3}(#{1,6})\s+(.+?)\s*#*$/); + if (heading) output.push('[b]' + inline(heading[2], onImage) + '[/b]'); + else if (/^\s*(?:---+|\*\*\*+|___+)\s*$/.test(content)) output.push('[hr]'); + else output.push(inline(content, onImage)); + } + closeList(); + if (quote) output.push('[/quote]'); + if (code) output.push('[/code]'); + return output.join('\n').trim(); + } + + function compile(markdown, mdPath, fileMap, titleOverride) { + let body = String(markdown).replace(/^\uFEFF/, '').replace(/\r\n?/g, '\n'); + const firstHeading = body.match(/^\s*#\s+([^\n]+)\n?/); + const title = String(titleOverride || firstHeading?.[1] || mdPath.split('/').pop().replace(/\.md$/i, '')).trim(); + if (firstHeading) body = body.slice(firstHeading[0].length).trim(); + if (!title || Array.from(title).length > 80) throw new Error('标题为空或超过 80 字，请修改 Markdown 标题后重试。'); + if (!body.trim()) throw new Error('正文为空。'); + const warnings = []; + if (/<\/?[a-z][^>]*>/i.test(body)) warnings.push('存在 HTML，将作为文字保留；请检查排版。'); + if (/^\s*\|.*\|\s*$/m.test(body)) warnings.push('表格暂按原文保留，需手动检查。'); + if (/!\[[^\]]*\]\s*\[[^\]]*\]/.test(body) || /^\s*\[[^\]]+\]:/m.test(body)) { + throw new Error('暂不支持引用式 Markdown 图片/链接，请改成 ![](图片路径) 或 [文字](网址)。'); + } + const images = new Map(); + // Validate every image before any network request; repeated references upload once. + markdownToBBCode(body, (target) => { + const path = imagePath(mdPath, target); + const file = fileMap.get(path); + if (!file) throw new Error('找不到配图：' + path); + if (!IMAGE_EXT.test(path)) throw new Error('网站仅支持 JPG、JPEG、PNG、GIF：' + path); + if (!file.size || file.size >= MAX_IMAGE_SIZE) throw new Error('配图为空或达到 20 MB：' + path); + images.set(path, file); + return '[图片：' + path + ']'; + }); + return { title, body, mdPath, images, warnings, + render(aids) { + return markdownToBBCode(body, target => { + const path = imagePath(mdPath, target); + const aid = aids.get(path); + if (!/^[1-9]\d*$/.test(String(aid))) throw new Error('配图尚未上传：' + path); + return '[attachimg]' + aid + '[/attachimg]'; + }); + } + }; + } + + async function prepareFiles(files, markdownPath) { + const fileMap = new Map(); + for (const file of Array.from(files)) { + const path = normalizePath(file.webkitRelativePath || file.name); + if (fileMap.has(path)) throw new Error('文件路径重复：' + path); + fileMap.set(path, file); + } + const candidates = Array.from(fileMap.keys()).filter(p => /\.md$/i.test(p)).sort(); + if (!candidates.length) throw new Error('所选目录中没有 .md 文件。'); + if (!markdownPath && candidates.length > 1) return { candidates, files: Array.from(files) }; + const mdPath = markdownPath || candidates[0]; + const md = fileMap.get(mdPath); + if (!md) throw new Error('指定的 Markdown 文件不存在。'); + return compile(await md.text(), mdPath, fileMap); + } + + async function preparePackage(data) { + if (!data || data.schemaVersion !== 1 || typeof data.markdown !== 'string' || !Array.isArray(data.images)) { + throw new Error('文章包格式错误，需要 schemaVersion: 1、markdown 和 images。'); + } + const map = new Map(); + for (const item of data.images) { + const path = normalizePath(item.path); + if (map.has(path)) throw new Error('文章包图片路径重复：' + path); + let blob = item.blob; + if (!blob && typeof item.base64 === 'string') { + const binary = atob(item.base64); + blob = new Blob([Uint8Array.from(binary, ch => ch.charCodeAt(0))], { type: item.mime || 'application/octet-stream' }); + } + if (!blob || typeof blob.arrayBuffer !== 'function') throw new Error('文章包缺少图片数据：' + path); + map.set(path, blob); + } + return compile(data.markdown, normalizePath(data.markdownPath || 'article.md'), map, data.title); + } + + function parseAid(text) { + const value = String(text).trim(); + // The site's actual WebUploader adapter uses a positive integer response. + if (!/^(?:[1-9]\d*|"[1-9]\d*")$/.test(value)) throw new Error('服务器未返回有效附件编号（可能登录过期、超出权限或上传失败）。'); + return value.replace(/"/g, ''); + } + + function mount(win) { + const doc = win.document; + const params = new URLSearchParams(win.location.search); + if (params.get('mod') !== 'post' || params.get('action') !== 'newthread' || !doc.querySelector('#subject') || !doc.querySelector('#e_textarea')) return; + if (win.DWW11Importer) return; + let article = null, busy = false, candidates = null, lastResult = null, savedBackup = null, stageRevision = 0; + const cache = new Map(), urls = [], logs = []; + const host = doc.createElement('div'); + host.id = 'dww11-importer'; + host.style.cssText = 'position:fixed;right:18px;bottom:18px;z-index:2147483000'; + const shadow = host.attachShadow({ mode: 'open' }); + shadow.innerHTML = `
本地文章导入 · 1.0
+ 选择整个文章文件夹，检查后上传配图并填写。发布由你操作。网站自带的自动保存仍可能运行。 +

+ + +

尚未选择目录

+ + +
`; + doc.body.appendChild(host); + const $ = id => shadow.getElementById(id); + const summary = () => ({ version: VERSION, busy, ready: !!article, title: article?.title || null, + markdownPath: article?.mdPath || null, imageCount: article?.images.size || 0, + warnings: article?.warnings || [], result: lastResult }); + function notify(phase, message, extra = {}) { + $('status').textContent = message; + $('status').className = phase === 'error' ? 'error' : phase === 'complete' ? 'success' : ''; + logs.push({ time: new Date().toISOString(), phase, message, ...extra }); + $('log').hidden = false; + $('log').textContent = logs.slice(-8).map(l => l.message).join('\n'); + win.dispatchEvent(new CustomEvent('dww11-importer:progress', { detail: { phase, message, ...extra } })); + } + function releasePreviews() { while (urls.length) URL.revokeObjectURL(urls.pop()); } + function clearStage() { + article = null; lastResult = null; candidates = null; releasePreviews(); + $('preview').hidden = true; $('md').hidden = true; $('import').disabled = true; + } + function showArticle(prepared) { + article = prepared; lastResult = null; releasePreviews(); + $('preview').hidden = false; + $('title').textContent = article.title; + $('body').textContent = article.body; + $('warnings').textContent = article.warnings.join('；'); + $('images').replaceChildren(); + for (const [path, blob] of article.images) { + const img = doc.createElement('img'); + img.src = URL.createObjectURL(blob); urls.push(img.src); img.alt = path; img.title = path; + $('images').appendChild(img); + } + $('import').disabled = false; + notify('ready', `已检查：${article.images.size} 张图片。点击“上传配图并填写”开始导入。`); + return summary(); + } + async function stageFiles(files, options = {}) { + if (busy) throw new Error('正在导入，请稍候。'); + clearStage(); + const revision = ++stageRevision; + const list = Array.from(files); + const prepared = await prepareFiles(list, options.markdownPath); + if (revision !== stageRevision) return { cancelled: true }; + if (prepared.candidates) { + candidates = prepared.files; + $('md').replaceChildren(new Option('请选择目录中的 Markdown 文件', '')); + for (const path of prepared.candidates) $('md').appendChild(new Option(path, path)); + $('md').hidden = false; + notify('choose-markdown', '目录中有多个 Markdown 文件，请选择一篇。'); + return { candidates: prepared.candidates }; + } + return showArticle(prepared); + } + async function stagePackage(data) { + if (busy) throw new Error('正在导入，请稍候。'); + clearStage(); + const revision = ++stageRevision; + const prepared = await preparePackage(data); + if (revision !== stageRevision) return { cancelled: true }; + return showArticle(prepared); + } + const snapshot = () => ({ title: doc.querySelector('#subject').value, + mode: Number(win.wysiwyg), text: win.getEditorContents() }); + function assertEditor() { + for (const name of ['getEditorContents', 'switchEditor']) { + if (typeof win[name] !== 'function') throw new Error('未识别到网站编辑器：' + name + '。请刷新页面后重试。'); + } + if (!win.imgUpload?.settings || typeof win.updateImageList !== 'function') throw new Error('网站图片上传组件尚未就绪，请刷新后重试。'); + if (Number(win.allowbbcode) === 0 || Number(win.allowimgcode) === 0) throw new Error('当前版块或账号不支持正文格式/图片。'); + } + async function uploadImage(blob, path, settings, signal) { + signal?.throwIfAborted(); + const url = new URL(settings.upload_url, win.location.href); + if (url.origin !== win.location.origin || url.pathname !== '/misc.php' || url.searchParams.get('operation') !== 'upload') { + throw new Error('上传地址与预期不符，已停止。'); + } + const hash = Array.from(new Uint8Array(await win.crypto.subtle.digest('SHA-256', await blob.arrayBuffer())), n => n.toString(16).padStart(2, '0')).join(''); + const key = url.href + ':' + settings.post_params.uid + ':' + hash; + if (cache.has(key)) { notify('upload', '复用已上传图片：' + path); return cache.get(key); } + const data = new FormData(); + for (const [key, value] of Object.entries(settings.post_params)) data.append(key, String(value)); + data.set('type', 'image'); + data.set('filetype', blob.type || (/\.png$/i.test(path) ? 'image/png' : /\.gif$/i.test(path) ? 'image/gif' : 'image/jpeg')); + data.append(settings.file_post_name || 'Filedata', blob, path.split('/').pop()); + const control = new AbortController(), timer = setTimeout(() => control.abort(), 90000); + try { + signal?.throwIfAborted(); + signal?.addEventListener('abort', () => control.abort(), { once: true }); + const response = await win.fetch(url.href, { method: 'POST', body: data, credentials: 'same-origin', redirect: 'error', signal: control.signal }); + if (!response.ok) throw new Error('图片上传请求失败：HTTP ' + response.status); + const aid = parseAid(await response.text()); + cache.set(key, aid); + return aid; + } catch (error) { + if (error.name === 'AbortError') throw new Error('上传超时；该图片可能已到达服务器，请检查网站图片列表后再重试。'); + throw error; + } finally { clearTimeout(timer); } + } + async function registerImages(aids, signal) { + signal?.throwIfAborted(); + if (!aids.length) return; + const ids = new Set(aids); + doc.querySelectorAll('#imgattachlist [id^="image_td_"],#imgattachlist [id^="image_"]').forEach(el => { + const id = el.id.match(/^(?:image_td_|image_)(\d+)$/)?.[1]; if (id) ids.add(id); + }); + const ready = () => aids.every(id => doc.getElementById('image_' + id)); + if (ready()) return; + // Use the site's own list loader, which registers attachment form fields too. + win.updateImageList(1, Array.from(ids).join('|')); + await new Promise((resolve, reject) => { + const timer = setTimeout(() => { observer.disconnect(); reject(new Error('图片已上传，但网站图片列表加载超时。重试会复用本页已上传图片。')); }, 25000); + signal?.addEventListener('abort', () => { clearTimeout(timer); observer.disconnect(); reject(new Error('流程已终止')); }, { once: true }); + const check = () => { if (ready()) { clearTimeout(timer); observer.disconnect(); resolve(); } }; + const observer = new MutationObserver(check); + observer.observe(doc.body, { childList: true, subtree: true }); check(); + }); + } + function setEditor(title, bbcode) { + win.switchEditor(0); + if (Number(win.wysiwyg) !== 0) throw new Error('无法切换编辑器为纯文本模式。'); + const textarea = doc.querySelector('#e_textarea'); + textarea.value = bbcode; + doc.querySelector('#subject').value = title; + for (const el of [textarea, doc.querySelector('#subject')]) { + el.dispatchEvent(new Event('input', { bubbles: true })); el.dispatchEvent(new Event('change', { bubbles: true })); + } + // Let Discuz generate the WYSIWYG content with native attachment metadata. + win.switchEditor(1); + const switcher = doc.querySelector('#e_switchercheck'); + if (switcher) switcher.checked = Number(win.wysiwyg) === 0; + } + async function importPrepared(options = {}) { + const { signal, automatic = false } = options; + signal?.throwIfAborted(); + if (busy) throw new Error('正在导入，请勿重复点击。'); + if (!article) throw new Error('请先选择文章目录或文章包。'); + assertEditor(); + for (const id of ['bbcodeoff', 'htmlon']) { + if (doc.getElementById(id)?.checked) throw new Error('请先关闭“禁用 Discuz! 代码”和“HTML 代码”，再导入。'); + } + const before = snapshot(); + if ((before.title.trim() || before.text.replace(/<[^>]*>/g, '').trim() || / { throw new Error('编辑器已有内容，请人工处理旧稿后重试'); })() : !win.confirm('当前编辑器已有内容。导入将替换标题和正文，是否继续？'))) return { cancelled: true }; + const selected = article; + busy = true; + const controls = ['choose', 'package', 'import', 'md'].map($); + controls.forEach(el => { el.disabled = true; }); + // Prevent accidental submission of a partly imported article. + const blockSubmit = event => { event.preventDefault(); event.stopImmediatePropagation(); notify('busy', '正在导入，请等待完成后再操作发布。'); }; + const form = doc.querySelector('#postform'); + form.addEventListener('submit', blockSubmit, true); + const submitButtons = Array.from(form.querySelectorAll('button[type="submit"],button[name],input[type="submit"]')); + const previousDisabled = submitButtons.map(el => el.disabled); + submitButtons.forEach(el => { el.disabled = true; }); + let committed = false; + try { + const aids = new Map(); + const settings = win.imgUpload.settings; + const max = Math.min(MAX_IMAGE_SIZE, Number(settings.file_size_limit) * 1024 || MAX_IMAGE_SIZE); + for (const [path, blob] of selected.images) if (blob.size >= max) throw new Error('配图超过当前网站限制：' + path); + let index = 0; + for (const [path, blob] of selected.images) { + notify('upload', `上传 ${++index}/${selected.images.size}：${path}`, { completed: index - 1, total: selected.images.size }); + aids.set(path, await uploadImage(blob, path, settings, signal)); + } + notify('register', '正在加载网站图片列表…'); + await registerImages(Array.from(new Set(aids.values())), signal); + signal?.throwIfAborted(); + const now = snapshot(); + if ((now.title !== before.title || now.text !== before.text) && (automatic ? (() => { throw new Error('上传期间编辑器被修改，已保留当前内容'); })() : !win.confirm('上传期间你修改了编辑器。是否用导入文章替换最新内容？'))) { + notify('cancelled', '已保留当前正文；图片已上传，可稍后再次导入。'); return { cancelled: true }; + } + const backup = snapshot(); + const bbcode = selected.render(aids); + // Preserve a local, downloadable snapshot before changing title or body. + savedBackup = { title: backup.title, content: backup.text, mode: backup.mode, createdAt: new Date().toISOString() }; + try { + for (const id of ['bbcodeoff', 'htmlon']) { + const el = doc.getElementById(id); + if (el && id === 'bbcodeoff' && el.checked) throw new Error('请先取消“禁用 Discuz! 代码”，再重试。'); + if (el && id === 'htmlon' && el.checked) throw new Error('请先关闭“HTML 代码”，再重试。'); + } + signal?.throwIfAborted(); + setEditor(selected.title, bbcode); + const raw = win.getEditorContents(); + if (Number(win.wysiwyg) === 1) { + for (const id of new Set(aids.values())) if (!raw.includes('attachimg_' + id)) throw new Error('富文本图片转换未通过检查。'); + } else if (raw !== bbcode) throw new Error('正文填写校验失败。'); + if (doc.querySelector('#subject').value !== selected.title) throw new Error('标题填写校验失败。'); + committed = true; + } catch (error) { + // Restore the exact editor representation saved immediately before filling. + win.switchEditor(backup.mode); + if (backup.mode) win.editdoc.body.innerHTML = backup.text; + else doc.querySelector('#e_textarea').value = backup.text; + doc.querySelector('#subject').value = backup.title; + const switcher = doc.querySelector('#e_switchercheck'); if (switcher) switcher.checked = !backup.mode; + throw error; + } + lastResult = { title: selected.title, images: Object.fromEntries(aids), completedAt: new Date().toISOString() }; + notify('complete', `已填写标题、正文和 ${aids.size} 张配图。请检查排版，随后手动发表。`); + return lastResult; + } catch (error) { + notify('error', error.message + (committed ? '' : ' 标题和正文未替换；已上传的图片会保留。')); + throw error; + } finally { + busy = false; form.removeEventListener('submit', blockSubmit, true); + submitButtons.forEach((el, index) => { el.disabled = previousDisabled[index]; }); + controls.forEach(el => { el.disabled = false; }); + $('import').disabled = !article; + } + } + function downloadJSON(value, filename) { + const url = URL.createObjectURL(new Blob([JSON.stringify(value, null, 2)], { type: 'application/json' })); + const link = doc.createElement('a'); link.href = url; link.download = filename; link.click(); + setTimeout(() => URL.revokeObjectURL(url), 1000); + } + // Public v1 interface. Staging is read-only; importPrepared is the explicit upload/fill step. + // No postMessage listener, localhost service, publishing endpoint or saved credentials. + const api = Object.freeze({ version: VERSION, schemaVersion: 1, stageFiles, stagePackage, + getState: summary, openPicker: () => { if (!busy) $('folder').click(); }, importPrepared, + getBackup: () => savedBackup }); + win.DWW11Importer = api; + $('choose').onclick = () => { $('folder').value = ''; $('folder').click(); }; + $('package').onclick = () => { $('json').value = ''; $('json').click(); }; + const handleError = error => notify('error', error.message || String(error)); + $('folder').onchange = () => stageFiles($('folder').files).catch(handleError); + $('json').onchange = async () => { + try { const file = $('json').files[0]; if (file) await stagePackage(JSON.parse(await file.text())); } + catch (error) { handleError(error); } + }; + $('md').onchange = () => { + const files = candidates, path = $('md').value; + if (files && path) stageFiles(files, { markdownPath: path }).catch(handleError); + }; + $('import').onclick = () => importPrepared().catch(handleError); + $('diagnostics').onclick = () => downloadJSON({ ...summary(), logs }, 'dww11-import-diagnostics.json'); + win.addEventListener('pagehide', releasePreviews, { once: true }); + } + return { VERSION, normalizePath, imagePath, readLink, markdownToBBCode, compile, prepareFiles, preparePackage, parseAid, mount }; +}); + +// Extracted from dww11-wechat-oneclick.user.js v1.0.9; package source is authoritative. +(() => { +'use strict'; +const cleanText = value => String(value || '').replace(/\s+/g, ' ').trim(); + function flattenParagraphs(body) { + const selector = 'p,div,section,article,figure,figcaption,h1,h2,h3,h4,h5,h6'; + const marker = () => { + const br = body.ownerDocument.createElement('br'); + br.dataset.dww11Boundary = '1'; return br; + }; + for (const block of Array.from(body.querySelectorAll(selector)).reverse()) { + if (block.closest('table,ul,ol,blockquote')) continue; + block.replaceWith(marker(), ...block.childNodes, marker()); + } + let previous = false, pending = []; + function finish() { + const actual = pending.filter(br => !br.hasAttribute('data-dww11-boundary')); + let retained = false; + for (const br of pending) { + if (!br.hasAttribute('data-dww11-boundary')) continue; + if (previous && !actual.length && !retained) { br.removeAttribute('data-dww11-boundary'); retained = true; } + else br.remove(); + } + pending = []; + } + const walker = body.ownerDocument.createTreeWalker(body, NodeFilter.SHOW_ELEMENT | NodeFilter.SHOW_TEXT); + const nodes = []; while (walker.nextNode()) nodes.push(walker.currentNode); + for (const node of nodes) { + if (node.nodeType === 1 && node.tagName === 'BR') pending.push(node); + else if ((node.nodeType === 3 && node.textContent.trim()) || (node.nodeType === 1 && ['IMG', 'VIDEO', 'HR', 'IFRAME'].includes(node.tagName))) { + finish(); previous = true; + } + } + // 末尾不保留由容器边界制造的额外换行。 + for (const br of pending) if (br.hasAttribute('data-dww11-boundary')) br.remove(); + } + function spaceImages(body) { + let previous = null, gapNodes = [], blankLines = 0; + const changes = []; + function content(kind, node) { + if (previous && previous.kind !== kind) { + let anchor = node; + while (anchor.parentElement && anchor.parentElement !== body && + !['TD', 'TH', 'LI', 'BLOCKQUOTE'].includes(anchor.parentElement.tagName) && !anchor.parentElement.contains(previous.node)) anchor = anchor.parentElement; + changes.push({ anchor, nodes: gapNodes.slice(), count: Math.max(2, blankLines) }); + } + previous = { kind, node }; gapNodes = []; blankLines = 0; + } + function visit(node) { + if (node.nodeType === 3) { + if (node.textContent.trim()) content('text', node); else gapNodes.push(node); + return; + } + if (node.nodeType !== 1 || ['SCRIPT', 'STYLE', 'NOSCRIPT'].includes(node.tagName)) return; + if (node.tagName === 'BR') { gapNodes.push(node); blankLines++; return; } + if (node.tagName === 'IMG') { content('image', node); return; } + for (const child of node.childNodes) visit(child); + } + for (const child of body.childNodes) visit(child); + for (const { anchor, nodes, count } of changes) { + for (const node of nodes) node.remove(); + const fragment = body.ownerDocument.createDocumentFragment(); + for (let i = 0; i < count; i++) fragment.append(body.ownerDocument.createElement('br')); + anchor.parentNode.insertBefore(fragment, anchor); + } + } + function formatBody(body, author, sourceText = null) { + const doc = body.ownerDocument; + body.querySelectorAll('[data-dww11-wx-source="1"]').forEach(el => el.remove()); + // Discuz 会把内联 color 值直接转为 [color=…]。 + // !important 不能出现在该值中；颜色和字号只用原生 FONT 属性。 + for (const el of [body, ...body.querySelectorAll('*')]) { + if (['SCRIPT', 'STYLE'].includes(el.tagName)) continue; + for (const property of ['font', 'font-size', 'color', '-webkit-text-fill-color']) { + el.style.removeProperty(property); + } + // 其他排版属性也不保留 CSS 优先级，避免它泄漏进论坛标签。 + for (const property of Array.from(el.style)) { + if (el.style.getPropertyPriority(property)) { + el.style.setProperty(property, el.style.getPropertyValue(property)); + } + } + if (!el.style.cssText) el.removeAttribute('style'); + } + // 去掉采集器或旧版脚本生成的嵌套 FONT，保留其中的内容和图片。 + for (const font of Array.from(body.querySelectorAll('font'))) { + font.replaceWith(...font.childNodes); + } + flattenParagraphs(body); + spaceImages(body); + // 所有正文内容和换行放在同一 FONT 中。不能使用只有 BR 的空 FONT： + // 论坛转换器可能清除空格式标签，导致空行退回默认1号或直接丢失。 + const articleFont = doc.createElement('font'); + articleFont.size = '4'; articleFont.color = '#000000'; + articleFont.dataset.dww11WxBody = '1'; + articleFont.append(...body.childNodes); + body.append(articleFont); + // A 自身的浏览器默认蓝色会覆盖外层继承色，链接文字另设黑色。 + for (const link of articleFont.querySelectorAll('a')) { + const linkFont = doc.createElement('font'); + linkFont.size = '4'; linkFont.color = '#000000'; + linkFont.append(...link.childNodes); link.append(linkFont); + } + // 只用于编辑器图片适配；帖子展示仍交给网站原有图片/附件规则。 + for (const img of articleFont.querySelectorAll('img')) { + img.style.maxWidth = '100%'; img.style.height = 'auto'; + } + const source = doc.createElement('p'); + source.dataset.dww11WxSource = '1'; + const font = doc.createElement('font'); + font.size = '1'; font.color = '#c0c0c0'; + const lines = (sourceText ?? `来源：${author}，如有侵权，请联系删除。`).split('\n'); + lines.forEach((line, index) => { + if (index) font.append(doc.createElement('br')); + font.append(doc.createTextNode(line)); + }); + source.append(font); body.append(source); + } + function existingSource(body) { + // 按段落和 BR 读取末尾逻辑行，兼容嵌套 FONT、纯文本及末尾空段落。 + const lines = []; + let parts = []; + function flush() { + const text = cleanText(parts.map(part => part.node.textContent.slice(part.start, part.end)).join('')); + if (text) lines.push({ text, parts }); + parts = []; + } + function visit(node) { + if (node.nodeType === 3) { + // 保留文本中的显式换行，并记录精确位置，避免删除同容器中的正文。 + const value = node.textContent; + let start = 0; + for (let i = 0; i <= value.length; i++) { + if (i !== value.length && value[i] !== '\n') continue; + // HTML 缩进换行通常只是空白；只有后续是来源或版权行才分行。 + if (i < value.length && !/^\s*(?:(?:来源|文章来源|本文来源|图文来源|文字来源|作者|作者信息|来源作者|转自|转载自|出处)\s*[:：]|如有侵权|若有侵权|侵权请|转载请|版权归)/.test(value.slice(i + 1))) continue; + if (i > start) parts.push({ node, start, end: i }); + if (i < value.length) flush(); + start = i + 1; + } + return; + } + if (node.nodeType !== 1 || ['SCRIPT', 'STYLE', 'NOSCRIPT'].includes(node.tagName)) return; + if (node.tagName === 'BR') { flush(); return; } + if (['IMG', 'VIDEO', 'AUDIO', 'IFRAME', 'HR'].includes(node.tagName)) { + flush(); lines.push({ text: '\ufffc', parts: [] }); return; + } + const block = /^(P|DIV|SECTION|ARTICLE|FIGURE|FIGCAPTION|H[1-6]|LI|TR|BLOCKQUOTE|PRE)$/.test(node.tagName); + if (block) flush(); + for (const child of node.childNodes) visit(child); + if (block) flush(); + } + for (const child of body.childNodes) visit(child); + flush(); + let first = -1; + for (let i = lines.length - 1; i >= 0; i--) { + if (/^(?:来源|文章来源|本文来源|图文来源|文字来源|作者|作者信息|来源作者|转自|转载自|出处)\s*[:：]\s*\S/.test(lines[i].text)) { + first = i; + } else if (!/^(?:如有侵权|若有侵权|侵权请|转载请|版权归)/.test(lines[i].text)) { + break; + } + } + if (first < 0) return null; + const start = lines[first].parts[0]; + const range = body.ownerDocument.createRange(); + range.setStart(start.node, start.start); + range.setEnd(body, body.childNodes.length); + return { + text: lines.slice(first).map(line => line.text).join('\n'), + remove: () => range.deleteContents() + }; + } + +window.DWW11Formatter = Object.freeze({ + format(expectedSource) { + if (Number(window.wysiwyg) !== 1) throw new Error('请切换到可视化编辑器后排版'); + const body = document.querySelector('#e_iframe')?.contentDocument?.body; + if (!body) throw new Error('编辑器未就绪'); + const footer = existingSource(body); + const expected = `来源：${expectedSource}，如有侵权，请联系删除。`; + if (!footer || footer.text !== expected) throw new Error('文末来源与文章包不一致，请人工检查'); + const images = [...body.querySelectorAll('img')].map(x => x.id + ':' + x.getAttribute('src')); + const backup = body.innerHTML; + try { + footer.remove(); + formatBody(body, expectedSource, expected); + const after = [...body.querySelectorAll('img')].map(x => x.id + ':' + x.getAttribute('src')); + if (JSON.stringify(images) !== JSON.stringify(after)) throw new Error('排版后图片标识或顺序改变'); + if (body.querySelectorAll('[data-dww11-wx-source="1"]').length !== 1) throw new Error('来源尾注数量异常'); + body.dispatchEvent(new Event('input', {bubbles:true})); + return {images: after, source: expected}; + } catch (error) { body.innerHTML = backup; throw error; } + } +}); +})(); + +/* Page-side orchestrator. This file never clicks or submits the publication form. */ +(() => { + 'use strict'; + if (window.DWW11NewsRunner) return; + window.DWW11NewsRunner = true; + const SLOT='auto-news-current'; + const owner=sessionStorage.getItem('auto-news-owner') || crypto.randomUUID(); + sessionStorage.setItem('auto-news-owner',owner); + let run=null, working=false, halted=true, aborter=null, active=null, tickBusy=false; + const pending=new Map(); + function rpc(route,body={}) { + return new Promise((resolve,reject)=>{ + const id=crypto.randomUUID(); + const timer=setTimeout(()=>{pending.delete(id);reject(new Error('本地连接无响应'));},65000); + pending.set(id,{resolve,reject,timer}); + document.dispatchEvent(new CustomEvent('dww11:local-request',{detail:JSON.stringify({id,route,body:{owner,...body}})})); + }); + } + document.addEventListener('dww11:local-response',event=>{ + let data;try{data=JSON.parse(event.detail);}catch{return;} + const waiter=pending.get(data.id);if(!waiter)return; + clearTimeout(waiter.timer);pending.delete(data.id); + data.error?waiter.reject(new Error(data.error)):waiter.resolve(data.value); + }); + const status=message=>document.dispatchEvent(new CustomEvent('dww11:connection-status',{detail:message})); + document.addEventListener('dww11:auto-stop',()=>{halted=true;aborter?.abort(new Error('流程已终止'));}); + function account() { + const element=document.querySelector('#mumucms_username'); + if(!element)return null; + const name=[...element.childNodes].filter(n=>n.nodeType===Node.TEXT_NODE).map(n=>n.textContent).join('').trim(); + const links=[element,...element.querySelectorAll('a')].filter(e=>e.href); + let uid=null; + for(const link of links) { + const href=link.href; + uid=new URL(href,location.href).searchParams.get('uid') || href.match(/space-uid-(\d+)/)?.[1]; + if(uid)break; + } + return uid&&name?{uid,name}:null; + } + function extension() { + try{return JSON.parse(document.querySelector('#dww11-extension-panel')?.getAttribute('data-auto-news-state') || '{}');}catch{return {};} + } + function assertLive(epoch) { + if(halted||!run?.running||run.epoch!==epoch)throw new Error('流程已暂停或终止'); + if(active?.account?.uid!==account()?.uid)throw new Error('当前账号与任务不一致'); + } + function editorSnapshot() { + const body=document.querySelector('#e_iframe')?.contentDocument?.body; + if(!body)throw new Error('找不到可视化编辑器'); + return {title:document.querySelector('#subject')?.value || '', + images:[...body.querySelectorAll('img')].map(x=>({id:x.id,src:x.getAttribute('src')})), + // Snapshot only final submitted content; never includes hidden tokens or the full form. + html:body.innerHTML.slice(0,500000), text:body.innerText.slice(0,100000)}; + } + function saveLocal(value) {sessionStorage.setItem(SLOT,JSON.stringify(value));} + function loadLocal(){try{return JSON.parse(sessionStorage.getItem(SLOT)||'null');}catch{return null;}} + async function event(state,extra={}) {return rpc('event',{id:active.id,state,epoch:run.epoch,...extra});} + async function fail(error) { + status(error.message); + if(active)try{await event('needs_attention',{error:error.message});}catch{} + halted=true;aborter?.abort();document.dispatchEvent(new CustomEvent('dww11:auto-stop')); + } + function editorPage(job) { + const u=new URL(location.href); + return u.searchParams.get('mod')==='post'&&u.searchParams.get('action')==='newthread'&&u.searchParams.get('fid')===String(job.fid); + } + async function prepare(job) { + working=true;active=job;aborter=new AbortController();const epoch=run.epoch; + try { + assertLive(epoch); + if(!editorPage(job)) { + saveLocal({id:job.id}); + location.assign(`https://www.dww11.com/forum.php?mod=post&action=newthread&fid=${job.fid}`);return; + } + if(!window.DWW11Importer||!window.DWW11Formatter)throw new Error('导入或排版模块尚未就绪，请检查安装'); + status('正在检查文章包…'); + const pack=await rpc('package',{id:job.id});assertLive(epoch); + const prepared=await window.DWW11Importer.stagePackage(pack);assertLive(epoch); + if(prepared.warnings?.length)throw new Error('文章需要人工处理：'+prepared.warnings.join('；')); + await event('importing');assertLive(epoch);status('上传图片并填写文章…'); + const result=await window.DWW11Importer.importPrepared({automatic:true,signal:aborter.signal});assertLive(epoch); + if(result?.cancelled)throw new Error('导入已取消'); + await event('formatting');assertLive(epoch); + window.DWW11Formatter.format(job.source);assertLive(epoch); + const snapshot=editorSnapshot(); + if(snapshot.title!==job.title)throw new Error('标题校验失败'); + const aids=new Set(Object.values(result.images)); + for(const aid of aids) if(!snapshot.images.some(x=>x.id==='attachimg_'+aid))throw new Error('配图附件缺失：'+aid); + await event('awaiting_user_review',{snapshot});assertLive(epoch); + active={...job,state:'awaiting_user_review'};saveLocal({id:job.id}); + status('已完成排版，请核对内容并亲手点击“发表帖子”。'); + }catch(error){await fail(error);}finally{working=false;} + } + // Record only trusted user activation. Never replay a click, call submit(), or send a post request. + document.addEventListener('click',event=>{ + if(!event.isTrusted||!event.target.closest?.('#postsubmit')||active?.state!=='awaiting_user_review')return; + try { + const snapshot=editorSnapshot(); + const local={id:active.id,snapshot,clickedAt:Date.now(),observed:false};saveLocal(local); + rpc('event',{id:active.id,state:'user_submitting',epoch:run?.epoch,snapshot}) + .then(()=>{const latest=loadLocal();if(latest?.clickedAt===local.clickedAt)saveLocal({...local,observed:true});}) + .catch(error=>status('提交记录待恢复：'+error.message)); + active.state='user_submitting';status('已观察到人工点击，等待结果页核对。'); + }catch(error){status('提交快照记录失败：'+error.message);} + },true); + async function observeResult(job) { + const local=loadLocal(); + if(local?.id===job.id&&local.snapshot&&job.state==='awaiting_user_review') { + await rpc('event',{id:job.id,state:'user_submitting',epoch:run.epoch,snapshot:local.snapshot}); + job.state='user_submitting'; + } + if(job.state==='user_submitting') { + // Result selectors intentionally await user-provided HTML; URL alone is not proof. + if(!editorPage(job) || (local?.clickedAt && Date.now()-local.clickedAt>45000)) { + await rpc('event',{id:job.id,state:'submit_unknown',error:'等待结果页 HTML 适配；候选页面：'+location.href}); + await rpc('stop'); + status('已记录候选结果页；尚不能自动核对。流程已暂停，请补充结果页 HTML。'); + } + }else if(job.state==='submit_unknown')status('发布结果待核对；不会重发、计数或换号。'); + } + async function switchAccount() { + if(working||halted)return; + if(location.origin!=='https://www.dww11.com'||location.pathname!=='/') { + location.assign('https://www.dww11.com/');return; + } + const ext=extension(),button=document.querySelector('#dww11-extension-next'); + if(!ext.ready||!ext.idle||!button||button.disabled) {status('请安装并重新加载带联动接口的换号插件');return;} + await rpc('switch-begin'); + if(halted||!run?.running)return; + button.click();status('正在换号；等待插件完成并核对新账号'); + } + async function tick() { + if(tickBusy)return;tickBusy=true; + try { + run=await rpc('heartbeat',{account:account(),url:location.href,extension:extension()}); + halted=!run.running; + if(!run.running) {aborter?.abort();document.dispatchEvent(new CustomEvent('dww11:auto-stop'));} + if(working)return; + // Passive result recording is permitted after Stop, but no new business actions. + if(run.active) { + const local=loadLocal(); + if(local?.id===run.active&&local.snapshot&&!run.running)status('流程已暂停；提交结果仍需核对'); + } + if(!run.running) { + if(run.active && run.owner===owner) {const saved=await rpc('current');if(saved.job) {active=saved.job;await observeResult(saved.job);}} + status(run.reason || '流程已暂停');return; + } + const next=await rpc('next',{account:account(),extension:extension()});run=next.run; + if(next.job)active=next.job; + if(next.action==='prepare'||(next.action==='resume'&&next.job.state==='preparing'))void prepare(next.job); + else if(next.action==='resume') { + await observeResult(next.job); + if(next.job.state==='awaiting_user_review') { + if(!editorPage(next.job)||!document.querySelector('#subject')?.value) await fail(new Error('待审稿页面已丢失，请人工核对旧稿，不自动重新导入')); + else status('等待你亲手发表；程序不再修改编辑器'); + } + else if(['importing','formatting'].includes(next.job.state))await fail(new Error('导入阶段发生中断，请检查编辑器和已上传图片后处理任务')); + else if(next.job.state==='needs_attention')status(next.job.error); + }else if(next.action==='switch')await switchAccount(); + else if(next.action==='switch_wait')status('等待换号结果；若插件已暂停，请人工处理后继续'); + else if(next.action==='login')status('未能读取当前账号 UID，请登录并确认账号元素'); + else if(next.action==='other_tab')status('另一个标签持有任务；如需接管请先暂停'); + else if(next.action==='interval')status('等待设定的处理间隔'); + else status(run.reason || '等待任务'); + }catch(error){status(error.message);halted=true;aborter?.abort();document.dispatchEvent(new CustomEvent('dww11:auto-stop'));} + finally{tickBusy=false;} + } + const takeover=document.createElement('button');takeover.type='button';takeover.textContent='接管已暂停任务'; + takeover.style.cssText='position:fixed;left:16px;top:16px;z-index:2147483646;padding:8px;background:#fff;border:1px solid #aab;border-radius:6px'; + takeover.onclick=async()=>{try{await rpc('takeover');status('已接管；核对当前页面后在工作台继续');}catch(error){status(error.message);}}; + document.body.append(takeover); + setInterval(tick,2000);tick(); +})(); diff --git a/browser/formatter-original.user.js b/browser/formatter-original.user.js new file mode 100644 index 0000000..afc0684 --- /dev/null +++ b/browser/formatter-original.user.js @@ -0,0 +1,397 @@ +// ==UserScript== +// @name 广谈大湾网 · 微信文章一键导入并排版 +// @namespace local.dww11.wechat-oneclick +// @version 1.0.9 +// @description 使用网站现有微信采集器，修正标题，统一正文4号黑色，追加1号银色来源；不点击保存或发布。 +// @match https://www.dww11.com/forum.php* +// @match https://dww11.com/forum.php* +// @grant GM_xmlhttpRequest +// @grant unsafeWindow +// @connect mp.weixin.qq.com +// @run-at document-idle +// @noframes +// ==/UserScript== + +(() => { + 'use strict'; + const ID = 'dww11-wx-oneclick'; + const FORMAT_ID = 'dww11-format-oneclick'; + let busy = false; + function setBusy(value) { + busy = value; + for (const id of [ID, FORMAT_ID]) { + const button = document.getElementById(id); + if (button) button.disabled = value; + } + } + const sleep = ms => new Promise(resolve => setTimeout(resolve, ms)); + const visible = el => el && el.getClientRects().length && getComputedStyle(el).display !== 'none'; + async function waitFor(fn, timeout = 10000) { + const deadline = Date.now() + timeout; + while (Date.now() < deadline) { + const result = fn(); + if (result) return result; + await sleep(100); + } + throw new Error('等待编辑器或采集窗口超时，请关闭遮挡窗口后重试。'); + } + function normalizeURL(raw) { + const url = new URL(raw.trim().replace(/[\u200b-\u200d\ufeff]/g, '')); + if (url.protocol !== 'https:' || url.hostname !== 'mp.weixin.qq.com' || url.port || url.username || url.password || !/^\/(s(?:\/|$)|s$)/.test(url.pathname)) { + throw new Error('请输入 https://mp.weixin.qq.com/s/… 或 /s?… 微信文章地址。'); + } + url.hash = ''; + return url.href; + } + function cleanText(value) { + return String(value || '').replace(/\s+/g, ' ').trim(); + } + function metadata(html) { + const doc = new DOMParser().parseFromString(html, 'text/html'); + const text = selector => cleanText(doc.querySelector(selector)?.textContent); + const meta = selector => cleanText(doc.querySelector(selector)?.getAttribute('content')); + // 与下载组件一致，先确认是真正的文章，避免把验证页标题当成文章。 + if (!doc.querySelector('#js_content')) throw new Error('未找到微信文章正文，可能需要验证、登录，或文章已失效。'); + const title = text('#activity-name .js_title_inner') || text('#activity-name') || meta('meta[property="og:title"]') || meta('meta[name="twitter:title"]') || text('h1') || text('title'); + // 不读取 rich_media_meta_text 容器：它可能包含重复的隐藏作者，或实际上是日期/IP。 + // 来源使用蓝色链接 #js_name 的公众号名称，不使用灰色署名作者。 + const author = text('#js_name'); + if (!title || !author) throw new Error('微信未返回完整标题和公众号名称，可能需要验证或登录。'); + return { title, author }; + } + function fetchMetadata(url) { + return new Promise((resolve, reject) => { + GM_xmlhttpRequest({ + method: 'GET', url, timeout: 25000, anonymous: true, + onload(response) { + try { + if (response.status !== 200) throw new Error('微信返回状态 ' + response.status); + if (response.finalUrl && new URL(response.finalUrl).hostname !== 'mp.weixin.qq.com') throw new Error('微信地址发生了非预期跳转。'); + resolve(metadata(response.responseText)); + } catch (error) { reject(error); } + }, + onerror: () => reject(new Error('无法读取微信文章。')), + ontimeout: () => reject(new Error('读取微信文章超时。')) + }); + }); + } + async function getMetadata(url) { + try { return await fetchMetadata(url); } + catch (error) { + const title = prompt(error.message + '\n请从源文章复制完整标题（取消则停止导入）：'); + if (title === null) return null; + const author = prompt('请填写源文章蓝色链接处的公众号名称（取消则停止导入）：'); + if (author === null) return null; + if (!cleanText(title) || !cleanText(author)) throw new Error('标题和作者不能为空。'); + return { title: cleanText(title), author: cleanText(author) }; + } + } + function editorBody() { + return document.querySelector('#e_iframe')?.contentDocument?.body; + } + async function ensureVisualEditor() { + const checkbox = document.querySelector('#e_switchercheck'); + if (checkbox?.checked) checkbox.click(); + await waitFor(() => visible(document.querySelector('#e_iframe')) && editorBody()); + } + // 只监听本次现有采集器的响应，不重写其请求或图片附件处理。 + function watchImport(jq, url) { + let timer, resolveResult, rejectResult; + const result = new Promise((resolve, reject) => { resolveResult = resolve; rejectResult = reject; }); + const events = jq(document); + const cleanup = () => { clearTimeout(timer); events.off('.dww11wx'); }; + const finish = error => { cleanup(); error ? rejectResult(error) : resolveResult(); }; + events.on('ajaxComplete.dww11wx', (_event, xhr, settings) => { + let requestURL, sentURL; + try { + requestURL = new URL(settings.url, location.href); + sentURL = typeof settings.data === 'string' ? new URLSearchParams(settings.data).get('url') : settings.data?.url; + } catch { return; } + if (requestURL.origin !== location.origin || requestURL.searchParams.get('id') !== 'wxcj:cj' || sentURL !== url) return; + const parts = String(xhr.responseText || '').split('----wxcj----'); + if (xhr.status < 200 || xhr.status >= 300 || parts.length < 4 || !parts[2]?.trim()) { + finish(new Error('网站采集失败或返回内容不完整。未执行排版，请检查采集提示。')); + return; + } + finish(); + }); + timer = setTimeout(() => finish(new Error('网站采集超过90秒，未执行排版。采集器仍可能在后台返回，请勿连续重复导入。')), 90000); + return { result, cleanup }; + } + // 将微信 P/SECTION 的隐式换行改成真实 BR，避免论坛忽略 SECTION 边界。 + function flattenParagraphs(body) { + const selector = 'p,div,section,article,figure,figcaption,h1,h2,h3,h4,h5,h6'; + const marker = () => { + const br = body.ownerDocument.createElement('br'); + br.dataset.dww11Boundary = '1'; return br; + }; + for (const block of Array.from(body.querySelectorAll(selector)).reverse()) { + if (block.closest('table,ul,ol,blockquote')) continue; + block.replaceWith(marker(), ...block.childNodes, marker()); + } + let previous = false, pending = []; + function finish() { + const actual = pending.filter(br => !br.hasAttribute('data-dww11-boundary')); + let retained = false; + for (const br of pending) { + if (!br.hasAttribute('data-dww11-boundary')) continue; + if (previous && !actual.length && !retained) { br.removeAttribute('data-dww11-boundary'); retained = true; } + else br.remove(); + } + pending = []; + } + const walker = body.ownerDocument.createTreeWalker(body, NodeFilter.SHOW_ELEMENT | NodeFilter.SHOW_TEXT); + const nodes = []; while (walker.nextNode()) nodes.push(walker.currentNode); + for (const node of nodes) { + if (node.nodeType === 1 && node.tagName === 'BR') pending.push(node); + else if ((node.nodeType === 3 && node.textContent.trim()) || (node.nodeType === 1 && ['IMG', 'VIDEO', 'HR', 'IFRAME'].includes(node.tagName))) { + finish(); previous = true; + } + } + // 末尾不保留由容器边界制造的额外换行。 + for (const br of pending) if (br.hasAttribute('data-dww11-boundary')) br.remove(); + } + function spaceImages(body) { + let previous = null, gapNodes = [], blankLines = 0; + const changes = []; + function content(kind, node) { + if (previous && previous.kind !== kind) { + let anchor = node; + while (anchor.parentElement && anchor.parentElement !== body && + !['TD', 'TH', 'LI', 'BLOCKQUOTE'].includes(anchor.parentElement.tagName) && !anchor.parentElement.contains(previous.node)) anchor = anchor.parentElement; + changes.push({ anchor, nodes: gapNodes.slice(), count: Math.max(2, blankLines) }); + } + previous = { kind, node }; gapNodes = []; blankLines = 0; + } + function visit(node) { + if (node.nodeType === 3) { + if (node.textContent.trim()) content('text', node); else gapNodes.push(node); + return; + } + if (node.nodeType !== 1 || ['SCRIPT', 'STYLE', 'NOSCRIPT'].includes(node.tagName)) return; + if (node.tagName === 'BR') { gapNodes.push(node); blankLines++; return; } + if (node.tagName === 'IMG') { content('image', node); return; } + for (const child of node.childNodes) visit(child); + } + for (const child of body.childNodes) visit(child); + for (const { anchor, nodes, count } of changes) { + for (const node of nodes) node.remove(); + const fragment = body.ownerDocument.createDocumentFragment(); + for (let i = 0; i < count; i++) fragment.append(body.ownerDocument.createElement('br')); + anchor.parentNode.insertBefore(fragment, anchor); + } + } + function formatBody(body, author, sourceText = null) { + const doc = body.ownerDocument; + body.querySelectorAll('[data-dww11-wx-source="1"]').forEach(el => el.remove()); + // Discuz 会把内联 color 值直接转为 [color=…]。 + // !important 不能出现在该值中；颜色和字号只用原生 FONT 属性。 + for (const el of [body, ...body.querySelectorAll('*')]) { + if (['SCRIPT', 'STYLE'].includes(el.tagName)) continue; + for (const property of ['font', 'font-size', 'color', '-webkit-text-fill-color']) { + el.style.removeProperty(property); + } + // 其他排版属性也不保留 CSS 优先级，避免它泄漏进论坛标签。 + for (const property of Array.from(el.style)) { + if (el.style.getPropertyPriority(property)) { + el.style.setProperty(property, el.style.getPropertyValue(property)); + } + } + if (!el.style.cssText) el.removeAttribute('style'); + } + // 去掉采集器或旧版脚本生成的嵌套 FONT，保留其中的内容和图片。 + for (const font of Array.from(body.querySelectorAll('font'))) { + font.replaceWith(...font.childNodes); + } + flattenParagraphs(body); + spaceImages(body); + // 所有正文内容和换行放在同一 FONT 中。不能使用只有 BR 的空 FONT： + // 论坛转换器可能清除空格式标签，导致空行退回默认1号或直接丢失。 + const articleFont = doc.createElement('font'); + articleFont.size = '4'; articleFont.color = '#000000'; + articleFont.dataset.dww11WxBody = '1'; + articleFont.append(...body.childNodes); + body.append(articleFont); + // A 自身的浏览器默认蓝色会覆盖外层继承色，链接文字另设黑色。 + for (const link of articleFont.querySelectorAll('a')) { + const linkFont = doc.createElement('font'); + linkFont.size = '4'; linkFont.color = '#000000'; + linkFont.append(...link.childNodes); link.append(linkFont); + } + // 只用于编辑器图片适配；帖子展示仍交给网站原有图片/附件规则。 + for (const img of articleFont.querySelectorAll('img')) { + img.style.maxWidth = '100%'; img.style.height = 'auto'; + } + const source = doc.createElement('p'); + source.dataset.dww11WxSource = '1'; + const font = doc.createElement('font'); + font.size = '1'; font.color = '#c0c0c0'; + const lines = (sourceText ?? `来源：${author}，如有侵权，请联系删除。`).split('\n'); + lines.forEach((line, index) => { + if (index) font.append(doc.createElement('br')); + font.append(doc.createTextNode(line)); + }); + source.append(font); body.append(source); + } + function existingSource(body) { + // 按段落和 BR 读取末尾逻辑行，兼容嵌套 FONT、纯文本及末尾空段落。 + const lines = []; + let parts = []; + function flush() { + const text = cleanText(parts.map(part => part.node.textContent.slice(part.start, part.end)).join('')); + if (text) lines.push({ text, parts }); + parts = []; + } + function visit(node) { + if (node.nodeType === 3) { + // 保留文本中的显式换行，并记录精确位置，避免删除同容器中的正文。 + const value = node.textContent; + let start = 0; + for (let i = 0; i <= value.length; i++) { + if (i !== value.length && value[i] !== '\n') continue; + // HTML 缩进换行通常只是空白；只有后续是来源或版权行才分行。 + if (i < value.length && !/^\s*(?:(?:来源|文章来源|本文来源|图文来源|文字来源|作者|作者信息|来源作者|转自|转载自|出处)\s*[:：]|如有侵权|若有侵权|侵权请|转载请|版权归)/.test(value.slice(i + 1))) continue; + if (i > start) parts.push({ node, start, end: i }); + if (i < value.length) flush(); + start = i + 1; + } + return; + } + if (node.nodeType !== 1 || ['SCRIPT', 'STYLE', 'NOSCRIPT'].includes(node.tagName)) return; + if (node.tagName === 'BR') { flush(); return; } + if (['IMG', 'VIDEO', 'AUDIO', 'IFRAME', 'HR'].includes(node.tagName)) { + flush(); lines.push({ text: '\ufffc', parts: [] }); return; + } + const block = /^(P|DIV|SECTION|ARTICLE|FIGURE|FIGCAPTION|H[1-6]|LI|TR|BLOCKQUOTE|PRE)$/.test(node.tagName); + if (block) flush(); + for (const child of node.childNodes) visit(child); + if (block) flush(); + } + for (const child of body.childNodes) visit(child); + flush(); + let first = -1; + for (let i = lines.length - 1; i >= 0; i--) { + if (/^(?:来源|文章来源|本文来源|图文来源|文字来源|作者|作者信息|来源作者|转自|转载自|出处)\s*[:：]\s*\S/.test(lines[i].text)) { + first = i; + } else if (!/^(?:如有侵权|若有侵权|侵权请|转载请|版权归)/.test(lines[i].text)) { + break; + } + } + if (first < 0) return null; + const start = lines[first].parts[0]; + const range = body.ownerDocument.createRange(); + range.setStart(start.node, start.start); + range.setEnd(body, body.childNodes.length); + return { + text: lines.slice(first).map(line => line.text).join('\n'), + remove: () => range.deleteContents() + }; + } + async function runFormat(button) { + if (busy) return; + setBusy(true); + try { + await ensureVisualEditor(); + const body = editorBody(); + const source = existingSource(body); + const hasText = cleanText(body.textContent).replace(source ? cleanText(source.text) : '', '').trim(); + if (!hasText && !body.querySelector('img,video,audio,iframe,hr,table')) { + throw new Error('正文为空，请先输入或粘贴文章。'); + } + const raw = source ? '' : prompt('未在文末检测到来源／作者信息，请补充来源公众号名称（取消则停止排版）：'); + if (raw === null) return; + const author = cleanText(raw); + if (!source && !author) throw new Error('来源公众号名称不能为空。'); + button.textContent = '正在排版…'; + // 已有来源保留原文，仅调整字号颜色；没有时才生成来源行。 + source?.remove(); + formatBody(body, author, source?.text ?? null); + alert(`排版完成。\n正文：4号黑色；来源：1号银色。\n${source ? source.text : `来源：${author}`}\n请人工检查后自行决定是否保存或发布。`); + } catch (error) { alert('排版未完成：' + error.message); } + finally { + setBusy(false); + button.textContent = '一键排版'; + } + } + async function run(button) { + if (busy) return; + const raw = prompt('粘贴微信公众号文章 URL：'); + if (raw === null || !raw.trim()) return; + setBusy(true); + let watcher; + try { + const url = normalizeURL(raw); + const jq = unsafeWindow.myJQ; + if (typeof jq !== 'function' || !jq.fn?.on) throw new Error('没有找到网站微信采集器的 myJQ，请刷新页面后重试。'); + const plugin = document.querySelector('#e_controls .wxcj'); + if (!plugin) throw new Error('当前页面没有微信采集组件。'); + button.textContent = '读取标题和作者…'; + const info = await getMetadata(url); + if (!info) return; + const subject = document.querySelector('#subject'); + if (!subject) throw new Error('没有找到标题框。'); + if (subject.maxLength > 0 && info.title.length > subject.maxLength) throw new Error('完整标题超过标题框长度限制，请先处理标题长度。'); + await ensureVisualEditor(); + button.textContent = '采集文章中…'; + plugin.click(); + const input = await waitFor(() => Array.from(document.querySelectorAll('.wxjc-dialog input')).find(visible)); + const submit = input.closest('.wxjc-dialog').querySelector('.wxjc-subimt'); + if (!submit) throw new Error('没有找到采集按钮。'); + input.value = url; + input.dispatchEvent(new Event('input', { bubbles: true })); + input.dispatchEvent(new Event('change', { bubbles: true })); + watcher = watchImport(jq, url); + // 先登记失败处理，避免点击失败时留下未处理的 Promise。 + watcher.result.catch(() => {}); + submit.click(); + await watcher.result; + button.textContent = '正在排版…'; + const body = await waitFor(() => editorBody()?.innerHTML.trim() && editorBody()); + formatBody(body, info.author); + subject.value = info.title; + subject.dispatchEvent(new Event('input', { bubbles: true })); + subject.dispatchEvent(new Event('change', { bubbles: true })); + subject.dispatchEvent(new KeyboardEvent('keyup', { bubbles: true })); + // 正文保持在可视化编辑器，由网站正常提交流程转成 BBCode。 + // 不把 HTML 写入纯文本 message，也不调用任何保存／发布入口。 + alert(`导入并排版完成。\n标题：${info.title}\n作者：${info.author}\n正文：4号黑色；来源：1号银色。\n请人工检查后自行决定是否保存或发布。`); + } catch (error) { alert('导入未完成：' + error.message); } + finally { + watcher?.cleanup(); + setBusy(false); + button.textContent = '一键导入微信公众号并排版'; + } + } + function mount() { + const toolbar = document.querySelector('#e_controls'); + if (!toolbar || !document.querySelector('#subject')) return; + const style = 'position:relative;z-index:2;padding:0 12px;height:32px;line-height:30px;border:1px solid #159447;border-radius:4px;background:#159447;color:white;font-size:13px;cursor:pointer;'; + // 右浮动的同一组内使用 flex，保证排版按钮始终位于导入按钮左侧。 + let group = document.getElementById('dww11-wx-actions'); + if (!group) { + group = document.createElement('span'); + group.id = 'dww11-wx-actions'; + group.style.cssText = 'float:right;display:inline-flex;align-items:center;gap:8px;margin:6px 8px;'; + toolbar.append(group); + } + if (!document.getElementById(FORMAT_ID)) { + const button = document.createElement('button'); + button.id = FORMAT_ID; button.type = 'button'; + button.textContent = '一键排版'; button.style.cssText = style; + button.disabled = busy; + button.addEventListener('click', () => runFormat(button)); + group.prepend(button); + } + if (toolbar.querySelector('.wxcj') && !document.getElementById(ID)) { + const button = document.createElement('button'); + button.id = ID; button.type = 'button'; + button.textContent = '一键导入微信公众号并排版'; button.style.cssText = style; + button.disabled = busy; + button.addEventListener('click', () => run(button)); + group.append(button); + } + } + mount(); + const observer = new MutationObserver(mount); + observer.observe(document.documentElement, { childList: true, subtree: true }); +})(); diff --git a/browser/formatter.js b/browser/formatter.js new file mode 100644 index 0000000..46a7712 --- /dev/null +++ b/browser/formatter.js @@ -0,0 +1,195 @@ +// Extracted from dww11-wechat-oneclick.user.js v1.0.9; package source is authoritative. +(() => { +'use strict'; +const cleanText = value => String(value || '').replace(/\s+/g, ' ').trim(); + function flattenParagraphs(body) { + const selector = 'p,div,section,article,figure,figcaption,h1,h2,h3,h4,h5,h6'; + const marker = () => { + const br = body.ownerDocument.createElement('br'); + br.dataset.dww11Boundary = '1'; return br; + }; + for (const block of Array.from(body.querySelectorAll(selector)).reverse()) { + if (block.closest('table,ul,ol,blockquote')) continue; + block.replaceWith(marker(), ...block.childNodes, marker()); + } + let previous = false, pending = []; + function finish() { + const actual = pending.filter(br => !br.hasAttribute('data-dww11-boundary')); + let retained = false; + for (const br of pending) { + if (!br.hasAttribute('data-dww11-boundary')) continue; + if (previous && !actual.length && !retained) { br.removeAttribute('data-dww11-boundary'); retained = true; } + else br.remove(); + } + pending = []; + } + const walker = body.ownerDocument.createTreeWalker(body, NodeFilter.SHOW_ELEMENT | NodeFilter.SHOW_TEXT); + const nodes = []; while (walker.nextNode()) nodes.push(walker.currentNode); + for (const node of nodes) { + if (node.nodeType === 1 && node.tagName === 'BR') pending.push(node); + else if ((node.nodeType === 3 && node.textContent.trim()) || (node.nodeType === 1 && ['IMG', 'VIDEO', 'HR', 'IFRAME'].includes(node.tagName))) { + finish(); previous = true; + } + } + // 末尾不保留由容器边界制造的额外换行。 + for (const br of pending) if (br.hasAttribute('data-dww11-boundary')) br.remove(); + } + function spaceImages(body) { + let previous = null, gapNodes = [], blankLines = 0; + const changes = []; + function content(kind, node) { + if (previous && previous.kind !== kind) { + let anchor = node; + while (anchor.parentElement && anchor.parentElement !== body && + !['TD', 'TH', 'LI', 'BLOCKQUOTE'].includes(anchor.parentElement.tagName) && !anchor.parentElement.contains(previous.node)) anchor = anchor.parentElement; + changes.push({ anchor, nodes: gapNodes.slice(), count: Math.max(2, blankLines) }); + } + previous = { kind, node }; gapNodes = []; blankLines = 0; + } + function visit(node) { + if (node.nodeType === 3) { + if (node.textContent.trim()) content('text', node); else gapNodes.push(node); + return; + } + if (node.nodeType !== 1 || ['SCRIPT', 'STYLE', 'NOSCRIPT'].includes(node.tagName)) return; + if (node.tagName === 'BR') { gapNodes.push(node); blankLines++; return; } + if (node.tagName === 'IMG') { content('image', node); return; } + for (const child of node.childNodes) visit(child); + } + for (const child of body.childNodes) visit(child); + for (const { anchor, nodes, count } of changes) { + for (const node of nodes) node.remove(); + const fragment = body.ownerDocument.createDocumentFragment(); + for (let i = 0; i < count; i++) fragment.append(body.ownerDocument.createElement('br')); + anchor.parentNode.insertBefore(fragment, anchor); + } + } + function formatBody(body, author, sourceText = null) { + const doc = body.ownerDocument; + body.querySelectorAll('[data-dww11-wx-source="1"]').forEach(el => el.remove()); + // Discuz 会把内联 color 值直接转为 [color=…]。 + // !important 不能出现在该值中；颜色和字号只用原生 FONT 属性。 + for (const el of [body, ...body.querySelectorAll('*')]) { + if (['SCRIPT', 'STYLE'].includes(el.tagName)) continue; + for (const property of ['font', 'font-size', 'color', '-webkit-text-fill-color']) { + el.style.removeProperty(property); + } + // 其他排版属性也不保留 CSS 优先级，避免它泄漏进论坛标签。 + for (const property of Array.from(el.style)) { + if (el.style.getPropertyPriority(property)) { + el.style.setProperty(property, el.style.getPropertyValue(property)); + } + } + if (!el.style.cssText) el.removeAttribute('style'); + } + // 去掉采集器或旧版脚本生成的嵌套 FONT，保留其中的内容和图片。 + for (const font of Array.from(body.querySelectorAll('font'))) { + font.replaceWith(...font.childNodes); + } + flattenParagraphs(body); + spaceImages(body); + // 所有正文内容和换行放在同一 FONT 中。不能使用只有 BR 的空 FONT： + // 论坛转换器可能清除空格式标签，导致空行退回默认1号或直接丢失。 + const articleFont = doc.createElement('font'); + articleFont.size = '4'; articleFont.color = '#000000'; + articleFont.dataset.dww11WxBody = '1'; + articleFont.append(...body.childNodes); + body.append(articleFont); + // A 自身的浏览器默认蓝色会覆盖外层继承色，链接文字另设黑色。 + for (const link of articleFont.querySelectorAll('a')) { + const linkFont = doc.createElement('font'); + linkFont.size = '4'; linkFont.color = '#000000'; + linkFont.append(...link.childNodes); link.append(linkFont); + } + // 只用于编辑器图片适配；帖子展示仍交给网站原有图片/附件规则。 + for (const img of articleFont.querySelectorAll('img')) { + img.style.maxWidth = '100%'; img.style.height = 'auto'; + } + const source = doc.createElement('p'); + source.dataset.dww11WxSource = '1'; + const font = doc.createElement('font'); + font.size = '1'; font.color = '#c0c0c0'; + const lines = (sourceText ?? `来源：${author}，如有侵权，请联系删除。`).split('\n'); + lines.forEach((line, index) => { + if (index) font.append(doc.createElement('br')); + font.append(doc.createTextNode(line)); + }); + source.append(font); body.append(source); + } + function existingSource(body) { + // 按段落和 BR 读取末尾逻辑行，兼容嵌套 FONT、纯文本及末尾空段落。 + const lines = []; + let parts = []; + function flush() { + const text = cleanText(parts.map(part => part.node.textContent.slice(part.start, part.end)).join('')); + if (text) lines.push({ text, parts }); + parts = []; + } + function visit(node) { + if (node.nodeType === 3) { + // 保留文本中的显式换行，并记录精确位置，避免删除同容器中的正文。 + const value = node.textContent; + let start = 0; + for (let i = 0; i <= value.length; i++) { + if (i !== value.length && value[i] !== '\n') continue; + // HTML 缩进换行通常只是空白；只有后续是来源或版权行才分行。 + if (i < value.length && !/^\s*(?:(?:来源|文章来源|本文来源|图文来源|文字来源|作者|作者信息|来源作者|转自|转载自|出处)\s*[:：]|如有侵权|若有侵权|侵权请|转载请|版权归)/.test(value.slice(i + 1))) continue; + if (i > start) parts.push({ node, start, end: i }); + if (i < value.length) flush(); + start = i + 1; + } + return; + } + if (node.nodeType !== 1 || ['SCRIPT', 'STYLE', 'NOSCRIPT'].includes(node.tagName)) return; + if (node.tagName === 'BR') { flush(); return; } + if (['IMG', 'VIDEO', 'AUDIO', 'IFRAME', 'HR'].includes(node.tagName)) { + flush(); lines.push({ text: '\ufffc', parts: [] }); return; + } + const block = /^(P|DIV|SECTION|ARTICLE|FIGURE|FIGCAPTION|H[1-6]|LI|TR|BLOCKQUOTE|PRE)$/.test(node.tagName); + if (block) flush(); + for (const child of node.childNodes) visit(child); + if (block) flush(); + } + for (const child of body.childNodes) visit(child); + flush(); + let first = -1; + for (let i = lines.length - 1; i >= 0; i--) { + if (/^(?:来源|文章来源|本文来源|图文来源|文字来源|作者|作者信息|来源作者|转自|转载自|出处)\s*[:：]\s*\S/.test(lines[i].text)) { + first = i; + } else if (!/^(?:如有侵权|若有侵权|侵权请|转载请|版权归)/.test(lines[i].text)) { + break; + } + } + if (first < 0) return null; + const start = lines[first].parts[0]; + const range = body.ownerDocument.createRange(); + range.setStart(start.node, start.start); + range.setEnd(body, body.childNodes.length); + return { + text: lines.slice(first).map(line => line.text).join('\n'), + remove: () => range.deleteContents() + }; + } + +window.DWW11Formatter = Object.freeze({ + format(expectedSource) { + if (Number(window.wysiwyg) !== 1) throw new Error('请切换到可视化编辑器后排版'); + const body = document.querySelector('#e_iframe')?.contentDocument?.body; + if (!body) throw new Error('编辑器未就绪'); + const footer = existingSource(body); + const expected = `来源：${expectedSource}，如有侵权，请联系删除。`; + if (!footer || footer.text !== expected) throw new Error('文末来源与文章包不一致，请人工检查'); + const images = [...body.querySelectorAll('img')].map(x => x.id + ':' + x.getAttribute('src')); + const backup = body.innerHTML; + try { + footer.remove(); + formatBody(body, expectedSource, expected); + const after = [...body.querySelectorAll('img')].map(x => x.id + ':' + x.getAttribute('src')); + if (JSON.stringify(images) !== JSON.stringify(after)) throw new Error('排版后图片标识或顺序改变'); + if (body.querySelectorAll('[data-dww11-wx-source="1"]').length !== 1) throw new Error('来源尾注数量异常'); + body.dispatchEvent(new Event('input', {bubbles:true})); + return {images: after, source: expected}; + } catch (error) { body.innerHTML = backup; throw error; } + } +}); +})(); diff --git a/browser/importer.js b/browser/importer.js new file mode 100644 index 0000000..58515c1 --- /dev/null +++ b/browser/importer.js @@ -0,0 +1,480 @@ +// ==UserScript== +// @name 广谈大湾网 · 本地文章目录导入 +// @namespace local.dww11.article-importer +// @version 1.0.0 +// @description 选择整个文章目录，导入 Markdown 标题、正文与本地配图；保留人工发布与程序接口。 +// @match https://www.dww11.com/forum.php* +// @match https://dww11.com/forum.php* +// @run-at document-idle +// @grant none +// @noframes +// @license MIT +// ==/UserScript== + +(function (root, factory) { + 'use strict'; + const core = factory(); + if (typeof module === 'object' && module.exports) module.exports = core; + else core.mount(root); +})(typeof window === 'undefined' ? null : window, function () { + 'use strict'; + const VERSION = '1.0.0'; + const MAX_IMAGE_SIZE = 20 * 1024 * 1024; + const IMAGE_EXT = /\.(?:jpe?g|png|gif)$/i; + + function normalizePath(path) { + const parts = []; + const value = String(path).replace(/\\/g, '/').normalize('NFC'); + if (/^(?:\/|[a-z]:|[a-z]+:)/i.test(value)) throw new Error('请使用目录内的相对路径：' + path); + for (const part of value.split('/')) { + if (!part || part === '.') continue; + if (part === '..') { + if (!parts.length) throw new Error('图片路径超出所选目录：' + path); + parts.pop(); + } else parts.push(part); + } + return parts.join('/'); + } + + function imagePath(mdPath, target) { + if (/^(?:[a-z][\w+.-]*:|\/\/|\/)/i.test(target)) throw new Error('图片必须在所选目录内，请先下载：' + target); + let decoded; + try { decoded = decodeURIComponent(target); } catch { throw new Error('图片路径编码无效：' + target); } + return normalizePath(mdPath.slice(0, mdPath.lastIndexOf('/') + 1) + decoded); + } + + // A small, intentionally bounded Markdown reader. Raw HTML is never executed. + // Links/images support balanced parentheses, angle destinations and optional titles. + function readLink(text, start) { + const image = text.startsWith('![', start); + if (!image && text[start] !== '[') return null; + const left = start + (image ? 2 : 1); + let end = left; + for (; end < text.length; end++) { + if (text[end] === '\\') { end++; continue; } + if (text[end] === ']') break; + } + if (text.slice(end, end + 2) !== '](') return null; + let pos = end + 2, depth = 1, quoted = '', angle = false; + for (; pos < text.length; pos++) { + const ch = text[pos]; + if (ch === '\\') { pos++; continue; } + if (quoted) { if (ch === quoted) quoted = ''; continue; } + if (!angle && depth === 1 && /\s/.test(text[pos - 1]) && (ch === '"' || ch === "'")) { quoted = ch; continue; } + if (ch === '<') { angle = true; continue; } + if (ch === '>') { angle = false; continue; } + if (!angle && ch === '(') depth++; + if (!angle && ch === ')' && --depth === 0) break; + } + if (depth) return null; + let target = text.slice(end + 2, pos).trim(); + const destination = target.match(/^<([^>]+)>\s*(?:["'][\s\S]*["'])?$/); + target = destination ? destination[1] : target.replace(/\s+["'][\s\S]*["']\s*$/, ''); + target = target.replace(/\\([()\\ ])/g, '$1'); + return { image, label: text.slice(left, end), target, end: pos + 1 }; + } + + function inline(text, onImage) { + let out = ''; + for (let pos = 0; pos < text.length;) { + if (text[pos] === '\\' && pos + 1 < text.length) { out += text[pos + 1]; pos += 2; continue; } + const link = readLink(text, pos); + if (link) { + if (link.image) out += onImage(link.target, link.label); + else if (/^(https?:\/\/|mailto:)/i.test(link.target) && !/[\[\]\r\n"']/.test(link.target)) { + out += '[url=' + link.target + ']' + inline(link.label, onImage) + '[/url]'; + } else out += link.label + ' (' + link.target + ')'; + pos = link.end; + continue; + } + if (text[pos] === '`') { + const end = text.indexOf('`', pos + 1); + if (end > pos + 1) { out += text.slice(pos + 1, end); pos = end + 1; continue; } + } + let matched = false; + for (const [mark, tag] of [['**', 'b'], ['__', 'b'], ['~~', 's'], ['*', 'i'], ['_', 'i']]) { + if (!text.startsWith(mark, pos) || (mark === '_' && /\w/.test(text[pos - 1] || ''))) continue; + const end = text.indexOf(mark, pos + mark.length); + if (end <= pos + mark.length) continue; + out += '[' + tag + ']' + inline(text.slice(pos + mark.length, end), onImage) + '[/' + tag + ']'; + pos = end + mark.length; matched = true; break; + } + if (!matched) out += text[pos++]; + } + return out; + } + + function markdownToBBCode(markdown, onImage) { + const lines = markdown.replace(/\r\n?/g, '\n').split('\n'); + const output = []; + let list = '', quote = false, code = false, fence = ''; + const closeList = () => { if (list) output.push('[/list]'); list = ''; }; + for (let index = 0; index < lines.length; index++) { + const line = lines[index]; + const codeMark = line.match(/^\s*(`{3,}|~{3,})/); + if (codeMark && (!code || codeMark[1][0] === fence)) { + closeList(); + output.push(code ? '[/code]' : '[code]'); + code = !code; fence = codeMark[1][0]; continue; + } + if (code) { output.push(line.replace(/\[\/code\]/gi, '［/code］')); continue; } + const quoted = /^\s*>\s?/.test(line); + if (quoted !== quote) { closeList(); output.push(quoted ? '[quote]' : '[/quote]'); quote = quoted; } + const content = quoted ? line.replace(/^\s*>\s?/, '') : line; + const item = content.match(/^\s*(?:([-+*])|\d+[.)])\s+(.+)$/); + if (item) { + const type = item[1] ? '[list]' : '[list=1]'; + if (list !== type) { closeList(); output.push(type); list = type; } + output.push('[*]' + inline(item[2], onImage)); continue; + } + closeList(); + const heading = content.match(/^\s{0,3}(#{1,6})\s+(.+?)\s*#*$/); + if (heading) output.push('[b]' + inline(heading[2], onImage) + '[/b]'); + else if (/^\s*(?:---+|\*\*\*+|___+)\s*$/.test(content)) output.push('[hr]'); + else output.push(inline(content, onImage)); + } + closeList(); + if (quote) output.push('[/quote]'); + if (code) output.push('[/code]'); + return output.join('\n').trim(); + } + + function compile(markdown, mdPath, fileMap, titleOverride) { + let body = String(markdown).replace(/^\uFEFF/, '').replace(/\r\n?/g, '\n'); + const firstHeading = body.match(/^\s*#\s+([^\n]+)\n?/); + const title = String(titleOverride || firstHeading?.[1] || mdPath.split('/').pop().replace(/\.md$/i, '')).trim(); + if (firstHeading) body = body.slice(firstHeading[0].length).trim(); + if (!title || Array.from(title).length > 80) throw new Error('标题为空或超过 80 字，请修改 Markdown 标题后重试。'); + if (!body.trim()) throw new Error('正文为空。'); + const warnings = []; + if (/<\/?[a-z][^>]*>/i.test(body)) warnings.push('存在 HTML，将作为文字保留；请检查排版。'); + if (/^\s*\|.*\|\s*$/m.test(body)) warnings.push('表格暂按原文保留，需手动检查。'); + if (/!\[[^\]]*\]\s*\[[^\]]*\]/.test(body) || /^\s*\[[^\]]+\]:/m.test(body)) { + throw new Error('暂不支持引用式 Markdown 图片/链接，请改成 ![](图片路径) 或 [文字](网址)。'); + } + const images = new Map(); + // Validate every image before any network request; repeated references upload once. + markdownToBBCode(body, (target) => { + const path = imagePath(mdPath, target); + const file = fileMap.get(path); + if (!file) throw new Error('找不到配图：' + path); + if (!IMAGE_EXT.test(path)) throw new Error('网站仅支持 JPG、JPEG、PNG、GIF：' + path); + if (!file.size || file.size >= MAX_IMAGE_SIZE) throw new Error('配图为空或达到 20 MB：' + path); + images.set(path, file); + return '[图片：' + path + ']'; + }); + return { title, body, mdPath, images, warnings, + render(aids) { + return markdownToBBCode(body, target => { + const path = imagePath(mdPath, target); + const aid = aids.get(path); + if (!/^[1-9]\d*$/.test(String(aid))) throw new Error('配图尚未上传：' + path); + return '[attachimg]' + aid + '[/attachimg]'; + }); + } + }; + } + + async function prepareFiles(files, markdownPath) { + const fileMap = new Map(); + for (const file of Array.from(files)) { + const path = normalizePath(file.webkitRelativePath || file.name); + if (fileMap.has(path)) throw new Error('文件路径重复：' + path); + fileMap.set(path, file); + } + const candidates = Array.from(fileMap.keys()).filter(p => /\.md$/i.test(p)).sort(); + if (!candidates.length) throw new Error('所选目录中没有 .md 文件。'); + if (!markdownPath && candidates.length > 1) return { candidates, files: Array.from(files) }; + const mdPath = markdownPath || candidates[0]; + const md = fileMap.get(mdPath); + if (!md) throw new Error('指定的 Markdown 文件不存在。'); + return compile(await md.text(), mdPath, fileMap); + } + + async function preparePackage(data) { + if (!data || data.schemaVersion !== 1 || typeof data.markdown !== 'string' || !Array.isArray(data.images)) { + throw new Error('文章包格式错误，需要 schemaVersion: 1、markdown 和 images。'); + } + const map = new Map(); + for (const item of data.images) { + const path = normalizePath(item.path); + if (map.has(path)) throw new Error('文章包图片路径重复：' + path); + let blob = item.blob; + if (!blob && typeof item.base64 === 'string') { + const binary = atob(item.base64); + blob = new Blob([Uint8Array.from(binary, ch => ch.charCodeAt(0))], { type: item.mime || 'application/octet-stream' }); + } + if (!blob || typeof blob.arrayBuffer !== 'function') throw new Error('文章包缺少图片数据：' + path); + map.set(path, blob); + } + return compile(data.markdown, normalizePath(data.markdownPath || 'article.md'), map, data.title); + } + + function parseAid(text) { + const value = String(text).trim(); + // The site's actual WebUploader adapter uses a positive integer response. + if (!/^(?:[1-9]\d*|"[1-9]\d*")$/.test(value)) throw new Error('服务器未返回有效附件编号（可能登录过期、超出权限或上传失败）。'); + return value.replace(/"/g, ''); + } + + function mount(win) { + const doc = win.document; + const params = new URLSearchParams(win.location.search); + if (params.get('mod') !== 'post' || params.get('action') !== 'newthread' || !doc.querySelector('#subject') || !doc.querySelector('#e_textarea')) return; + if (win.DWW11Importer) return; + let article = null, busy = false, candidates = null, lastResult = null, savedBackup = null, stageRevision = 0; + const cache = new Map(), urls = [], logs = []; + const host = doc.createElement('div'); + host.id = 'dww11-importer'; + host.style.cssText = 'position:fixed;right:18px;bottom:18px;z-index:2147483000'; + const shadow = host.attachShadow({ mode: 'open' }); + shadow.innerHTML = `
本地文章导入 · 1.0
+ 选择整个文章文件夹，检查后上传配图并填写。发布由你操作。网站自带的自动保存仍可能运行。 +

+ + +

尚未选择目录

+ + +
`; + doc.body.appendChild(host); + const $ = id => shadow.getElementById(id); + const summary = () => ({ version: VERSION, busy, ready: !!article, title: article?.title || null, + markdownPath: article?.mdPath || null, imageCount: article?.images.size || 0, + warnings: article?.warnings || [], result: lastResult }); + function notify(phase, message, extra = {}) { + $('status').textContent = message; + $('status').className = phase === 'error' ? 'error' : phase === 'complete' ? 'success' : ''; + logs.push({ time: new Date().toISOString(), phase, message, ...extra }); + $('log').hidden = false; + $('log').textContent = logs.slice(-8).map(l => l.message).join('\n'); + win.dispatchEvent(new CustomEvent('dww11-importer:progress', { detail: { phase, message, ...extra } })); + } + function releasePreviews() { while (urls.length) URL.revokeObjectURL(urls.pop()); } + function clearStage() { + article = null; lastResult = null; candidates = null; releasePreviews(); + $('preview').hidden = true; $('md').hidden = true; $('import').disabled = true; + } + function showArticle(prepared) { + article = prepared; lastResult = null; releasePreviews(); + $('preview').hidden = false; + $('title').textContent = article.title; + $('body').textContent = article.body; + $('warnings').textContent = article.warnings.join('；'); + $('images').replaceChildren(); + for (const [path, blob] of article.images) { + const img = doc.createElement('img'); + img.src = URL.createObjectURL(blob); urls.push(img.src); img.alt = path; img.title = path; + $('images').appendChild(img); + } + $('import').disabled = false; + notify('ready', `已检查：${article.images.size} 张图片。点击“上传配图并填写”开始导入。`); + return summary(); + } + async function stageFiles(files, options = {}) { + if (busy) throw new Error('正在导入，请稍候。'); + clearStage(); + const revision = ++stageRevision; + const list = Array.from(files); + const prepared = await prepareFiles(list, options.markdownPath); + if (revision !== stageRevision) return { cancelled: true }; + if (prepared.candidates) { + candidates = prepared.files; + $('md').replaceChildren(new Option('请选择目录中的 Markdown 文件', '')); + for (const path of prepared.candidates) $('md').appendChild(new Option(path, path)); + $('md').hidden = false; + notify('choose-markdown', '目录中有多个 Markdown 文件，请选择一篇。'); + return { candidates: prepared.candidates }; + } + return showArticle(prepared); + } + async function stagePackage(data) { + if (busy) throw new Error('正在导入，请稍候。'); + clearStage(); + const revision = ++stageRevision; + const prepared = await preparePackage(data); + if (revision !== stageRevision) return { cancelled: true }; + return showArticle(prepared); + } + const snapshot = () => ({ title: doc.querySelector('#subject').value, + mode: Number(win.wysiwyg), text: win.getEditorContents() }); + function assertEditor() { + for (const name of ['getEditorContents', 'switchEditor']) { + if (typeof win[name] !== 'function') throw new Error('未识别到网站编辑器：' + name + '。请刷新页面后重试。'); + } + if (!win.imgUpload?.settings || typeof win.updateImageList !== 'function') throw new Error('网站图片上传组件尚未就绪，请刷新后重试。'); + if (Number(win.allowbbcode) === 0 || Number(win.allowimgcode) === 0) throw new Error('当前版块或账号不支持正文格式/图片。'); + } + async function uploadImage(blob, path, settings, signal) { + signal?.throwIfAborted(); + const url = new URL(settings.upload_url, win.location.href); + if (url.origin !== win.location.origin || url.pathname !== '/misc.php' || url.searchParams.get('operation') !== 'upload') { + throw new Error('上传地址与预期不符，已停止。'); + } + const hash = Array.from(new Uint8Array(await win.crypto.subtle.digest('SHA-256', await blob.arrayBuffer())), n => n.toString(16).padStart(2, '0')).join(''); + const key = url.href + ':' + settings.post_params.uid + ':' + hash; + if (cache.has(key)) { notify('upload', '复用已上传图片：' + path); return cache.get(key); } + const data = new FormData(); + for (const [key, value] of Object.entries(settings.post_params)) data.append(key, String(value)); + data.set('type', 'image'); + data.set('filetype', blob.type || (/\.png$/i.test(path) ? 'image/png' : /\.gif$/i.test(path) ? 'image/gif' : 'image/jpeg')); + data.append(settings.file_post_name || 'Filedata', blob, path.split('/').pop()); + const control = new AbortController(), timer = setTimeout(() => control.abort(), 90000); + try { + signal?.throwIfAborted(); + signal?.addEventListener('abort', () => control.abort(), { once: true }); + const response = await win.fetch(url.href, { method: 'POST', body: data, credentials: 'same-origin', redirect: 'error', signal: control.signal }); + if (!response.ok) throw new Error('图片上传请求失败：HTTP ' + response.status); + const aid = parseAid(await response.text()); + cache.set(key, aid); + return aid; + } catch (error) { + if (error.name === 'AbortError') throw new Error('上传超时；该图片可能已到达服务器，请检查网站图片列表后再重试。'); + throw error; + } finally { clearTimeout(timer); } + } + async function registerImages(aids, signal) { + signal?.throwIfAborted(); + if (!aids.length) return; + const ids = new Set(aids); + doc.querySelectorAll('#imgattachlist [id^="image_td_"],#imgattachlist [id^="image_"]').forEach(el => { + const id = el.id.match(/^(?:image_td_|image_)(\d+)$/)?.[1]; if (id) ids.add(id); + }); + const ready = () => aids.every(id => doc.getElementById('image_' + id)); + if (ready()) return; + // Use the site's own list loader, which registers attachment form fields too. + win.updateImageList(1, Array.from(ids).join('|')); + await new Promise((resolve, reject) => { + const timer = setTimeout(() => { observer.disconnect(); reject(new Error('图片已上传，但网站图片列表加载超时。重试会复用本页已上传图片。')); }, 25000); + signal?.addEventListener('abort', () => { clearTimeout(timer); observer.disconnect(); reject(new Error('流程已终止')); }, { once: true }); + const check = () => { if (ready()) { clearTimeout(timer); observer.disconnect(); resolve(); } }; + const observer = new MutationObserver(check); + observer.observe(doc.body, { childList: true, subtree: true }); check(); + }); + } + function setEditor(title, bbcode) { + win.switchEditor(0); + if (Number(win.wysiwyg) !== 0) throw new Error('无法切换编辑器为纯文本模式。'); + const textarea = doc.querySelector('#e_textarea'); + textarea.value = bbcode; + doc.querySelector('#subject').value = title; + for (const el of [textarea, doc.querySelector('#subject')]) { + el.dispatchEvent(new Event('input', { bubbles: true })); el.dispatchEvent(new Event('change', { bubbles: true })); + } + // Let Discuz generate the WYSIWYG content with native attachment metadata. + win.switchEditor(1); + const switcher = doc.querySelector('#e_switchercheck'); + if (switcher) switcher.checked = Number(win.wysiwyg) === 0; + } + async function importPrepared(options = {}) { + const { signal, automatic = false } = options; + signal?.throwIfAborted(); + if (busy) throw new Error('正在导入，请勿重复点击。'); + if (!article) throw new Error('请先选择文章目录或文章包。'); + assertEditor(); + for (const id of ['bbcodeoff', 'htmlon']) { + if (doc.getElementById(id)?.checked) throw new Error('请先关闭“禁用 Discuz! 代码”和“HTML 代码”，再导入。'); + } + const before = snapshot(); + if ((before.title.trim() || before.text.replace(/<[^>]*>/g, '').trim() || / { throw new Error('编辑器已有内容，请人工处理旧稿后重试'); })() : !win.confirm('当前编辑器已有内容。导入将替换标题和正文，是否继续？'))) return { cancelled: true }; + const selected = article; + busy = true; + const controls = ['choose', 'package', 'import', 'md'].map($); + controls.forEach(el => { el.disabled = true; }); + // Prevent accidental submission of a partly imported article. + const blockSubmit = event => { event.preventDefault(); event.stopImmediatePropagation(); notify('busy', '正在导入，请等待完成后再操作发布。'); }; + const form = doc.querySelector('#postform'); + form.addEventListener('submit', blockSubmit, true); + const submitButtons = Array.from(form.querySelectorAll('button[type="submit"],button[name],input[type="submit"]')); + const previousDisabled = submitButtons.map(el => el.disabled); + submitButtons.forEach(el => { el.disabled = true; }); + let committed = false; + try { + const aids = new Map(); + const settings = win.imgUpload.settings; + const max = Math.min(MAX_IMAGE_SIZE, Number(settings.file_size_limit) * 1024 || MAX_IMAGE_SIZE); + for (const [path, blob] of selected.images) if (blob.size >= max) throw new Error('配图超过当前网站限制：' + path); + let index = 0; + for (const [path, blob] of selected.images) { + notify('upload', `上传 ${++index}/${selected.images.size}：${path}`, { completed: index - 1, total: selected.images.size }); + aids.set(path, await uploadImage(blob, path, settings, signal)); + } + notify('register', '正在加载网站图片列表…'); + await registerImages(Array.from(new Set(aids.values())), signal); + signal?.throwIfAborted(); + const now = snapshot(); + if ((now.title !== before.title || now.text !== before.text) && (automatic ? (() => { throw new Error('上传期间编辑器被修改，已保留当前内容'); })() : !win.confirm('上传期间你修改了编辑器。是否用导入文章替换最新内容？'))) { + notify('cancelled', '已保留当前正文；图片已上传，可稍后再次导入。'); return { cancelled: true }; + } + const backup = snapshot(); + const bbcode = selected.render(aids); + // Preserve a local, downloadable snapshot before changing title or body. + savedBackup = { title: backup.title, content: backup.text, mode: backup.mode, createdAt: new Date().toISOString() }; + try { + for (const id of ['bbcodeoff', 'htmlon']) { + const el = doc.getElementById(id); + if (el && id === 'bbcodeoff' && el.checked) throw new Error('请先取消“禁用 Discuz! 代码”，再重试。'); + if (el && id === 'htmlon' && el.checked) throw new Error('请先关闭“HTML 代码”，再重试。'); + } + signal?.throwIfAborted(); + setEditor(selected.title, bbcode); + const raw = win.getEditorContents(); + if (Number(win.wysiwyg) === 1) { + for (const id of new Set(aids.values())) if (!raw.includes('attachimg_' + id)) throw new Error('富文本图片转换未通过检查。'); + } else if (raw !== bbcode) throw new Error('正文填写校验失败。'); + if (doc.querySelector('#subject').value !== selected.title) throw new Error('标题填写校验失败。'); + committed = true; + } catch (error) { + // Restore the exact editor representation saved immediately before filling. + win.switchEditor(backup.mode); + if (backup.mode) win.editdoc.body.innerHTML = backup.text; + else doc.querySelector('#e_textarea').value = backup.text; + doc.querySelector('#subject').value = backup.title; + const switcher = doc.querySelector('#e_switchercheck'); if (switcher) switcher.checked = !backup.mode; + throw error; + } + lastResult = { title: selected.title, images: Object.fromEntries(aids), completedAt: new Date().toISOString() }; + notify('complete', `已填写标题、正文和 ${aids.size} 张配图。请检查排版，随后手动发表。`); + return lastResult; + } catch (error) { + notify('error', error.message + (committed ? '' : ' 标题和正文未替换；已上传的图片会保留。')); + throw error; + } finally { + busy = false; form.removeEventListener('submit', blockSubmit, true); + submitButtons.forEach((el, index) => { el.disabled = previousDisabled[index]; }); + controls.forEach(el => { el.disabled = false; }); + $('import').disabled = !article; + } + } + function downloadJSON(value, filename) { + const url = URL.createObjectURL(new Blob([JSON.stringify(value, null, 2)], { type: 'application/json' })); + const link = doc.createElement('a'); link.href = url; link.download = filename; link.click(); + setTimeout(() => URL.revokeObjectURL(url), 1000); + } + // Public v1 interface. Staging is read-only; importPrepared is the explicit upload/fill step. + // No postMessage listener, localhost service, publishing endpoint or saved credentials. + const api = Object.freeze({ version: VERSION, schemaVersion: 1, stageFiles, stagePackage, + getState: summary, openPicker: () => { if (!busy) $('folder').click(); }, importPrepared, + getBackup: () => savedBackup }); + win.DWW11Importer = api; + $('choose').onclick = () => { $('folder').value = ''; $('folder').click(); }; + $('package').onclick = () => { $('json').value = ''; $('json').click(); }; + const handleError = error => notify('error', error.message || String(error)); + $('folder').onchange = () => stageFiles($('folder').files).catch(handleError); + $('json').onchange = async () => { + try { const file = $('json').files[0]; if (file) await stagePackage(JSON.parse(await file.text())); } + catch (error) { handleError(error); } + }; + $('md').onchange = () => { + const files = candidates, path = $('md').value; + if (files && path) stageFiles(files, { markdownPath: path }).catch(handleError); + }; + $('import').onclick = () => importPrepared().catch(handleError); + $('diagnostics').onclick = () => downloadJSON({ ...summary(), logs }, 'dww11-import-diagnostics.json'); + win.addEventListener('pagehide', releasePreviews, { once: true }); + } + return { VERSION, normalizePath, imagePath, readLink, markdownToBBCode, compile, prepareFiles, preparePackage, parseAid, mount }; +}); diff --git a/browser/local-bridge.user.js b/browser/local-bridge.user.js new file mode 100644 index 0000000..71b6cec --- /dev/null +++ b/browser/local-bridge.user.js @@ -0,0 +1,73 @@ +// ==UserScript== +// @name 新闻工作台 · 本地连接 +// @namespace local.dww11.auto-news +// @version 0.1.0 +// @match https://www.dww11.com/* +// @match https://dww11.com/* +// @match https://house.dww11.com/* +// @grant GM_xmlhttpRequest +// @grant GM_getValue +// @grant GM_setValue +// @grant GM_addValueChangeListener +// @connect 127.0.0.1 +// @run-at document-start +// @noframes +// ==/UserScript== +(() => { + 'use strict'; + const allowed = new Set(['heartbeat','next','package','event','accept','switch-begin','takeover','stop','current']); + let token = GM_getValue('pairToken',''), port = GM_getValue('pairPort',8770); + let stopRevision = 0; + const signalStop = () => { stopRevision++; document.dispatchEvent(new CustomEvent('dww11:auto-stop')); }; + GM_addValueChangeListener('halted', (_key, _old, value) => { if (value) signalStop(); }); + function request(route, body) { + return new Promise((resolve, reject) => { + if (!token) return reject(new Error('请在左下角填入本地工作台的连接码')); + GM_xmlhttpRequest({method:'POST',url:`http://127.0.0.1:${port}/bridge/${route}`, + headers:{'Content-Type':'application/json','X-Session-Token':token},data:JSON.stringify(body),timeout:60000, + onload(response) { try { const value=JSON.parse(response.responseText); if(response.status!==200) throw new Error(value.error || '本地连接失败'); resolve(value); } catch(error) { reject(error); } }, + onerror:()=>reject(new Error('本地服务未连接，请检查服务与脚本权限')), + ontimeout:()=>reject(new Error('本地服务超时，任务已暂停'))}); + }); + } + document.addEventListener('dww11:local-request', async event => { + let message; + try {message=JSON.parse(event.detail);} catch {return;} + if (!allowed.has(message.route) || typeof message.id !== 'string') return; + try { + if (message.route==='stop') { GM_setValue('halted',true); signalStop(); } + const revision = stopRevision; + let value=await request(message.route,message.body || {}); + if (message.route==='heartbeat') { + if (revision !== stopRevision) value = {...value, running:false, reason:'终止后忽略旧连接响应'}; + GM_setValue('halted',!value.running); + if (!value.running) signalStop(); + } + document.dispatchEvent(new CustomEvent('dww11:local-response',{detail:JSON.stringify({id:message.id,value})})); + } catch(error) { + if (message.route==='heartbeat') {GM_setValue('halted',true); signalStop();} + document.dispatchEvent(new CustomEvent('dww11:local-response',{detail:JSON.stringify({id:message.id,error:error.message})})); + } + }); + function mount() { + if (!document.body || document.getElementById('auto-news-connection')) return; + const host=document.createElement('div');host.id='auto-news-connection'; + host.style.cssText='position:fixed;left:16px;bottom:16px;z-index:2147483647'; + const shadow=host.attachShadow({mode:'closed'}); + shadow.innerHTML='
新闻工作台 · 本地连接
连接设置
请启动本地工作台并配对
'; + const $=id=>shadow.getElementById(id);$('port').value=port; + $('save').onclick=()=>{ + const value=Number($('port').value);if(!Number.isInteger(value)||value<1||value>65535){$('status').textContent='端口无效';return;} + if($('token').value.trim()) token=$('token').value.trim();port=value; + GM_setValue('pairToken',token);GM_setValue('pairPort',port);$('token').value='';$('status').textContent='已保存；服务重启后需要更新连接码'; + }; + $('halt').onclick=async()=>{ + GM_setValue('halted',true);signalStop();$('status').textContent='已终止；在途请求仍可能完成'; + try {await request('stop',{});} catch(error) {$('status').textContent+='。'+error.message;} + }; + document.addEventListener('dww11:connection-status',event=>{$('status').textContent=String(event.detail).slice(0,250);}); + document.body.append(host); + if(GM_getValue('halted',true)) signalStop(); + } + if(document.readyState==='loading') document.addEventListener('DOMContentLoaded',mount,{once:true}); else mount(); +})(); diff --git a/browser/runner.js b/browser/runner.js new file mode 100644 index 0000000..4e5ce89 --- /dev/null +++ b/browser/runner.js @@ -0,0 +1,173 @@ +/* Page-side orchestrator. This file never clicks or submits the publication form. */ +(() => { + 'use strict'; + if (window.DWW11NewsRunner) return; + window.DWW11NewsRunner = true; + const SLOT='auto-news-current'; + const owner=sessionStorage.getItem('auto-news-owner') || crypto.randomUUID(); + sessionStorage.setItem('auto-news-owner',owner); + let run=null, working=false, halted=true, aborter=null, active=null, tickBusy=false; + const pending=new Map(); + function rpc(route,body={}) { + return new Promise((resolve,reject)=>{ + const id=crypto.randomUUID(); + const timer=setTimeout(()=>{pending.delete(id);reject(new Error('本地连接无响应'));},65000); + pending.set(id,{resolve,reject,timer}); + document.dispatchEvent(new CustomEvent('dww11:local-request',{detail:JSON.stringify({id,route,body:{owner,...body}})})); + }); + } + document.addEventListener('dww11:local-response',event=>{ + let data;try{data=JSON.parse(event.detail);}catch{return;} + const waiter=pending.get(data.id);if(!waiter)return; + clearTimeout(waiter.timer);pending.delete(data.id); + data.error?waiter.reject(new Error(data.error)):waiter.resolve(data.value); + }); + const status=message=>document.dispatchEvent(new CustomEvent('dww11:connection-status',{detail:message})); + document.addEventListener('dww11:auto-stop',()=>{halted=true;aborter?.abort(new Error('流程已终止'));}); + function account() { + const element=document.querySelector('#mumucms_username'); + if(!element)return null; + const name=[...element.childNodes].filter(n=>n.nodeType===Node.TEXT_NODE).map(n=>n.textContent).join('').trim(); + const links=[element,...element.querySelectorAll('a')].filter(e=>e.href); + let uid=null; + for(const link of links) { + const href=link.href; + uid=new URL(href,location.href).searchParams.get('uid') || href.match(/space-uid-(\d+)/)?.[1]; + if(uid)break; + } + return uid&&name?{uid,name}:null; + } + function extension() { + try{return JSON.parse(document.querySelector('#dww11-extension-panel')?.getAttribute('data-auto-news-state') || '{}');}catch{return {};} + } + function assertLive(epoch) { + if(halted||!run?.running||run.epoch!==epoch)throw new Error('流程已暂停或终止'); + if(active?.account?.uid!==account()?.uid)throw new Error('当前账号与任务不一致'); + } + function editorSnapshot() { + const body=document.querySelector('#e_iframe')?.contentDocument?.body; + if(!body)throw new Error('找不到可视化编辑器'); + return {title:document.querySelector('#subject')?.value || '', + images:[...body.querySelectorAll('img')].map(x=>({id:x.id,src:x.getAttribute('src')})), + // Snapshot only final submitted content; never includes hidden tokens or the full form. + html:body.innerHTML.slice(0,500000), text:body.innerText.slice(0,100000)}; + } + function saveLocal(value) {sessionStorage.setItem(SLOT,JSON.stringify(value));} + function loadLocal(){try{return JSON.parse(sessionStorage.getItem(SLOT)||'null');}catch{return null;}} + async function event(state,extra={}) {return rpc('event',{id:active.id,state,epoch:run.epoch,...extra});} + async function fail(error) { + status(error.message); + if(active)try{await event('needs_attention',{error:error.message});}catch{} + halted=true;aborter?.abort();document.dispatchEvent(new CustomEvent('dww11:auto-stop')); + } + function editorPage(job) { + const u=new URL(location.href); + return u.searchParams.get('mod')==='post'&&u.searchParams.get('action')==='newthread'&&u.searchParams.get('fid')===String(job.fid); + } + async function prepare(job) { + working=true;active=job;aborter=new AbortController();const epoch=run.epoch; + try { + assertLive(epoch); + if(!editorPage(job)) { + saveLocal({id:job.id}); + location.assign(`https://www.dww11.com/forum.php?mod=post&action=newthread&fid=${job.fid}`);return; + } + if(!window.DWW11Importer||!window.DWW11Formatter)throw new Error('导入或排版模块尚未就绪，请检查安装'); + status('正在检查文章包…'); + const pack=await rpc('package',{id:job.id});assertLive(epoch); + const prepared=await window.DWW11Importer.stagePackage(pack);assertLive(epoch); + if(prepared.warnings?.length)throw new Error('文章需要人工处理：'+prepared.warnings.join('；')); + await event('importing');assertLive(epoch);status('上传图片并填写文章…'); + const result=await window.DWW11Importer.importPrepared({automatic:true,signal:aborter.signal});assertLive(epoch); + if(result?.cancelled)throw new Error('导入已取消'); + await event('formatting');assertLive(epoch); + window.DWW11Formatter.format(job.source);assertLive(epoch); + const snapshot=editorSnapshot(); + if(snapshot.title!==job.title)throw new Error('标题校验失败'); + const aids=new Set(Object.values(result.images)); + for(const aid of aids) if(!snapshot.images.some(x=>x.id==='attachimg_'+aid))throw new Error('配图附件缺失：'+aid); + await event('awaiting_user_review',{snapshot});assertLive(epoch); + active={...job,state:'awaiting_user_review'};saveLocal({id:job.id}); + status('已完成排版，请核对内容并亲手点击“发表帖子”。'); + }catch(error){await fail(error);}finally{working=false;} + } + // Record only trusted user activation. Never replay a click, call submit(), or send a post request. + document.addEventListener('click',event=>{ + if(!event.isTrusted||!event.target.closest?.('#postsubmit')||active?.state!=='awaiting_user_review')return; + try { + const snapshot=editorSnapshot(); + const local={id:active.id,snapshot,clickedAt:Date.now(),observed:false};saveLocal(local); + rpc('event',{id:active.id,state:'user_submitting',epoch:run?.epoch,snapshot}) + .then(()=>{const latest=loadLocal();if(latest?.clickedAt===local.clickedAt)saveLocal({...local,observed:true});}) + .catch(error=>status('提交记录待恢复：'+error.message)); + active.state='user_submitting';status('已观察到人工点击，等待结果页核对。'); + }catch(error){status('提交快照记录失败：'+error.message);} + },true); + async function observeResult(job) { + const local=loadLocal(); + if(local?.id===job.id&&local.snapshot&&job.state==='awaiting_user_review') { + await rpc('event',{id:job.id,state:'user_submitting',epoch:run.epoch,snapshot:local.snapshot}); + job.state='user_submitting'; + } + if(job.state==='user_submitting') { + // Result selectors intentionally await user-provided HTML; URL alone is not proof. + if(!editorPage(job) || (local?.clickedAt && Date.now()-local.clickedAt>45000)) { + await rpc('event',{id:job.id,state:'submit_unknown',error:'等待结果页 HTML 适配；候选页面：'+location.href}); + await rpc('stop'); + status('已记录候选结果页；尚不能自动核对。流程已暂停，请补充结果页 HTML。'); + } + }else if(job.state==='submit_unknown')status('发布结果待核对；不会重发、计数或换号。'); + } + async function switchAccount() { + if(working||halted)return; + if(location.origin!=='https://www.dww11.com'||location.pathname!=='/') { + location.assign('https://www.dww11.com/');return; + } + const ext=extension(),button=document.querySelector('#dww11-extension-next'); + if(!ext.ready||!ext.idle||!button||button.disabled) {status('请安装并重新加载带联动接口的换号插件');return;} + await rpc('switch-begin'); + if(halted||!run?.running)return; + button.click();status('正在换号；等待插件完成并核对新账号'); + } + async function tick() { + if(tickBusy)return;tickBusy=true; + try { + run=await rpc('heartbeat',{account:account(),url:location.href,extension:extension()}); + halted=!run.running; + if(!run.running) {aborter?.abort();document.dispatchEvent(new CustomEvent('dww11:auto-stop'));} + if(working)return; + // Passive result recording is permitted after Stop, but no new business actions. + if(run.active) { + const local=loadLocal(); + if(local?.id===run.active&&local.snapshot&&!run.running)status('流程已暂停；提交结果仍需核对'); + } + if(!run.running) { + if(run.active && run.owner===owner) {const saved=await rpc('current');if(saved.job) {active=saved.job;await observeResult(saved.job);}} + status(run.reason || '流程已暂停');return; + } + const next=await rpc('next',{account:account(),extension:extension()});run=next.run; + if(next.job)active=next.job; + if(next.action==='prepare'||(next.action==='resume'&&next.job.state==='preparing'))void prepare(next.job); + else if(next.action==='resume') { + await observeResult(next.job); + if(next.job.state==='awaiting_user_review') { + if(!editorPage(next.job)||!document.querySelector('#subject')?.value) await fail(new Error('待审稿页面已丢失，请人工核对旧稿，不自动重新导入')); + else status('等待你亲手发表；程序不再修改编辑器'); + } + else if(['importing','formatting'].includes(next.job.state))await fail(new Error('导入阶段发生中断，请检查编辑器和已上传图片后处理任务')); + else if(next.job.state==='needs_attention')status(next.job.error); + }else if(next.action==='switch')await switchAccount(); + else if(next.action==='switch_wait')status('等待换号结果；若插件已暂停，请人工处理后继续'); + else if(next.action==='login')status('未能读取当前账号 UID，请登录并确认账号元素'); + else if(next.action==='other_tab')status('另一个标签持有任务；如需接管请先暂停'); + else if(next.action==='interval')status('等待设定的处理间隔'); + else status(run.reason || '等待任务'); + }catch(error){status(error.message);halted=true;aborter?.abort();document.dispatchEvent(new CustomEvent('dww11:auto-stop'));} + finally{tickBusy=false;} + } + const takeover=document.createElement('button');takeover.type='button';takeover.textContent='接管已暂停任务'; + takeover.style.cssText='position:fixed;left:16px;top:16px;z-index:2147483646;padding:8px;background:#fff;border:1px solid #aab;border-radius:6px'; + takeover.onclick=async()=>{try{await rpc('takeover');status('已接管；核对当前页面后在工作台继续');}catch(error){status(error.message);}}; + document.body.append(takeover); + setInterval(tick,2000);tick(); +})(); diff --git a/build_browser.py b/build_browser.py new file mode 100644 index 0000000..6e9b75d --- /dev/null +++ b/build_browser.py @@ -0,0 +1,23 @@ +"""Build the page-context userscript from reviewed local components; no external assets.""" +from pathlib import Path +ROOT = Path(__file__).resolve().parent +header = '''// ==UserScript== +// @name 新闻工作台 · 导入排版与流程 +// @namespace local.dww11.auto-news +// @version 0.1.0 +// @match https://www.dww11.com/* +// @match https://dww11.com/* +// @match https://house.dww11.com/* +// @grant none +// @run-at document-idle +// @noframes +// ==/UserScript== +''' +parts = [] +for name in ('importer.js', 'formatter.js', 'runner.js'): + source = (ROOT / 'browser' / name).read_text() + if '// ==/UserScript==' in source: + source = source.split('// ==/UserScript==', 1)[1] + parts.append(source) +(ROOT / 'browser/auto-news.user.js').write_text(header + '\n'.join(parts)) +print('已生成 browser/auto-news.user.js') diff --git a/modules/downloader/README.md b/modules/downloader/README.md new file mode 100644 index 0000000..bb0daa7 --- /dev/null +++ b/modules/downloader/README.md @@ -0,0 +1,57 @@ +# 探数新闻下载器 + +在本机浏览器中填写 API Key、获取频道、选择数量，下载新闻正文和图片。所有项目文件与下载结果都位于本目录，不修改微信下载器。 + +## 启动 + +安装 `uv` 后，macOS 可以双击 `start.command`。也可以在本目录运行： + +```sh +uv run --no-project --python 3.12 --with-requirements requirements.txt python app.py +``` + +启动后自动打开 http://127.0.0.1:8765 。保留启动窗口，退出时按 Ctrl+C。端口被占用时加 `--port 8766`；不自动打开浏览器时加 `--no-browser`。 + +1. 填写探数 API Key，点击「获取新闻频道」。频道来自真实接口，不使用写死的列表。 +2. 选择频道、输入目标数量，点击「开始下载」。 +3. 页面显示成功保存的数量、百分比、重复数、失败数和最近 300 条日志。日志固定高度，可滚动；向上查看时不会强制滚回底部。 +4. 下载结果保存在本目录的 `downloads` 文件夹。点击「停止下载」后，等待当前请求或文章保存结束。 +5. 「调试终端」默认折叠，支持频道查询以及列表查询的 `type`、`num`、`start` 参数。测试请求只显示响应，不保存文章；同样消耗 API 调用额度。输出最多保留 100000 字符。 + +密钥仅在页面和服务运行内存中使用，不保存到配置、历史数据库或浏览器存储。服务仅监听本机地址。刷新页面可查看当前任务进度，开始新任务需重新填写密钥。单个服务同时只运行一个下载任务，请勿同时启动多个实例操作同一下载目录。 + +## 保存格式 + +沿用 `wechat_official_acc_article_downloader` 的格式和图片处理规则： + +```text +downloads/ +├── .history.sqlite3 +└── 新闻标题/ + ├── 新闻标题.md + ├── image001.jpg + └── image002.png +``` + +Markdown 开头是一级标题，空行后直接接由接口 `content` 转换的正文，不额外添加接口 `time` 对应的发布时间或分隔线。末尾为 `来源：{src}，如有侵权，请联系删除。`，来源为空时使用「未知作者」。不在开头添加原文链接或作者。正文中的图片下载到同一目录、使用相对引用、按真实文件类型命名，同一图片地址只下载一次。接口的 `pic` 封面不单独插入正文。 + +标题中的不合法字符会替换；不同文章碰巧同名时添加 ` (2)` 等后缀，目录和 Markdown 文件保持同名。任何正文图片下载失败，该篇不计入完成数，并清理半成品，再继续其他新闻；下次任务可以重试。 + +## 去重与分页 + +- 下载图片前，检查原文 URL / PC URL（移除常见跟踪参数和片段）及规范化正文指纹。任一匹配即跳过，标题相同但正文和网址不同不会单凭标题去重。 +- SQLite 保存成功文章的指纹，跨任务、跨频道和服务重启后继续去重。被删除的文章目录不会阻止重新下载。不要删除 `.history.sqlite3`，否则会失去对应历史记录。 +- 每次任务从最新位置 `start=0` 开始，按返回数量推进，每页最多 40 条；重复和失败不计入成功数量，并继续后面的新闻。 +- 接口限制 `start ≤ 400`，一次任务最多覆盖约 440 条，具体还受返回数量和实时更新影响。达到分页边界或收到空列表时停止，未达目标就显示「未达到目标」，不会伪装成 100%。 +- 列表接口不自动重试，防止隐蔽消耗计费额度。API 业务错误、网络错误或响应格式错误会中断任务，已成功保存的文章保留。图片请求沿用原下载器的重试策略。 +- 新闻列表会实时变化，无法保证服务器在不同请求中不返回同一新闻；本工具在保存前去重，尽量避免重复图片下载与文件保存。 + +接口依据：[探数官方新闻 API 文档](https://www.tanshuapi.com/market/detail-85)。 + +## 验证 + +```sh +uv run --no-project --python 3.12 --with-requirements requirements.txt python -m unittest discover -s tests -v +``` + +测试使用模拟新闻响应与临时目录，不消耗真实 API 额度。覆盖格式与图片引用、图片失败清理、历史去重、分页边界、失败重试、取消、日志上限和本地 HTTP 接口。真实账号权限、余额、返回内容与远程图片可达性，需要在页面填入有效 Key 后验证。 diff --git a/modules/downloader/app.py b/modules/downloader/app.py new file mode 100644 index 0000000..efb4d21 --- /dev/null +++ b/modules/downloader/app.py @@ -0,0 +1,299 @@ +#!/usr/bin/env python3 +"""仅在本机运行的探数新闻下载器。""" +from contextlib import contextmanager +from collections import deque +from datetime import datetime +from hashlib import sha256 +from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer +from pathlib import Path +from urllib.parse import urlsplit, urlunsplit, parse_qsl, urlencode +import argparse +import json +import secrets +import sqlite3 +import threading +import time +import unicodedata +import webbrowser + +import requests +from bs4 import BeautifulSoup +from article_writer import save_article + +ROOT = Path(__file__).resolve().parent +API = 'https://api.tanshuapi.com/api/toutiao/v1/' + + +def api_request(key, endpoint, params=None): + if endpoint not in ('channel', 'index'): + raise ValueError('未知接口') + try: + # 不自动重试计费接口，避免一次操作产生不可见的重复调用。 + response = requests.get(API + endpoint, params={'key': key, **(params or {})}, timeout=(10, 40)) + response.raise_for_status() + payload = response.json() + except requests.RequestException: + raise ValueError('接口网络请求失败或超时，请在调试终端检查后重试') from None + except ValueError: + raise ValueError('接口未返回有效 JSON') from None + if not isinstance(payload, dict): + raise ValueError('接口响应格式错误') + return payload + + +def result_list(payload): + if payload.get('code') != 1: + raise ValueError(f"探数接口错误 {payload.get('code')}：{payload.get('msg', '未知错误')}") + data = payload.get('data') + if not isinstance(data, dict) or not isinstance(data.get('list'), list): + raise ValueError('接口响应缺少 data.list') + return data['list'] + + +def fingerprints(article): + values = [] + for field in ('url', 'weburl'): + value = str(article.get(field) or '').strip() + if value: + u = urlsplit(value) + query = [(k, v) for k, v in parse_qsl(u.query) if not k.lower().startswith('utm_') and k.lower() not in ('spm', 'from', 'pos', 'vt')] + values.append('url:' + urlunsplit(('', u.netloc.lower(), u.path, urlencode(sorted(query)), ''))) + body = BeautifulSoup(str(article.get('content') or ''), 'html.parser').get_text(' ', strip=True) + body = ''.join(unicodedata.normalize('NFKC', body).split()) + if body: + values.append('body:' + body) + return [sha256(value.encode()).hexdigest() for value in values] + + +class Downloader: + def __init__(self, root=ROOT / 'downloads', requester=api_request, writer=save_article, on_saved=None): + self.root = Path(root).resolve() + self.root.mkdir(parents=True, exist_ok=True) + self.requester, self.writer = requester, writer + self.on_saved = on_saved + self.lock = threading.RLock() + self.stop = threading.Event() + self.thread = None + self.logs = deque(maxlen=300) + self.seq = 0 + self.state = dict(status='idle', saved=0, target=0, skipped=0, failed=0, scanned=0, requests=0, channel='', message='等待开始') + with self.db() as db: + db.execute('CREATE TABLE IF NOT EXISTS seen (fingerprint TEXT PRIMARY KEY, directory TEXT NOT NULL)') + + @contextmanager + def db(self): + connection = sqlite3.connect(self.root / '.history.sqlite3') + try: + with connection: + yield connection + finally: + connection.close() + + def log(self, message): + with self.lock: + self.seq += 1 + self.logs.append(dict(id=self.seq, time=datetime.now().strftime('%H:%M:%S'), message=message)) + + def update(self, **values): + with self.lock: + self.state.update(values) + + def snapshot(self): + with self.lock: + return {**self.state, 'logs': list(self.logs), 'output': str(self.root)} + + def start(self, key, channel, target): + with self.lock: + if self.thread and self.thread.is_alive(): + raise ValueError('已有任务正在运行') + self.stop.clear() + self.logs.clear() + self.state = dict(status='running', saved=0, target=target, skipped=0, failed=0, scanned=0, requests=0, channel=channel, message='正在下载') + self.thread = threading.Thread(target=self.run, args=(key, channel, target), daemon=True) + self.thread.start() + + def run(self, key, channel, target): + saved = skipped = failed = scanned = calls = 0 + seen_in_run = set() + self.log(f'开始下载频道「{channel}」，目标 {target} 条；历史重复新闻将跳过') + try: + with self.db() as db: + offset = 0 + while offset <= 400 and saved < target and not self.stop.is_set(): + count = min(40, target - saved) + calls += 1 + self.update(requests=calls) + self.log(f'请求第 {calls} 页：start={offset}，num={count}') + items = result_list(self.requester(key, 'index', {'type': channel, 'num': count, 'start': offset})) + if not items: + self.log('接口返回空列表，已停止') + break + for article in items: + if saved >= target or self.stop.is_set(): + break + scanned += 1 + try: + if not isinstance(article, dict): + raise ValueError('新闻条目格式错误') + keys = fingerprints(article) + existing = any(k in seen_in_run for k in keys) + for k in keys: + row = db.execute('SELECT directory FROM seen WHERE fingerprint=?', (k,)).fetchone() + if row and Path(row[0]).is_dir(): + existing = True + seen_in_run.update(keys) + if existing: + skipped += 1 + self.log('跳过重复新闻：' + str(article.get('title', '无标题'))[:160]) + continue + result = self.writer(article, self.root) + try: + db.executemany('INSERT OR REPLACE INTO seen VALUES (?, ?)', [(k, result.directory) for k in keys]) + db.commit() + except Exception: + # 保存目录尚未登记成功，回滚本次产物，避免下次重复保存。 + import shutil + shutil.rmtree(result.directory, ignore_errors=True) + raise + saved += 1 + if self.on_saved: + try: + self.on_saved(article, result, keys) + except Exception as error: + self.log('文章已保存，入队需处理：' + str(error).replace(key, '[已隐藏]')[:300]) + self.log(f'下载新闻 {saved}/{target} 条：{result.title}') + except Exception as exc: + failed += 1 + self.log(f'保存失败：{str(exc).replace(key, "[已隐藏]")[:400]}') + finally: + self.update(saved=saved, skipped=skipped, failed=failed, scanned=scanned) + # 避免越过 start=400；已消费的条目决定下一起始位置。 + offset += len(items) + if offset > 400: + self.log('已到达接口允许的分页范围') + if saved < target and offset <= 400: + self.stop.wait(0.3) + status = 'completed' if saved >= target else 'cancelled' if self.stop.is_set() else 'partial' + message = f'已保存 {saved}/{target} 条，跳过重复 {skipped} 条，失败 {failed} 条' + if status == 'partial': + message += '；当前可获取新闻不足，未达到目标数量' + if status == 'cancelled': + message += '；任务已停止' + self.update(status=status, message=message) + self.log(message) + except Exception as exc: + message = str(exc).replace(key, '[已隐藏]')[:500] + self.update(status='error', message=message) + self.log('任务中断：' + message) + + +def make_handler(manager, token): + class Handler(BaseHTTPRequestHandler): + def log_message(self, *args): + pass + + def send(self, status, payload, mime='application/json; charset=utf-8'): + data = json.dumps(payload, ensure_ascii=False).encode() if isinstance(payload, dict) else payload + self.send_response(status) + self.send_header('Content-Type', mime) + self.send_header('Content-Length', str(len(data))) + self.send_header('Cache-Control', 'no-store') + self.send_header('X-Content-Type-Options', 'nosniff') + self.end_headers() + self.wfile.write(data) + + def local(self): + return self.headers.get('Host') in (f'127.0.0.1:{self.server.server_port}', f'localhost:{self.server.server_port}') + + def do_GET(self): + if not self.local(): + return self.send(403, {'error': '仅允许本机访问'}) + path = urlsplit(self.path).path + if path == '/api/state': + return self.send(200, manager.snapshot()) + if path == '/api/session': + return self.send(200, {'token': token}) + files = {'/': ('index.html', 'text/html; charset=utf-8'), '/app.js': ('app.js', 'text/javascript; charset=utf-8'), '/style.css': ('style.css', 'text/css; charset=utf-8')} + if path not in files: + return self.send(404, {'error': '未找到页面'}) + name, mime = files[path] + self.send(200, (ROOT / 'static' / name).read_bytes(), mime) + + def do_POST(self): + if not self.local() or self.headers.get('X-Session-Token') != token: + return self.send(403, {'error': '页面会话失效，请刷新页面'}) + key = '' + try: + length = int(self.headers.get('Content-Length', 0)) + if not 0 < length <= 16384: + raise ValueError('请求大小无效') + body = json.loads(self.rfile.read(length)) + if not isinstance(body, dict): + raise ValueError('请求必须是 JSON 对象') + if self.path == '/api/stop': + manager.stop.set() + return self.send(200, {'ok': True}) + key = str(body.get('key') or '').strip() + if not key or len(key) > 512: + raise ValueError('请填写有效 API Key') + if self.path == '/api/channels': + channels = result_list(manager.requester(key, 'channel')) + if not channels or not all(isinstance(c, str) and c for c in channels): + raise ValueError('频道列表为空或格式错误') + return self.send(200, {'channels': channels}) + if self.path == '/api/start': + target = body.get('target') + channel = body.get('channel') + if type(target) is not int or not 1 <= target <= 100000: + raise ValueError('下载数量须为 1 至 100000 的整数') + if not isinstance(channel, str) or not channel.strip() or len(channel) > 100: + raise ValueError('请选择新闻频道') + manager.start(key, channel, target) + return self.send(200, {'ok': True}) + if self.path == '/api/debug': + endpoint = body.get('endpoint') + params = {} + if endpoint == 'index': + for field, low, high in [('num', 1, 40), ('start', 0, 400)]: + value = body.get(field) + if type(value) is not int or not low <= value <= high: + raise ValueError(f'{field} 必须在 {low}–{high} 之间') + params[field] = value + params['type'] = str(body.get('channel') or '') + before = time.monotonic() + payload = manager.requester(key, endpoint, params) + # 服务端响应同样隐藏 key，且只作为文本展示，不渲染上游 HTML。 + clean = json.loads(json.dumps(payload, ensure_ascii=False).replace(key, '[已隐藏]')) + return self.send(200, {'elapsed': round(time.monotonic() - before, 2), 'request': API + str(endpoint) + '?' + urlencode({'key': '[已隐藏]', **params}), 'response': clean}) + self.send(404, {'error': '未知操作'}) + except Exception as exc: + message = str(exc) + if key: + message = message.replace(key, '[已隐藏]') + self.send(400, {'error': message[:500]}) + return Handler + + +def main(): + parser = argparse.ArgumentParser(description=__doc__) + parser.add_argument('--port', type=int, default=8765) + parser.add_argument('--no-browser', action='store_true') + args = parser.parse_args() + manager = Downloader() + server = ThreadingHTTPServer(('127.0.0.1', args.port), make_handler(manager, secrets.token_urlsafe(32))) + url = f'http://127.0.0.1:{server.server_port}' + print(f'新闻下载器：{url}\n保存目录：{manager.root}\n按 Ctrl+C 退出', flush=True) + if not args.no_browser: + webbrowser.open(url) + try: + server.serve_forever() + except KeyboardInterrupt: + manager.stop.set() + if manager.thread: + manager.thread.join(timeout=45) + finally: + server.server_close() + + +if __name__ == '__main__': + main() diff --git a/modules/downloader/article_writer.py b/modules/downloader/article_writer.py new file mode 100644 index 0000000..04a6ca0 --- /dev/null +++ b/modules/downloader/article_writer.py @@ -0,0 +1,212 @@ +#!/usr/bin/env python3 +"""将探数新闻正文保存为与微信下载器相同的 Markdown 目录格式。""" + +from __future__ import annotations + +import base64 +from dataclasses import asdict, dataclass +from pathlib import Path +import re +import shutil +import tempfile +from urllib.parse import unquote, urljoin, urlsplit + +import requests +from bs4 import BeautifulSoup +from markdownify import markdownify +from requests.adapters import HTTPAdapter +from urllib3.util.retry import Retry + + +class ArticleDownloadError(RuntimeError): + """页面不是文章、图片下载失败等可向调用方报告的错误。""" + + +@dataclass +class ArticleResult: + title: str + source_url: str + directory: str + markdown: str + images: list[str] + warnings: list[str] + + def to_dict(self) -> dict: + return asdict(self) + + +def safe_name(title: str) -> str: + """跨平台目录/文件名；目录名与其中 Markdown 的文件名保持一致。""" + name = re.sub(r'[<>:"/\\|?*\x00-\x1f\x7f]', '_', title) + name = re.sub(r'\s+', ' ', name).strip(' .') + # 同时限制 UTF-8 字节数，给 .md 和重名后缀保留空间。 + name = name.encode('utf-8')[:180].decode('utf-8', errors='ignore').rstrip(' .') + if not name: + name = '未命名文章' + if re.fullmatch(r'(?i:CON|PRN|AUX|NUL|COM[1-9]|LPT[1-9])(?:\..*)?', name): + name = '_' + name + return name + + +def _session() -> requests.Session: + session = requests.Session() + session.headers.update({ + 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) ' + 'AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36', + 'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8', + }) + retry = Retry(total=3, backoff_factor=0.6, + status_forcelist=[429, 500, 502, 503, 504], allowed_methods=['GET']) + session.mount('https://', HTTPAdapter(max_retries=retry)) + session.mount('http://', HTTPAdapter(max_retries=retry)) + return session + + +def _get(session: requests.Session, url: str, timeout: float, limit: int, + referer: str | None = None) -> tuple[bytes, str, str]: + if urlsplit(url).scheme not in ('http', 'https'): + raise ArticleDownloadError(f'不支持的下载地址：{url[:200]}') + headers = {'Referer': referer} if referer else {} + with session.get(url, timeout=(min(timeout, 15), timeout), + headers=headers, stream=True) as response: + response.raise_for_status() + chunks, size = [], 0 + for chunk in response.iter_content(65536): + size += len(chunk) + if size > limit: + raise ArticleDownloadError(f'文件超过大小限制（{limit // 1024 // 1024} MB）：{url[:200]}') + chunks.append(chunk) + return b''.join(chunks), response.headers.get('Content-Type', ''), response.url + + +def _image_ext(data: bytes, mime: str) -> str: + if data.startswith(b'\xff\xd8\xff'): + return '.jpg' + if data.startswith(b'\x89PNG\r\n\x1a\n'): + return '.png' + if data.startswith((b'GIF87a', b'GIF89a')): + return '.gif' + if data[:4] == b'RIFF' and data[8:12] == b'WEBP': + return '.webp' + if len(data) >= 12 and data[4:8] == b'ftyp' and data[8:12] in (b'avif', b'avis'): + return '.avif' + if b' str: + for attr in ('data-src', 'data-original', 'data-actualsrc', 'data-lazy-src', 'src'): + value = img.get(attr) + if value and str(value).strip(): + return str(value).strip() + srcset = img.get('data-srcset') or img.get('srcset') + if srcset: + return str(srcset).split(',')[-1].strip().split()[0] + return '' + + +def save_article(article: dict, output_root: str | Path = '.', *, timeout: float = 30, + allow_missing_images: bool = False) -> ArticleResult: + """从 API 正文保存文章；图片失败时清理半成品，不覆盖已有同名目录。""" + url = str(article.get('weburl') or article.get('url') or '') + title = str(article.get('title') or '').strip() + raw_content = str(article.get('content') or '').strip() + if not title or not raw_content: + raise ArticleDownloadError('新闻标题或正文为空') + if timeout <= 0: + raise ValueError('timeout 必须大于 0') + with _session() as session: + final_url = url + soup = BeautifulSoup('
' + raw_content + '
', 'html.parser') + content = soup.article + for tag in content.select('script, style, noscript, iframe, form, button'): + tag.decompose() + # 部分微信排版把插图放在行内 CSS 背景中，也转为普通图片参与下载。 + for tag in list(content.find_all(style=True)): + for match in re.finditer(r'url\(\s*[\'\"]?(.*?)[\'\"]?\s*\)', str(tag['style'])): + source = match.group(1).strip() + if source and not source.startswith('#'): + background = soup.new_tag('img', src=source, alt='') + tag.insert(0, background) + if not content.get_text(strip=True) and not content.find('img'): + raise ArticleDownloadError('文章正文为空，可能需要浏览器执行 JavaScript') + for link in content.find_all('a', href=True): + href = str(link['href']).strip() + if href and not href.startswith('#'): + absolute = urljoin(final_url, href) + if urlsplit(absolute).scheme in ('http', 'https', 'mailto', 'tel'): + link['href'] = absolute + else: + del link['href'] + + root = Path(output_root).expanduser().resolve() + root.mkdir(parents=True, exist_ok=True) + stage = Path(tempfile.mkdtemp(prefix='.article-', dir=root)) + images, warnings, downloaded = [], [], {} + try: + for img in list(content.find_all('img')): + source = _image_source(img) + if not source: + img.replace_with(soup.new_string('[图片缺少下载地址]')) + if not allow_missing_images: + raise ArticleDownloadError('正文中存在没有下载地址的图片') + warnings.append('正文中存在没有下载地址的图片') + continue + image_url = urljoin(final_url, source) + try: + if image_url not in downloaded: + if source.startswith('data:image/'): + header, payload = source.split(',', 1) + data = base64.b64decode(payload, validate=True) if ';base64' in header else unquote(payload).encode() + mime = header[5:].split(';')[0] + if len(data) > 50 * 1024 * 1024: + raise ArticleDownloadError('内嵌图片超过 50 MB') + else: + data, mime, _ = _get(session, image_url, timeout, 50 * 1024 * 1024, final_url) + ext = _image_ext(data, mime) + filename = f'image{len(images) + 1:03d}{ext}' + (stage / filename).write_bytes(data) + images.append(filename) + downloaded[image_url] = filename + # 清除懒加载/响应式属性，使转换器只引用本地文件。 + alt = str(img.get('alt') or '') + img.attrs = {'src': downloaded[image_url], 'alt': alt} + except (requests.RequestException, ArticleDownloadError, ValueError) as exc: + if not allow_missing_images: + raise ArticleDownloadError(f'图片下载失败：{image_url[:200]}；{exc}') from exc + warnings.append(f'图片下载失败：{image_url[:200]}；{exc}') + img.replace_with(soup.new_string(f'[图片下载失败：{img.get("alt") or "未命名图片"}]')) + + # 新闻图片后常带空的图注标题，避免生成单独的 ## 和多余空行。 + for heading in content.select('h1, h2, h3, h4, h5, h6'): + if not heading.get_text(strip=True) and not heading.find('img'): + heading.decompose() + body = markdownify(str(content), heading_style='ATX', bullets='-', + strip=['picture', 'source']).strip() + # 微信富文本中各段常没有标准 p 标签；markdownify 仍会保留文字和图片顺序。 + author = str(article.get('src') or '未知作者').strip() or '未知作者' + text = f'# {title}\n\n' + text += body + f'\n\n来源：{author}，如有侵权，请联系删除。\n' + basename = safe_name(title) + # 原子认领新目录，支持多个进程并发保存同名文章。 + index = 1 + while True: + name = basename if index == 1 else f'{basename} ({index})' + destination = root / name + try: + destination.mkdir() + break + except FileExistsError: + index += 1 + try: + (stage / f'{name}.md').write_text(text, encoding='utf-8') + for item in stage.iterdir(): + shutil.move(str(item), destination / item.name) + except BaseException: + shutil.rmtree(destination, ignore_errors=True) + raise + return ArticleResult(title, url, str(destination), str(destination / f'{name}.md'), + [str(destination / x) for x in images], warnings) + finally: + shutil.rmtree(stage, ignore_errors=True) diff --git a/modules/downloader/requirements.txt b/modules/downloader/requirements.txt new file mode 100644 index 0000000..4d42bf4 --- /dev/null +++ b/modules/downloader/requirements.txt @@ -0,0 +1,3 @@ +requests>=2.32,<3 +beautifulsoup4>=4.12,<5 +markdownify>=1.1,<2 diff --git a/modules/downloader/static/app.js b/modules/downloader/static/app.js new file mode 100644 index 0000000..528fcd5 --- /dev/null +++ b/modules/downloader/static/app.js @@ -0,0 +1,79 @@ +'use strict'; +const $ = id => document.getElementById(id); +let token = '', running = false, starting = false, loadingChannels = false, loadedKey = '', lastLog = -1; +const labels = {idle:'等待开始',running:'下载中',completed:'已完成',partial:'未达到目标',cancelled:'已停止',error:'任务中断'}; +const key = () => $('key').value.trim(); +function controls() { + const busy = running || starting; + $('start').disabled = busy || !loadedKey || loadedKey !== key() || !$('channel').value; + $('stop').disabled = !running; + $('channels').disabled = busy || loadingChannels; + for (const id of ['key','channel','target']) $(id).disabled = busy || (id === 'channel' && !loadedKey); +} +async function post(path, body) { + const response = await fetch('/api/' + path, {method:'POST',headers:{'Content-Type':'application/json','X-Session-Token':token},body:JSON.stringify(body)}); + const data = await response.json(); + if (!response.ok) throw new Error(data.error || '请求失败'); + return data; +} +$('key').addEventListener('input', () => {loadedKey=''; $('channel').replaceChildren(new Option('请重新获取频道','')); controls();}); +$('channels').addEventListener('click', async () => { + loadingChannels=true; controls(); $('notice').textContent='正在获取频道…'; + const submittedKey = key(); + try { + const data = await post('channels',{key:submittedKey}); + if (key() !== submittedKey) return; + $('channel').replaceChildren(...data.channels.map(c => new Option(c,c))); + loadedKey=submittedKey; $('notice').textContent=`已获取 ${data.channels.length} 个频道。`; + $('debug-channel').value=$('channel').value; + } catch(error) {$('notice').textContent=error.message;} + finally {loadingChannels=false; controls();} +}); +$('channel').addEventListener('change', () => {$('debug-channel').value=$('channel').value; controls();}); +$('download-form').addEventListener('submit', async event => { + event.preventDefault(); starting=true; controls(); $('notice').textContent=''; + try {await post('start',{key:key(),channel:$('channel').value,target:Number($('target').value)}); await refresh();} + catch(error) {$('notice').textContent=error.message;} + finally {starting=false; controls();} +}); +$('stop').addEventListener('click', async () => { + $('stop').disabled=true; + try {await post('stop',{}); $('notice').textContent='正在停止，等待当前请求或文章保存结束…';} + catch(error) {$('notice').textContent=error.message;} +}); +$('debug-form').addEventListener('submit', async event => { + event.preventDefault(); $('debug-submit').disabled=true; $('debug-output').textContent='正在请求…'; + try { + const data=await post('debug',{key:key(),endpoint:$('endpoint').value,channel:$('debug-channel').value,num:Number($('debug-num').value),start:Number($('debug-start').value)}); + const output=JSON.stringify(data,null,2); + $('debug-output').textContent=output.slice(0,100000)+(output.length>100000?'\n…输出超过 100000 字符，已截断。':''); + } catch(error) {$('debug-output').textContent=error.message;} + finally {$('debug-submit').disabled=false;} +}); +async function refresh() { + const response=await fetch('/api/state'); + if (!response.ok) throw new Error('无法读取下载状态'); + const data=await response.json(); + running=data.status==='running'; controls(); + const percent=data.target ? Math.floor(data.saved/data.target*100) : 0; + $('status').textContent=labels[data.status] || data.status; + $('progress-text').textContent=`下载新闻 ${data.saved}/${data.target} 条`; + $('percent').textContent=`已完成 ${percent}%`; $('progress').value=percent; + for (const id of ['saved','skipped','failed','requests','message','output']) $(id).textContent=data[id]; + const latest=data.logs.length ? data.logs[data.logs.length-1].id : 0; + if (latest!==lastLog) { + const logs=$('logs'); const bottom=logs.scrollHeight-logs.scrollTop-logs.clientHeight<40; + logs.replaceChildren(...data.logs.map(log => {const row=document.createElement('div'); const stamp=document.createElement('time'); stamp.textContent=log.time; row.append(stamp,document.createTextNode(log.message)); return row;})); + if (bottom) logs.scrollTop=logs.scrollHeight; + lastLog=latest; + } +} +async function poll() { + try {await refresh();} + catch(error) {$('notice').textContent='与本地服务连接中断，请检查启动窗口。';} + setTimeout(poll,700); +} +(async () => { + try {const response=await fetch('/api/session'); token=(await response.json()).token; await poll();} + catch(error) {$('notice').textContent='初始化失败，请刷新页面。';} +})(); diff --git a/modules/downloader/static/index.html b/modules/downloader/static/index.html new file mode 100644 index 0000000..68d77fd --- /dev/null +++ b/modules/downloader/static/index.html @@ -0,0 +1,14 @@ + + +探数 · 新闻下载器 +
+
TANSHU / NEWS ARCHIVE

把新闻，保存到本地。

选择频道，收集新闻。正文与图片一起保存，自动跳过已下载的内容。

+

下载设置

本地运行
+

密钥仅用于本次页面会话，不写入文件或浏览器存储。

+
+

接口每次最多 40 条，起始位置最多 400。遇到重复会继续向后查找；可用新闻不足时会说明原因。

+

下载进度

等待开始
下载新闻 0/0 条已完成 0%
已保存 0重复跳过 0保存失败 0接口请求 0

等待开始

保存位置：加载中…

+

运行输出

保留最近 300 条
运行情况将在这里显示。
+
调试终端 手动请求接口

使用上方 API Key。请求会消耗接口调用额度，但不会保存新闻。

尚未发送请求。
+
Markdown 正文 · 本地图片 · 历史去重
+
diff --git a/modules/downloader/static/style.css b/modules/downloader/static/style.css new file mode 100644 index 0000000..803f19b --- /dev/null +++ b/modules/downloader/static/style.css @@ -0,0 +1 @@ +:root{font-family:Inter,-apple-system,BlinkMacSystemFont,"Segoe UI","PingFang SC",sans-serif;color:#20312e;background:#f3f6f3;font-size:15px}*{box-sizing:border-box}body{margin:0}main{max-width:960px;margin:0 auto;padding:48px 24px 24px}header{margin-bottom:32px}.brand{font-size:12px;letter-spacing:2px;font-weight:700;color:#437b69}h1{font-size:36px;letter-spacing:-1px;margin:14px 0}header p{color:#687a74;line-height:1.8}h2{font-size:17px;margin:0}.card{padding:26px 28px;background:#fff;border:1px solid #dfe7e1;border-radius:16px;margin-bottom:20px;box-shadow:0 4px 16px #243c2904}.section-heading{display:flex;align-items:center;justify-content:space-between;gap:10px;margin-bottom:24px}.badge{background:#edf4ef;color:#4c7564;padding:6px 10px;border-radius:20px;font-size:12px}.key-row{display:flex;gap:12px}.key-row input{flex:1;min-width:0}label{display:block;font-weight:600;margin-bottom:9px;font-size:13px}input,select,button{font:inherit;border-radius:8px}input,select{background:#fbfcfb;border:1px solid #d7e0d9;width:100%;padding:12px;color:inherit}input:focus,select:focus,button:focus-visible,summary:focus-visible{outline:3px solid #8dcab5;outline-offset:2px}button{cursor:pointer;border:1px solid #286850;background:#286850;color:#fff;padding:12px 22px;font-weight:600;white-space:nowrap}.secondary{background:#fff;color:#345e4f;border-color:#cedbd3}button:disabled{opacity:.45;cursor:not-allowed}.fields{display:grid;grid-template-columns:1fr 1fr;gap:20px;margin:24px 0 16px}.hint{font-size:12px;color:#79867f;line-height:1.8;margin:10px 0}.actions{display:flex;gap:12px;margin-top:22px}#notice{color:#ac4c32;font-size:13px;white-space:pre-wrap}#notice:empty{display:none}.progress-heading{display:flex;justify-content:space-between;gap:16px;font-size:14px}#percent{color:#3f7b60}progress{display:block;width:100%;height:12px;border:0;border-radius:10px;overflow:hidden;margin:18px 0 20px;background:#edf2ef}progress::-webkit-progress-bar{background:#edf2ef}progress::-webkit-progress-value{background:#3c8b68;transition:width .25s}progress::-moz-progress-bar{background:#3c8b68}.stats{display:flex;gap:28px;flex-wrap:wrap;color:#7a8880;font-size:13px}.stats b{color:#304e40;margin-left:8px;font-size:17px}#message{font-size:13px;color:#52685b;line-height:1.8}.path{overflow-wrap:anywhere}.console{height:260px;overflow:auto;background:#15251f;color:#c5dacf;border-radius:10px;padding:18px;font:12px/1.9 ui-monospace,SFMono-Regular,Consolas,monospace;white-space:pre-wrap;overflow-wrap:anywhere}.console time{color:#7eac94;margin-right:14px}.empty{color:#7e9889}summary{cursor:pointer;font-weight:600}summary span{font-size:12px;font-weight:400;color:#79867f;margin-left:12px}#debug-output{margin-bottom:0;height:300px}footer{text-align:center;color:#89958e;font-size:12px;margin:32px 0}@media(max-width:600px){main{padding:26px 14px}h1{font-size:28px}.card{padding:22px 18px}.key-row{flex-direction:column}.fields{grid-template-columns:1fr}.stats{gap:14px}.progress-heading{font-size:12px}} diff --git a/modules/package.py b/modules/package.py new file mode 100644 index 0000000..13afdc2 --- /dev/null +++ b/modules/package.py @@ -0,0 +1,63 @@ +#!/usr/bin/env python3 +"""Build a portable v1 article package for the DWW11 userscript (standard library only).""" +from __future__ import annotations + +import argparse +import base64 +import json +import mimetypes +from pathlib import Path + + +def make_package(directory: str | Path, markdown: str | None = None) -> dict: + """Return JSON-serializable data; no network access or publishing side effects.""" + root = Path(directory).expanduser().resolve(strict=True) + if not root.is_dir(): + raise ValueError("文章目录不存在") + choices = sorted(path for path in root.rglob("*") if path.is_file() and path.suffix.lower() == ".md") + if markdown: + selected = (root / markdown).resolve(strict=True) + elif len(choices) == 1: + selected = choices[0].resolve() + else: + raise ValueError("目录必须包含一个 Markdown 文件，或通过 --markdown 指定目录内相对路径") + if not selected.is_relative_to(root) or selected.suffix.lower() != ".md" or not selected.is_file(): + raise ValueError("Markdown 必须位于所选文章目录内") + images = [] + # Package local supported images. The importer uploads only those referenced by Markdown. + for path in sorted(root.rglob("*")): + if not path.is_file() or path.suffix.lower() not in {".jpg", ".jpeg", ".png", ".gif"}: + continue + if not path.resolve().is_relative_to(root): + raise ValueError(f"图片符号链接指向目录外：{path.name}") + if not 0 < path.stat().st_size < 20 * 1024 * 1024: + raise ValueError(f"图片为空或达到 20 MB：{path.name}") + images.append({"path": path.relative_to(root).as_posix(), + "mime": mimetypes.guess_type(path.name)[0] or "application/octet-stream", + "base64": base64.b64encode(path.read_bytes()).decode("ascii")}) + return {"schemaVersion": 1, "markdownPath": selected.relative_to(root).as_posix(), + "markdown": selected.read_text(encoding="utf-8-sig"), "images": images} + + +def main() -> None: + parser = argparse.ArgumentParser(description="把文章目录打包为油猴脚本可导入的 JSON；不上传或发布") + parser.add_argument("directory", help="包含 Markdown 和图片的目录") + parser.add_argument("--markdown", help="多个 Markdown 时指定目录内的相对路径") + parser.add_argument("-o", "--output", help="输出文件路径；未指定时输出到标准输出") + args = parser.parse_args() + try: + content = json.dumps(make_package(args.directory, args.markdown), ensure_ascii=False, indent=2) + if args.output: + output = Path(args.output).expanduser() + # Never silently overwrite an article or an existing package. + with output.open("x", encoding="utf-8") as handle: + handle.write(content + "\n") + print(json.dumps({"ok": True, "package": str(output.resolve())}, ensure_ascii=False)) + else: + print(content) + except (OSError, ValueError) as error: + parser.exit(1, f"打包失败：{error}\n") + + +if __name__ == "__main__": + main() diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..4d42bf4 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,3 @@ +requests>=2.32,<3 +beautifulsoup4>=4.12,<5 +markdownify>=1.1,<2 diff --git a/start.command b/start.command new file mode 100755 index 0000000..a647886 --- /dev/null +++ b/start.command @@ -0,0 +1,8 @@ +#!/bin/zsh +cd "${0:A:h}" +if ! command -v uv >/dev/null 2>&1; then + print '未找到 uv，请安装 uv 后重试。' + read '?按回车关闭…' + exit 1 +fi +uv run --no-project --python 3.12 --with-requirements requirements.txt python app.py diff --git a/static/app.js b/static/app.js new file mode 100644 index 0000000..9a05752 --- /dev/null +++ b/static/app.js @@ -0,0 +1,51 @@ +'use strict'; +const $=id=>document.getElementById(id); +let token='',state=null,loadedKey='',refreshing=false; +const labels={queued:'待处理',preparing:'准备中',importing:'上传与导入',formatting:'排版中',awaiting_user_review:'等待人工审核',user_submitting:'已观察到人工提交',submit_unknown:'发布结果待核对',accepted_pending_moderation:'已受理 · 审核中',published:'已确认公开',needs_attention:'需要处理',cancelled:'已移出'}; +function notice(message){$('notice').hidden=!message;$('notice').textContent=message;} +async function api(route,body={}) { + const response=await fetch('/api/'+route,{method:'POST',headers:{'Content-Type':'application/json','X-Session-Token':token},body:JSON.stringify(body)}); + const data=await response.json();if(!response.ok)throw new Error(data.error||'请求失败');return data; +} +function action(id,fn){$(id).addEventListener('click',async()=>{const button=$(id);button.disabled=true;try{await fn();await refresh();}catch(error){notice(error.message);}finally{button.disabled=false;}});} +function text(tag,value,className){const e=document.createElement(tag);e.textContent=value;if(className)e.className=className;return e;} +function render(data){ + state=data;const {jobs,run,download}=data; + $('total').textContent=jobs.length;$('review').textContent=jobs.filter(j=>j.state==='awaiting_user_review').length; + $('accepted').textContent=jobs.filter(j=>['published','accepted_pending_moderation'].includes(j.state)).length; + $('batch').textContent=run.batch?`${run.batch.count} / ${run.batch.target}`:'—';$('account').textContent=run.batch?run.batch.account.name:'尚未绑定账号'; + $('run-state').textContent=run.running?'流程运行中':'流程已暂停';$('run-reason').textContent=run.reason; + $('run-light').classList.toggle('gray',!run.running);$('empty').hidden=jobs.length>0; + $('jobs').replaceChildren(...jobs.map(job=>{ + const tr=document.createElement('tr'),title=document.createElement('td');title.append(text('div',job.title),text('small',`${job.image_count} 张配图 · ${job.source}`));if(job.original_title!==job.title)title.append(text('small','已缩短标题，原题：'+job.original_title)); + const status=document.createElement('td');status.append(text('span',labels[job.state]||job.state,'badge'));if(job.error)status.append(text('small',job.error)); + const account=text('td',job.account?`${job.account.name} / ${job.fid}`:'待领取');const result=document.createElement('td'); + if(job.post_url){const link=text('a','查看帖子');link.href=job.post_url;link.target='_blank';link.rel='noopener';result.append(link);} + if(!['published','accepted_pending_moderation'].includes(job.state)){ + const retry=text('button','人工核对 / 处理');retry.className='secondary';retry.onclick=async()=>{ + if(state.run.running){notice('请先暂停流程，再处理任务');return;} + if(!confirm('只有确认网站未受理这篇文章，且已清理编辑器/草稿后才能继续。\n已受理、审核中或结果不明的文章请取消。\n你是否已经确认未受理？'))return; + const again=confirm('重新加入队列？\n确定：重新排队。取消：移出队列。'); + try{await api('resolve',{id:job.id,confirmed_not_accepted:true,retry:again});await refresh();}catch(error){notice(error.message);} + };result.append(retry); + } + tr.append(title,status,account,result);return tr; + })); + const dlLabels={idle:'等待开始',running:'下载中',completed:'下载完成',partial:'未达到目标',cancelled:'已停止',error:'下载出错'}; + $('download-state').textContent=dlLabels[download.status]||download.status;$('download-progress').textContent=`已保存 ${download.saved}/${download.target} 篇 · 跳过 ${download.skipped} · 失败 ${download.failed}`; + $('progress').value=download.target?Math.floor(download.saved/download.target*100):0; + $('download').disabled=download.status==='running';$('logs').textContent=download.logs.map(x=>`${x.time} ${x.message}`).join('\n')||'暂无日志'; + $('browser-state').textContent=data.clients.length?`${data.clients.length} 个标签在线`:'尚未连接'; + $('clients').textContent=data.clients.map(c=>`${c.account?.name||'未识别账号'} · 换号插件${c.extension?.ready?'已就绪':'未连接或需更新'}`).join('\n')||'没有在线执行标签'; +} +async function refresh(){if(refreshing||!token)return;refreshing=true;try{render(await api('state'));}catch(error){notice(error.message);$('run-state').textContent='本地服务连接中断';}finally{refreshing=false;}} +action('pair',async()=>{const value=await api('pair');$('pair-code').hidden=false;$('pair-code').type='text';$('pair-code').value=value.token;$('pair-code').select();}); +action('channels',async()=>{const value=await api('channels',{key:$('key').value.trim()});loadedKey=$('key').value.trim();$('channel').replaceChildren(...value.channels.map(c=>new Option(c,c)));}); +$('key').oninput=()=>{loadedKey='';$('channel').replaceChildren(new Option('请重新获取频道',''));}; +$('download-form').onsubmit=async event=>{event.preventDefault();try{if(!loadedKey||loadedKey!==$('key').value.trim())throw new Error('请先获取频道');await api('download',{key:loadedKey,channel:$('channel').value,target:Number($('target').value)});notice('下载已开始，完整保存的文章会自动入队');await refresh();}catch(error){notice(error.message);}}; +action('download-stop',()=>api('download-stop')); +action('scan',async()=>{notice('正在检查文章目录…');const value=await api('scan',{root:$('root').value.trim()});$('scan-result').textContent=value.results.map(x=>`${x.directory}：${x.status}`).join('\n')||'目录中未找到文章';notice('目录检查完成');}); +$('config-form').onsubmit=async event=>{event.preventDefault();try{await api('configure',{fid:Number($('fid').value),minimum:Number($('minimum').value),maximum:Number($('maximum').value),interval:Number($('interval').value),history_checked:$('history-checked').checked});notice('处理规则已保存');await refresh();}catch(error){notice(error.message);}}; +for(const name of ['start','pause','stop'])action(name,async()=>{await api(name);notice(name==='stop'?'流程已终止；浏览器将在下一次连接检查时停止后续操作。已发出的请求可能仍已完成。':'');}); +$('history-file').onchange=async()=>{try{const file=$('history-file').files[0];if(!file)return;if(file.size>2*1024*1024)throw new Error('记录文件过大');const value=JSON.parse(await file.text());await api('history',{records:value.records});notice('历史记录已导入；仅使用标记为 block_repost 的记录');await refresh();}catch(error){notice(error.message);}}; +(async()=>{try{const response=await fetch('/api/session');const session=await response.json();if(!response.ok)throw new Error(session.error);token=session.token;$('port').value=location.port;await refresh();if(state?.run.config?.fid){for(const id of ['fid','minimum','maximum','interval'])$(id).value=state.run.config[id];$('history-checked').checked=state.run.config.history_checked;}}catch(error){notice(error.message);}setInterval(refresh,2500);})(); diff --git a/static/index.html b/static/index.html new file mode 100644 index 0000000..ce25dae --- /dev/null +++ b/static/index.html @@ -0,0 +1,26 @@ + + +新闻工作台 + + +
+
CONTENT WORKSPACE

把内容准备好，把审核留给你。

下载、导入、排版与账号切换，在一个工作台管理。

+ +
01下载新闻
→
02导入与排版
→
03人工审核与发表
→
04结果核对与换号
+
当前接入进度 下载、导入、排版与换号接口已整合；结果页自动核对等待页面 HTML。人工发表后会暂停，不自动计数或继续下一篇。
+
队列文章0完整文件检查后入队
等待你审核0请在网站检查并亲手发表
明确受理0审核中与已公开分别记录
当前账号批次—尚未绑定账号
+
+
SOURCE

下载与文章

等待开始
+
+
等待下载
+
导入已有文章目录

填写包含文章子文件夹的完整路径。留空时扫描本工具的 downloads 目录。请在文件完整保存后扫描。


+

+
WORKFLOW
处理规则
人工发表

+
每个账号只抽取一次目标篇数；只有明确受理的文章才计数。历史演示去重记录会自动读取。

+

+
正在连接本地服务…
等待状态

+
ARTICLE QUEUE
文章队列
文章状态账号 / 版块结果与操作
＋从第一篇文章开始
下载新闻，或检查已有文章目录。准备好的文章会出现在这里。

+
CONNECTION
连接你的浏览器
尚未连接
  1. 在油猴中安装以下两个脚本，并停用原导入、排版脚本。
  2. 重新加载原目录中的换号插件，然后刷新网站。
  3. 在网站左下角展开连接设置，填入本地端口和连接码。
安装本地连接脚本安装导入排版脚本
服务重启后需要更新连接码。仅复制到你安装的本地连接脚本。
没有在线执行标签

+
下载日志
暂无日志
新闻工作台 · 本机运行 · v0.1   /   终止后不会自动恢复，已发出的请求可能仍已完成。

+

+
diff --git a/static/style.css b/static/style.css
new file mode 100644
index 0000000..7d1e2e2
--- /dev/null
+++ b/static/style.css
@@ -0,0 +1 @@
+:root{font-family:Inter,-apple-system,BlinkMacSystemFont,"PingFang SC","Microsoft YaHei",sans-serif;color:#203b38;background:#f3f6f4;font-synthesis:none;font-size:14px}*{box-sizing:border-box}body{margin:0}aside{position:fixed;inset:0 auto 0 0;width:220px;background:#113e37;color:#f4fbf7;padding:32px 22px;display:flex;flex-direction:column}.brand{display:flex;align-items:center;gap:12px;font-size:20px;font-weight:650;letter-spacing:.5px}.mark{display:grid;place-items:center;background:#d8efb9;color:#17483e;width:42px;height:42px;border-radius:13px}.brand small{display:block;font-size:11px;font-weight:400;color:#b3cdc5;margin-top:5px}nav{display:grid;gap:9px;margin-top:54px}nav a{color:#bad1c9;text-decoration:none;padding:12px 16px;border-radius:8px}nav a:hover,nav .selected{background:#28534a;color:#fff}.aside-note{margin-top:auto;color:#bad1c9;font-size:12px;line-height:1.9}.dot{display:inline-block;width:8px;height:8px;border-radius:50%;background:#a3db80;margin-right:7px}.dot.gray{background:#a1ada7}main{max-width:1660px;margin-left:220px;padding:42px 40px}header{display:flex;align-items:center;justify-content:space-between;gap:20px}.eyebrow{font-size:10px;letter-spacing:2px;color:#6b8980;font-weight:700}h1{font-size:28px;letter-spacing:-.6px;margin:12px 0}header p{color:#73857e;margin:0;font-size:13px}button,.button,.file-button{font:inherit;font-weight:550;border:1px solid #1c6554;border-radius:7px;background:#1c6554;color:white;padding:10px 15px;cursor:pointer;white-space:nowrap;text-decoration:none;display:inline-block}button:hover,.button:hover{filter:brightness(.94)}button:disabled{opacity:.45;cursor:wait}.secondary,.file-button{background:white;color:#36574d;border-color:#d4dfd7}.danger{background:#fff8f6;border-color:#e7c5bb;color:#a34d37}.flow{display:flex;align-items:center;justify-content:space-between;gap:12px;margin-top:34px;background:white;border:1px solid #e2e9e2;padding:22px 25px;border-radius:12px;font-size:12px}.flow span{background:#edf3ef;color:#5f7d70;padding:5px 7px;border-radius:5px;font-size:10px;margin-right:8px}.flow i{color:#b1c0b6;font-style:normal}.flow .highlight{font-weight:650;color:#2e6947}.flow .highlight span{background:#e3efcc;color:#476635}.pending-note{background:#f8f2df;border:1px solid #eae0bd;color:#7b6938;padding:12px 16px;border-radius:8px;margin:16px 0;font-size:12px;line-height:1.8}.pending-note b{margin-right:10px}.metrics{display:grid;grid-template-columns:repeat(4,1fr);gap:16px;margin:22px 0}.metrics article{padding:20px 23px;background:white;border:1px solid #e0e8e0;border-radius:10px}.metrics small{font-size:12px;color:#6b7f73}.metrics strong{display:block;font-size:30px;font-weight:550;margin:12px 0 8px}.metrics span{font-size:11px;color:#8a988f}.workspace-grid{display:grid;grid-template-columns:1.1fr 1fr;gap:20px}.card{background:white;border:1px solid #e0e8e0;border-radius:12px;padding:24px;margin-bottom:20px;min-width:0}.section-head{display:flex;align-items:center;justify-content:space-between;gap:12px;margin-bottom:20px}h2{font-size:17px;margin:6px 0 0;font-weight:600}.badge{font-size:11px;border-radius:20px;background:#f0f5ef;color:#6c826d;padding:5px 10px}.row{display:flex;gap:12px;align-items:flex-end}.grow{flex:1;min-width:0}label{display:block;font-size:12px;color:#61756b;margin-bottom:14px}input,select{display:block;width:100%;font:inherit;color:#304a3f;padding:10px 12px;margin-top:7px;border:1px solid #dbe4dd;border-radius:6px;background:#fcfdfb;outline:none}input:focus,select:focus{border-color:#659981;box-shadow:0 0 0 3px #6599811a}input::placeholder{color:#a4afa8}.row button{margin-bottom:14px}.check{display:flex;align-items:flex-start;gap:8px;line-height:1.7}.check input{width:15px;height:15px;margin:2px 0 0;accent-color:#276b54}.muted{font-size:12px;line-height:1.8;color:#8b988e}.progress{margin:12px 0 20px}progress{appearance:none;width:100%;height:5px;border:0;border-radius:4px;display:block;background:#edf2ec}progress::-webkit-progress-bar{background:#edf2ec}progress::-webkit-progress-value{background:#76a77f;border-radius:4px}.progress small{display:block;color:#82917f;margin-top:8px;font-size:11px}summary{cursor:pointer;color:#617d6d;font-size:12px}details label{margin-top:12px}.runbar{display:flex;align-items:center;justify-content:space-between;border-radius:10px;background:#e5eee5;padding:19px 23px;margin-bottom:22px;gap:16px}.runbar b{font-weight:550}.runbar p{margin:7px 0 0 15px;font-size:12px;color:#758b76}.actions{display:flex;gap:10px;flex-wrap:wrap}table{border-collapse:collapse;width:100%;text-align:left;font-size:12px}th{color:#8a998f;font-weight:500;background:#f7f9f5;padding:12px}td{padding:16px 12px;border-bottom:1px solid #eef1eb;vertical-align:top;line-height:1.8}td:first-child{max-width:350px}td small{display:block;color:#91a093;font-size:11px}td button{font-size:11px;padding:4px 8px}td a{color:#1c6554}.table-wrap{overflow-x:auto}.empty{padding:44px 16px;text-align:center;color:#81927f}.empty span{display:block;font-size:30px;margin-bottom:14px;color:#a5b69e}.empty b{font-size:14px;font-weight:500}.empty p{font-size:12px;color:#a0ad9c}.connection-grid{display:grid;grid-template-columns:1.5fr 1fr;gap:36px}.connection-grid ol{padding-left:18px;font-size:12px;color:#738673;line-height:2.3;margin:0 0 16px}.connection-grid small{display:block;margin-top:8px}pre{white-space:pre-wrap;overflow-wrap:anywhere;max-height:220px;overflow:auto;font:12px/1.8 ui-monospace,monospace;color:#73816f}.notice{padding:14px 18px;border:1px solid #dcccb0;background:#fff9e9;color:#876c40;border-radius:8px;margin-top:20px;line-height:1.7}footer{font-size:11px;color:#9ba697;text-align:center;margin-top:30px}a:focus-visible,button:focus-visible,summary:focus-visible{outline:3px solid #91ba80;outline-offset:3px}[hidden]{display:none!important}@media(max-width:1150px){aside{width:180px;padding:28px 15px}main{margin-left:180px;padding:30px 24px}.brand{font-size:17px}.flow{padding:18px 15px;flex-wrap:wrap}.metrics{gap:10px}.metrics article{padding:18px 15px}.row{flex-wrap:wrap}.row .grow{min-width:100px}h1{font-size:24px}}@media(max-width:800px){aside{position:relative;width:100%;padding:16px 22px}.brand small,.aside-note,nav{display:none}main{margin-left:0;padding:24px 16px}.workspace-grid,.connection-grid{grid-template-columns:1fr}.metrics{grid-template-columns:repeat(2,1fr)}header{align-items:flex-start}h1{font-size:22px}.flow{line-height:2.5}.flow i{display:none}.runbar{flex-wrap:wrap}.card{padding:20px}header .danger{font-size:12px;padding:9px}.connection-grid{gap:20px}}
diff --git a/store.py b/store.py
new file mode 100644
index 0000000..e4117c5
--- /dev/null
+++ b/store.py
@@ -0,0 +1,294 @@
+"""Persistent serial queue. Browser submissions are always initiated by the user."""
+import json
+from contextlib import contextmanager
+from pathlib import Path
+import secrets
+import sqlite3
+import threading
+import time
+from urllib.parse import urlsplit
+
+from articles import inspect_article
+
+ACCEPTED = {'published', 'accepted_pending_moderation'}
+SUBMITTED = {'user_submitting', 'submit_unknown'}
+
+
+class Store:
+    def __init__(self, path, ledger=None):
+        self.path = str(path)
+        Path(path).parent.mkdir(parents=True, exist_ok=True)
+        self.lock = threading.RLock()
+        with self.db() as db:
+            db.executescript('''
+                CREATE TABLE IF NOT EXISTS jobs(id TEXT PRIMARY KEY, article_key TEXT UNIQUE, value TEXT NOT NULL);
+                CREATE TABLE IF NOT EXISTS ledger(key TEXT PRIMARY KEY, value TEXT NOT NULL);
+                CREATE TABLE IF NOT EXISTS settings(id INTEGER PRIMARY KEY CHECK(id=1), value TEXT NOT NULL);
+                CREATE TABLE IF NOT EXISTS posts(id TEXT PRIMARY KEY, job TEXT NOT NULL);
+            ''')
+            row = db.execute('SELECT value FROM settings WHERE id=1').fetchone()
+            self.run = json.loads(row[0]) if row else dict(running=False, epoch=0, config={}, batch=None, active=None, owner=None, switch=None, reason='请配置任务后开始')
+            self.run.update(running=False, epoch=self.run['epoch'] + 1, reason='服务已启动，请明确点击开始/继续；未决任务不会重发')
+            self._persist(db)
+        self.clients = {}
+        if ledger and Path(ledger).is_file():
+            self.import_history(json.loads(Path(ledger).read_text()).get('records', []))
+
+    @contextmanager
+    def db(self):
+        connection = sqlite3.connect(self.path, timeout=20)
+        try:
+            with connection:
+                yield connection
+        finally:
+            connection.close()
+
+    def _persist(self, db):
+        db.execute('INSERT OR REPLACE INTO settings VALUES(1,?)', (json.dumps(self.run, ensure_ascii=False),))
+
+    def _job(self, db, id):
+        row = db.execute('SELECT value FROM jobs WHERE id=?', (id,)).fetchone()
+        if not row:
+            raise ValueError('任务不存在')
+        return json.loads(row[0])
+
+    def _save(self, db, job):
+        job['updated_at'] = time.time()
+        db.execute('INSERT OR REPLACE INTO jobs VALUES(?,?,?)', (job['id'], job['article_key'], json.dumps(job, ensure_ascii=False)))
+
+    def import_history(self, records):
+        with self.lock, self.db() as db:
+            for record in records:
+                digest = record.get('markdown_sha256')
+                if digest and record.get('block_repost'):
+                    db.execute('INSERT OR IGNORE INTO ledger VALUES(?,?)', ('md:' + digest, json.dumps(record, ensure_ascii=False)))
+                    # Add content identity where the original historical file is still present.
+                    try:
+                        article = inspect_article(Path(record['markdown_path']).parent)
+                        db.execute('INSERT OR IGNORE INTO ledger VALUES(?,?)', ('article:' + article['article_key'], json.dumps(record, ensure_ascii=False)))
+                    except (OSError, ValueError, KeyError):
+                        pass
+
+    def enqueue(self, directory):
+        article = inspect_article(directory)
+        article.pop('package')
+        keys = ['article:' + article['article_key'], 'md:' + article['markdown_sha256']] + ['source:' + str(k) for k in article['source_keys']]
+        with self.lock, self.db() as db:
+            if any(db.execute('SELECT 1 FROM ledger WHERE key=?', (k,)).fetchone() for k in keys):
+                return '已受理，跳过'
+            if db.execute('SELECT 1 FROM jobs WHERE article_key=?', (article['article_key'],)).fetchone():
+                return '已在队列，跳过'
+            # Source URL identities prevent different renderings of one downloaded article re-entering.
+            for row in db.execute('SELECT value FROM jobs'):
+                if set(article['source_keys']) & set(json.loads(row[0]).get('source_keys', [])):
+                    return '相同来源已在队列，跳过'
+            article.update(id=secrets.token_hex(12), state='queued', created_at=time.time(), error='', post_url='')
+            self._save(db, article)
+            return '已入队'
+
+    def state(self):
+        with self.lock, self.db() as db:
+            jobs = [json.loads(r[0]) for r in db.execute('SELECT value FROM jobs ORDER BY rowid')]
+            return dict(run=json.loads(json.dumps(self.run)), jobs=jobs,
+                        clients=[v for v in self.clients.values() if time.time() - v['seen'] < 20],
+                        history_count=db.execute('SELECT count(*) FROM ledger').fetchone()[0])
+
+    def configure(self, config):
+        fid, minimum, maximum = config.get('fid'), config.get('minimum'), config.get('maximum')
+        interval = config.get('interval')
+        if any(type(x) is not int for x in (fid, minimum, maximum, interval)) or not (fid > 0 and 1 <= minimum <= maximum <= 1000 and 0 <= interval <= 86400):
+            raise ValueError('请填写有效版块 ID、篇数范围（1～1000）和间隔秒数')
+        if config.get('history_checked') is not True:
+            raise ValueError('请先核对待处理文章与历史发布记录，并勾选确认')
+        with self.lock, self.db() as db:
+            if self.run['active'] or self.run['switch'] or self.run['running']:
+                raise ValueError('当前流程未结束，不能更换配置')
+            self.run.update(config={k: config[k] for k in ('fid', 'minimum', 'maximum', 'interval', 'history_checked')}, batch=None)
+            self._persist(db)
+
+    def control(self, action):
+        with self.lock, self.db() as db:
+            if action == 'start':
+                if not self.run['config']:
+                    raise ValueError('请先保存配置')
+                self.run.update(running=True, reason='等待浏览器连接')
+            else:
+                self.run.update(running=False, reason='已终止' if action == 'stop' else '已暂停')
+            self.run['epoch'] += 1
+            self._persist(db)
+            return dict(self.run)
+
+    def _batch(self, account):
+        cfg = self.run['config']
+        return dict(account=account, target=cfg['minimum'] + secrets.randbelow(cfg['maximum'] - cfg['minimum'] + 1), count=0)
+
+    def _check_owner(self, owner):
+        if self.run['owner'] != owner:
+            raise ValueError('任务由另一个浏览器标签持有')
+
+    def heartbeat(self, data):
+        owner = str(data.get('owner', ''))[:100]
+        if not owner:
+            raise ValueError('缺少执行标签标识')
+        with self.lock:
+            self.clients[owner] = dict(owner=owner, account=data.get('account'), url=str(data.get('url', ''))[:1000],
+                                       extension=data.get('extension'), seen=time.time())
+            return self.state()['run']
+
+    def next(self, data):
+        owner, account = data.get('owner'), data.get('account')
+        with self.lock, self.db() as db:
+            if not self.run['running']:
+                return dict(action='idle', run=self.run)
+            if not account or not str(account.get('uid', '')).isdigit() or not account.get('name'):
+                return dict(action='login', run=self.run)
+            if self.run['owner'] not in (None, owner):
+                return dict(action='other_tab', run=self.run)
+            self.run['owner'] = owner
+            if self.run['switch']:
+                switch = self.run['switch']
+                if account['uid'] != switch['from'] and data.get('extension', {}).get('idle') is True:
+                    self.run.update(batch=self._batch(account), switch=None)
+                    self._persist(db)
+                else:
+                    return dict(action='switch' if switch['state'] == 'pending' else 'switch_wait', run=self.run)
+            if self.run['batch'] is None:
+                self.run['batch'] = self._batch(account)
+            if self.run['batch']['account']['uid'] != account['uid']:
+                self.run.update(running=False, reason='检测到账号变化，请先核对当前任务')
+                self._persist(db)
+                return dict(action='idle', run=self.run)
+            if self.run['active']:
+                job = self._job(db, self.run['active'])
+                return dict(action='resume', job=job, run=self.run)
+            rows = [json.loads(r[0]) for r in db.execute('SELECT value FROM jobs ORDER BY rowid')]
+            job = next((j for j in rows if j['state'] == 'queued'), None)
+            if not job:
+                self.run.update(running=False, reason='当前队列已处理完；新文章入队后请点击继续')
+                self._persist(db)
+                return dict(action='idle', run=self.run)
+            if time.time() < self.run.get('not_before', 0):
+                return dict(action='interval', run=self.run)
+            if self.run['batch']['count'] >= self.run['batch']['target']:
+                self.run['switch'] = dict(state='pending', **{'from': account['uid']}, created_at=time.time())
+                self._persist(db)
+                return dict(action='switch', run=self.run)
+            job.update(state='preparing', account=account, fid=self.run['config']['fid'], error='')
+            self.run['active'] = job['id']
+            self._save(db, job)
+            self._persist(db)
+            return dict(action='prepare', job=job, run=self.run)
+
+    def current(self, data):
+        with self.lock, self.db() as db:
+            self._check_owner(data['owner'])
+            return {'job': self._job(db, self.run['active']) if self.run['active'] else None, 'run': self.run}
+
+    def switch_begin(self, data):
+        with self.lock, self.db() as db:
+            self._check_owner(data['owner'])
+            if not self.run['running'] or not self.run['switch'] or self.run['switch']['state'] != 'pending':
+                raise ValueError('换号状态已改变，禁止重复点击')
+            self.run['switch']['state'] = 'clicked'
+            self._persist(db)
+            return {'ok': True}
+
+    def package(self, data):
+        with self.lock, self.db() as db:
+            self._check_owner(data['owner'])
+            if not self.run['running'] or self.run['active'] != data['id']:
+                raise ValueError('流程已停止或任务不匹配')
+            job = self._job(db, data['id'])
+            if job['state'] != 'preparing':
+                raise ValueError('当前任务不允许重新导入，请先核对已上传内容')
+        article = inspect_article(job['directory'])
+        if article['markdown_sha256'] != job['markdown_sha256'] or article['article_key'] != job['article_key']:
+            raise ValueError('入队后原文章已改变，请移出并重新扫描')
+        return article['package']
+
+    def event(self, data):
+        with self.lock, self.db() as db:
+            self._check_owner(data['owner'])
+            job = self._job(db, data['id'])
+            if self.run['active'] != job['id']:
+                raise ValueError('不是当前任务')
+            target = data['state']
+            transitions = {'preparing': {'importing', 'needs_attention'}, 'importing': {'formatting', 'needs_attention'},
+                           'formatting': {'awaiting_user_review', 'needs_attention'},
+                           'awaiting_user_review': {'user_submitting', 'needs_attention'},
+                           'user_submitting': {'submit_unknown', 'needs_attention'}, 'submit_unknown': {'needs_attention'}}
+            if target not in transitions.get(job['state'], set()):
+                raise ValueError('任务状态不允许此操作：' + job['state'] + ' → ' + target)
+            if target in ('importing', 'formatting', 'awaiting_user_review') and (not self.run['running'] or data.get('epoch') != self.run['epoch']):
+                raise ValueError('流程已暂停/终止，过期回调不能继续')
+            job.update(state=target, error=str(data.get('error', ''))[:1000])
+            if target == 'user_submitting':
+                job.update(submitted_at=time.time(), snapshot=data.get('snapshot', {}), attempt=secrets.token_hex(8))
+            if target == 'awaiting_user_review':
+                job['prepared'] = data.get('snapshot', {})
+            if target == 'needs_attention':
+                self.run.update(running=False, reason=job['error'] or '当前任务需要处理')
+                self._persist(db)
+            self._save(db, job)
+            return {'ok': True}
+
+    def accept(self, data):
+        with self.lock, self.db() as db:
+            self._check_owner(data['owner'])
+            job = self._job(db, data['id'])
+            if job['state'] in ACCEPTED:
+                return {'ok': True, 'duplicate': True}
+            if self.run['active'] != job['id'] or job['state'] not in SUBMITTED:
+                raise ValueError('只有已观察到人工提交的任务才能登记结果')
+            url = urlsplit(str(data.get('post_url', '')))
+            import re
+            match = re.fullmatch(r'/thread/(\d+)\.html', url.path)
+            if url.scheme != 'https' or url.netloc not in ('www.dww11.com', 'dww11.com') or not match:
+                raise ValueError('未识别到帖子详情页')
+            if data.get('author_uid') != job['account']['uid'] or data.get('fid') != job['fid']:
+                raise ValueError('结果页作者或版块与任务不符，请人工核对')
+            if data.get('title') != job.get('snapshot', {}).get('title'):
+                raise ValueError('结果页标题与人工提交快照不一致')
+            if data.get('state') not in ACCEPTED:
+                raise ValueError('需要明确的公开或审核中状态')
+            if not data.get('evidence'):
+                raise ValueError('缺少页面结果证据')
+            post_id = match[1]
+            existing = db.execute('SELECT job FROM posts WHERE id=?', (post_id,)).fetchone()
+            if existing and existing[0] != job['id']:
+                raise ValueError('帖子已绑定其他任务，不能重复计数')
+            db.execute('INSERT OR IGNORE INTO posts VALUES(?,?)', (post_id, job['id']))
+            job.update(state=data['state'], post_id=post_id, post_url=url.geturl(), result=data['evidence'])
+            keys = ['article:' + job['article_key'], 'md:' + job['markdown_sha256']] + ['source:' + str(k) for k in job['source_keys']]
+            for key in keys:
+                db.execute('INSERT OR REPLACE INTO ledger VALUES(?,?)', (key, json.dumps(job, ensure_ascii=False)))
+            self.run['batch']['count'] += 1
+            self.run.update(active=None, not_before=time.time() + self.run['config']['interval'])
+            self._save(db, job)
+            self._persist(db)
+            return {'ok': True}
+
+    def resolve(self, data):
+        """Explicit local UI resolution, never an automatic retry of an unknown submission."""
+        with self.lock, self.db() as db:
+            job = self._job(db, data['id'])
+            if job['state'] in ACCEPTED:
+                raise ValueError('已受理文章不能重置')
+            if self.run['running']:
+                raise ValueError('请先暂停流程')
+            if data.get('confirmed_not_accepted') is not True:
+                raise ValueError('必须先人工核对网站未受理，并清理编辑器/草稿')
+            job.update(state='queued' if data.get('retry') else 'cancelled', error='', snapshot={})
+            if self.run['active'] == job['id']:
+                self.run.update(active=None, owner=None)
+            self._save(db, job)
+            self._persist(db)
+            return {'ok': True}
+
+    def takeover(self, data):
+        with self.lock, self.db() as db:
+            if self.run['running']:
+                raise ValueError('请先在控制台暂停流程，再接管')
+            self.run['owner'] = data['owner']
+            self._persist(db)
+            return {'ok': True}
diff --git a/test/README.md b/test/README.md
new file mode 100644
index 0000000..e69355b
--- /dev/null
+++ b/test/README.md
@@ -0,0 +1,12 @@
+# 测试与归档
+
+- `history/`：从 auto_news_upload 根目录移入的历史截图和演示任务 JSON，保留原内容。不是自动测试，不能用作本次测试结论。
+- `fixtures/article/`：自造 Markdown 和三张 1×1 PNG，其中两张内容相同，用于验证上传去重及插图顺序。
+- `test_queue.py`：持久队列、去重、重启、终止、未知提交和按篇数换号。
+- `test_controller.py`：本地接口权限、模拟下载到队列、静态页面路由。
+- `test_download_core.py`：复制的下载器原有离线测试，针对合并项目中的下载器副本运行。
+- `importer.test.cjs`：导入器回归与自动模式的停止/冲突保护。
+- `browser.test.cjs`：本地页面、移动布局与模拟编辑器；从不请求真实论坛。
+- `artifacts/`：本轮页面截图，属于生成产物。
+
+原始受理去重记录继续保存在 `../发布去重记录.json`，服务启动时自动导入；没有作为测试残留移走或删除。
diff --git a/test/bridge.test.cjs b/test/bridge.test.cjs
new file mode 100644
index 0000000..0a4fba6
--- /dev/null
+++ b/test/bridge.test.cjs
@@ -0,0 +1,13 @@
+'use strict';
+const {test}=require('node:test');const assert=require('node:assert/strict');const fs=require('node:fs');const path=require('node:path');const vm=require('node:vm');
+test('终止后较早的 heartbeat 响应不能恢复流程',async()=>{
+ const handlers=new Map(),requests=[],responses=[],values={pairToken:'test-token',pairPort:8770};
+ class Event{constructor(type,options={}){this.type=type;this.detail=options.detail;}}
+ const doc={readyState:'loading',addEventListener(type,fn){handlers.set(type,fn);},dispatchEvent(event){if(event.type==='dww11:local-response')responses.push(JSON.parse(event.detail));else handlers.get(event.type)?.(event);}};
+ vm.runInNewContext(fs.readFileSync(path.join(__dirname,'../browser/local-bridge.user.js'),'utf8'),{document:doc,CustomEvent:Event,GM_getValue:(k,d)=>values[k]??d,GM_setValue:(k,v)=>values[k]=v,GM_addValueChangeListener:()=>{},GM_xmlhttpRequest:r=>requests.push(r)});
+ const call=(id,route)=>handlers.get('dww11:local-request')(new Event('',{detail:JSON.stringify({id,route})}));
+ const heartbeat=call('old','heartbeat');const stop=call('stop','stop');
+ requests[0].onload({status:200,responseText:JSON.stringify({running:true,epoch:1})});await heartbeat;
+ assert.equal(responses.find(r=>r.id==='old').value.running,false);assert.equal(values.halted,true);
+ requests[1].onload({status:200,responseText:JSON.stringify({running:false,epoch:2})});await stop;
+});
diff --git a/test/browser.test.cjs b/test/browser.test.cjs
new file mode 100644
index 0000000..c8b01c9
--- /dev/null
+++ b/test/browser.test.cjs
@@ -0,0 +1,91 @@
+'use strict';
+const {chromium}=require('playwright');
+const fs=require('node:fs');
+const path=require('node:path');
+const assert=require('node:assert/strict');
+const ROOT=path.resolve(__dirname,'..');
+const output=path.join(__dirname,'artifacts');fs.mkdirSync(output,{recursive:true});
+(async()=>{
+ const browser=await chromium.launch({headless:true,executablePath:process.env.CHROME_PATH||'/Applications/Google Chrome.app/Contents/MacOS/Google Chrome'});
+ try{
+  const page=await browser.newPage({viewport:{width:1440,height:1100}}),errors=[];
+  page.on('pageerror',error=>errors.push(error.message));
+  await page.route('**/*',route=>new URL(route.request().url()).hostname==='127.0.0.1'?route.continue():route.abort());
+  await page.goto('http://127.0.0.1:8771/');
+  await page.getByText('原创导入测试稿',{exact:true}).waitFor();
+  await page.screenshot({path:path.join(output,'desktop.png'),fullPage:true});
+  await page.locator('#fid').fill('125');await page.locator('#minimum').fill('1');await page.locator('#maximum').fill('2');await page.locator('#interval').fill('10');await page.locator('#history-checked').check();
+  await page.getByRole('button',{name:'保存处理规则'}).click();await page.getByText('处理规则已保存',{exact:true}).waitFor();
+  await page.locator('#start').click();await page.getByText('流程运行中',{exact:true}).waitFor();
+  await page.locator('#stop').click();await page.getByText('流程已暂停',{exact:true}).waitFor();
+  await page.setViewportSize({width:390,height:844});await page.screenshot({path:path.join(output,'mobile.png'),fullPage:true});
+  assert.equal(await page.evaluate(()=>document.documentElement.scrollWidth>innerWidth),false,'mobile overflow');
+  assert.deepEqual(errors,[]);console.log('PASS local UI: configuration, start/stop, desktop/mobile layout');
+  await page.close();
+  const mock=await browser.newPage();
+  await mock.route('**/*',route=>route.fulfill({contentType:'text/html; charset=utf-8',body:'测试账号'}));
+  await mock.goto('https://www.dww11.com/forum.php?mod=post&action=newthread&fid=125');
+  await mock.evaluate(()=>{
+   window.wysiwyg=1;window.events=[];window.clicks=0;window.formats=0;
+   window.job={id:'fixture',state:'preparing',title:'测试标题',source:'测试来源',fid:125,account:{uid:'123',name:'测试账号'}};
+   window.flow={running:true,epoch:1,active:'fixture',config:{fid:125}};
+   document.querySelector('#postsubmit').addEventListener('click',()=>window.clicks++);
+   window.DWW11Importer={stagePackage:async()=>({warnings:[]}),importPrepared:async()=>{
+    document.querySelector('#subject').value='测试标题';
+    document.querySelector('#e_iframe').contentDocument.body.innerHTML='
正文第一段
正文第二段
来源：测试来源，如有侵权，请联系删除。
';
+    return {images:{'a.gif':'1'}};
+   }};
+   document.addEventListener('dww11:local-request',event=>{
+    const {id,route,body}=JSON.parse(event.detail);let value={};
+    window.events.push({route,body});
+    if(route==='heartbeat'){window.flow.owner=body.owner;value=window.flow;}
+    if(route==='next')value={action:window.job.state==='preparing'?'prepare':'resume',job:window.job,run:window.flow};
+    if(route==='current')value={job:window.job,run:window.flow};
+    if(route==='event'){window.job.state=body.state;value={ok:true};}
+    if(route==='stop'){window.flow.running=false;value=window.flow;}
+    document.dispatchEvent(new CustomEvent('dww11:local-response',{detail:JSON.stringify({id,value})}));
+   });
+  });
+  await mock.addScriptTag({path:path.join(ROOT,'browser/formatter.js')});
+  await mock.addScriptTag({path:path.join(ROOT,'browser/runner.js')});
+  await mock.waitForFunction(()=>window.job.state==='awaiting_user_review');
+  await mock.waitForTimeout(2400);
+  assert.equal(await mock.evaluate(()=>window.clicks),0,'runner must never publish');
+  assert.equal(await mock.evaluate(()=>document.querySelector('#e_iframe').contentDocument.body.querySelectorAll('[data-dww11-wx-source]').length),1);
+  const before=await mock.evaluate(()=>document.querySelector('#e_iframe').contentDocument.body.innerHTML);
+  await mock.evaluate(()=>window.DWW11Formatter.format('测试来源'));
+  const after=await mock.evaluate(()=>document.querySelector('#e_iframe').contentDocument.body.innerHTML);
+  assert.equal(after,before,'repeated formatting should be idempotent');
+  await mock.locator('#postsubmit').click();
+  await mock.waitForFunction(()=>window.job.state==='user_submitting');
+  await mock.evaluate(()=>history.pushState({},'', '/thread/999.html'));
+  await mock.waitForFunction(()=>window.job.state==='submit_unknown');
+  assert.equal(await mock.evaluate(()=>window.flow.running),false);
+  assert.equal(await mock.evaluate(()=>window.events.some(e=>e.route==='accept')),false,'unknown page must not count accepted');
+  assert.equal(await mock.evaluate(()=>window.clicks),1);
+  console.log('PASS browser fixture: import/format, source uniqueness, repeated formatting, manual-only publish, unknown result stops');
+  await mock.close();
+  const ext=await browser.newPage();
+  await ext.route('**/*',route=>route.fulfill({contentType:'text/html; charset=utf-8',body:'
立即登录
'}));
+  await ext.goto('https://www.dww11.com/');
+  await ext.evaluate(()=>{
+    window.routes=[];window.chrome.runtime={sendMessage:async message=>{
+      window.routes.push(message.route);
+      if(message.route==='/hello')return {ok:true,data:{total:1,active:1,round:1,remaining:1,flow:null}};
+      if(message.route==='/start')return new Promise(resolve=>window.finishStart=()=>resolve({ok:true,data:{flow:{id:'test-run',phase:'logout',paused:false}}}));
+      if(message.route==='/suspend')return {ok:true,data:{}};
+      throw new Error('Unexpected extension operation: '+message.route);
+    }};
+  });
+  await ext.addScriptTag({path:path.join(ROOT,'../dww11-account-switch-browser-extension/content.js')});
+  await ext.waitForFunction(()=>JSON.parse(document.querySelector('#dww11-extension-panel').dataset.autoNewsState).idle);
+  await ext.locator('#dww11-extension-next').click();
+  await ext.waitForFunction(()=>!!window.finishStart);
+  await ext.evaluate(()=>{document.dispatchEvent(new CustomEvent('dww11:auto-stop'));window.finishStart();});
+  await ext.waitForFunction(()=>window.routes.includes('/suspend'));
+  assert.equal(await ext.evaluate(()=>JSON.parse(document.querySelector('#dww11-extension-panel').dataset.autoNewsState).paused),true);
+  assert.deepEqual(await ext.evaluate(()=>window.routes),['/hello','/start','/suspend']);
+  console.log('PASS extension bridge: stop during pending start prevents login and persists pause');
+  await ext.close();
+ }finally{await browser.close();}
+})().catch(error=>{console.error(error);process.exitCode=1;});
diff --git a/test/fixtures/article/image001.png b/test/fixtures/article/image001.png
new file mode 100644
index 0000000000000000000000000000000000000000..4bee45d006ca31bcbbd08ddcb181a215ad46cf72
GIT binary patch
literal 69
zcmeAS@N?(olHy`uVBq!ia0vp^j3CUx1SBVv2j2ryJf1F&Ar*6y1voE&WEgt)oQ>NB
P6ld^s^>bP0l+XkKrxgy_

literal 0
HcmV?d00001

diff --git a/test/fixtures/article/image002.png b/test/fixtures/article/image002.png
new file mode 100644
index 0000000000000000000000000000000000000000..52db58fc3d81b72bb702dcf3e81697ff5da9c62f
GIT binary patch
literal 69
zcmeAS@N?(olHy`uVBq!ia0vp^j3CUx1SBVv2j2ryJf1F&Ar*6yH=HbHW?;O<@R4=d
RpHiSWgQu&X%Q~loCIHSr5Rd=>

literal 0
HcmV?d00001

diff --git a/test/fixtures/article/image003.png b/test/fixtures/article/image003.png
new file mode 100644
index 0000000000000000000000000000000000000000..4bee45d006ca31bcbbd08ddcb181a215ad46cf72
GIT binary patch
literal 69
zcmeAS@N?(olHy`uVBq!ia0vp^j3CUx1SBVv2j2ryJf1F&Ar*6y1voE&WEgt)oQ>NB
P6ld^s^>bP0l+XkKrxgy_

literal 0
HcmV?d00001

diff --git a/test/fixtures/article/原创导入测试稿.md b/test/fixtures/article/原创导入测试稿.md
new file mode 100644
index 0000000..f38ed9c
--- /dev/null
+++ b/test/fixtures/article/原创导入测试稿.md
@@ -0,0 +1,15 @@
+# 原创导入测试稿
+
+这是项目自有的离线测试稿，用于验证正文、段落和图片顺序。
+
+![](image001.png)
+
+第二段保留原文标点，以及普通文字。
+
+![](image002.png)
+
+最后一段说明图片上传不等于发表文章。
+
+![](image003.png)
+
+来源：项目测试素材，如有侵权，请联系删除。
diff --git a/test/importer.test.cjs b/test/importer.test.cjs
new file mode 100644
index 0000000..c192efb
--- /dev/null
+++ b/test/importer.test.cjs
@@ -0,0 +1,172 @@
+// Offline verification only. No browser account, uploads or publication requests.
+'use strict';
+const { test } = require('node:test');
+const assert = require('node:assert/strict');
+const fs = require('node:fs');
+const path = require('node:path');
+const vm = require('node:vm');
+const { webcrypto, createHash } = require('node:crypto');
+const { execFileSync } = require('node:child_process');
+const core = require('../browser/importer.js');
+const directory = path.join(__dirname, 'fixtures/article');
+const mdName = '原创导入测试稿.md';
+function articleFiles() {
+    return fs.readdirSync(directory).map(name => {
+        const blob = new Blob([fs.readFileSync(path.join(directory, name))], { type: name.endsWith('.png') ? 'image/png' : 'text/markdown' });
+        blob.name = name; blob.webkitRelativePath = '文章/' + name; return blob;
+    });
+}
+
+test('测试文章：标题、3 张配图、插入顺序、来源与段落完整', async () => {
+    const article = await core.prepareFiles(articleFiles());
+    assert.equal(article.title, mdName.slice(0, -3));
+    assert.deepEqual([...article.images.keys()], ['文章/image001.png', '文章/image002.png', '文章/image003.png']);
+    const output = article.render(new Map([...article.images.keys()].map((p, i) => [p, String(101 + i)])));
+    assert.deepEqual([...output.matchAll(/\[attachimg\](\d+)\[\/attachimg\]/g)].map(m => m[1]), ['101', '102', '103']);
+    assert.equal(output.includes('# 原创导入测试稿'), false);
+    const md = fs.readFileSync(path.join(directory, mdName), 'utf8');
+    const originalBody = md.split('\n').slice(1).join('\n').trim().replace(/!\[\]\(image00(\d)\.png\)/g, (_, n) => `[attachimg]${100 + Number(n)}[/attachimg]`);
+    assert.equal(output, originalBody);
+});
+
+test('缺图、远程图片、超出目录、超大图片与超长标题在上传前被拒绝', () => {
+    assert.throws(() => core.compile('# 标题\n\n![](missing.jpg)', 'a.md', new Map()), /找不到配图/);
+    assert.throws(() => core.compile('# 标题\n\n![](https://x/a.jpg)', 'a.md', new Map()), /目录内/);
+    assert.throws(() => core.imagePath('a.md', '../secret.jpg'), /超出/);
+    assert.throws(() => core.imagePath('a.md', '%2fetc/passwd'), /相对路径/);
+    assert.throws(() => core.compile('# ' + '长'.repeat(81) + '\n正文', 'a.md', new Map()), /80/);
+    assert.throws(() => core.compile('# 标题\n\n![](big.png)', 'a.md', new Map([['big.png', {size:20*1024*1024}]])), /20 MB/);
+});
+
+test('子目录、Unicode 规范化、空格编码、括号、重复图片和格式转换', () => {
+    const fileMap = new Map([['目录/图 (1).jpg', new Blob(['image'])]]);
+    const article = core.compile('# 标题\n\n**粗体**和*斜体*\n\n![](图%20(1).jpg)\n![](<图 (1).jpg> "说明")\n\n[链接](https://example.com/a)\n\n- 一\n- 二\n\n> 引用', '目录/a.md', fileMap);
+    assert.equal(article.images.size, 1);
+    assert.match(article.render(new Map([['目录/图 (1).jpg', '100']])), /\[b\]粗体\[\/b\]/);
+    assert.equal(core.normalizePath('cafe\u0301/a.jpg'), 'café/a.jpg');
+    assert.equal(core.readLink("![](child's.jpg)", 0).target, "child's.jpg");
+    assert.throws(() => core.compile('# 标题\n![][a]\n[a]: x.jpg', 'a.md', fileMap), /引用式/);
+});
+
+test('多个 Markdown 必须选择；无 Markdown 不接受', async () => {
+    const files = articleFiles();
+    const extra = new Blob(['# 另一篇\n正文']); extra.name = 'b.md'; extra.webkitRelativePath = '文章/b.md';
+    const result = await core.prepareFiles([...files, extra]);
+    assert.equal(result.candidates.length, 2);
+    assert.equal((await core.prepareFiles([...files, extra], '文章/b.md')).title, '另一篇');
+    await assert.rejects(core.prepareFiles(files.filter(f => !f.name.endsWith('.md'))), /没有/);
+});
+
+test('下载程序对接：Python 文章包与目录直接导入完全一致', async () => {
+    const data = JSON.parse(execFileSync('python3', [path.join(__dirname, '../modules/package.py'), directory], {encoding:'utf8'}));
+    const packaged = await core.preparePackage(data);
+    const direct = await core.prepareFiles(articleFiles());
+    assert.equal(packaged.title, direct.title);
+    assert.equal(packaged.body, direct.body);
+    assert.equal(packaged.images.size, 3);
+    for (const [p, blob] of packaged.images) assert.equal(blob.size, fs.statSync(path.join(directory, p)).size);
+});
+
+test('服务器返回错误、登录 HTML 或混入脚本时不猜测附件编号', () => {
+    assert.equal(core.parseAid(' 123456\n'), '123456');
+    for (const value of ['-1', '0', '123', '', '123error', '{"aid":123}']) assert.throws(() => core.parseAid(value));
+});
+
+// Small DOM harness exercises the public API and site adapter without installing browser software.
+function harness({ failUpload = false, loseImages = false, existing = false } = {}) {
+    const ids = new Map(), callbacks = new Map(), requests = [];
+    class Element {
+        constructor(id='') { this.id=id; this.style={}; this.value=''; this.disabled=false; this.checked=false; this.hidden=false; this.listeners=new Map(); this.children=[]; }
+        attachShadow() { return this; }
+        set innerHTML(value) { this._html=value; for (const m of value.matchAll(/\bid="([^"]+)"/g)) ids.set(m[1], new Element(m[1])); }
+        get innerHTML() { return this._html || ''; }
+        getElementById(id) { return ids.get(id); }
+        appendChild(el) { this.children.push(el); return el; }
+        replaceChildren(...els) { this.children=els; }
+        addEventListener(name, fn) { this.listeners.set(name, fn); }
+        removeEventListener(name) { this.listeners.delete(name); }
+        dispatchEvent() {}
+        click() { this.onclick?.(); }
+        querySelectorAll() { return []; }
+    }
+    for (const id of ['subject', 'e_textarea', 'e_switchercheck', 'postform']) ids.set(id, new Element(id));
+    ids.get('subject').value=existing ? '原标题' : '';
+    ids.get('e_textarea').value=existing ? '原正文' : '';
+    const doc = { body:new Element(), createElement: () => new Element(), getElementById:id=>ids.get(id),
+        querySelector: s=>ids.get(s.replace(/^#/,'')), querySelectorAll:()=>[] };
+    const win = { document:doc, location:{search:'?mod=post&action=newthread&fid=95',href:'https://www.dww11.com/forum.php?mod=post&action=newthread&fid=95',origin:'https://www.dww11.com'},
+        wysiwyg:0, allowbbcode:1, allowimgcode:1, crypto:webcrypto,
+        imgUpload:{settings:{upload_url:'https://www.dww11.com/misc.php?mod=swfupload&operation=upload&fid=95',post_params:{uid:'fake-user',hash:'fake-hash',type:'image'},file_size_limit:20480}},
+        confirm:()=>true, dispatchEvent:()=>{}, addEventListener:()=>{}, editdoc:{body:new Element()} };
+    win.getEditorContents=()=>win.wysiwyg ? win.editdoc.body.innerHTML : ids.get('e_textarea').value;
+    win.switchEditor=mode=>{
+        if (mode===win.wysiwyg) return;
+        if (mode===1) win.editdoc.body.innerHTML=ids.get('e_textarea').value.replace(/\[attachimg\](\d+)\[\/attachimg\]/g, (_,aid)=>loseImages ? '' : ``);
+        else ids.get('e_textarea').value=win.editdoc.body.innerHTML;
+        win.wysiwyg=mode;
+    };
+    win.updateImageList=(_action,aids)=>{ for (const id of aids.split('|')) ids.set('image_'+id,new Element()); };
+    win.fetch=async (url,options)=>{
+        requests.push({url,options});
+        return {ok:true,text:async()=>failUpload ? '-1' : String(1000+requests.length)};
+    };
+    const context = {window:win,URL,URLSearchParams,Blob,FormData,AbortController,Uint8Array,Option:Element,Event:class {},CustomEvent:class {},
+        MutationObserver:class {observe(){} disconnect(){}},atob,setTimeout,clearTimeout,console};
+    vm.runInNewContext(fs.readFileSync(path.join(__dirname, '../browser/importer.js'),'utf8'), context);
+    return {api:win.DWW11Importer, win, ids, requests};
+}
+
+test('完整导入：暂存零请求、相同图片去重、3处附件映射、富文本结果、重试复用、没有发布请求', async () => {
+    const h=harness();
+    await h.api.stageFiles(articleFiles());
+    assert.equal(h.requests.length,0);
+    const result=await h.api.importPrepared();
+    assert.equal(Object.keys(result.images).length,3);
+    const uniqueImages=new Set(fs.readdirSync(directory).filter(p=>p.endsWith('.png')).map(p=>createHash('sha256').update(fs.readFileSync(path.join(directory,p))).digest('hex'))).size;
+    assert.equal(h.requests.length,uniqueImages);
+    assert.equal(h.ids.get('subject').value,mdName.slice(0,-3));
+    assert.match(h.win.getEditorContents(),/attachimg_1001/);
+    assert.equal(h.api.getState().busy,false);
+    assert.equal(h.api.getBackup().content,'');
+    await h.api.importPrepared();
+    assert.equal(h.requests.length,uniqueImages);
+    for (const req of h.requests) {
+        assert.equal(new URL(req.url).pathname,'/misc.php');
+        assert.equal(req.options.body.get('type'),'image');
+        assert.ok(req.options.body.get('Filedata') instanceof Blob);
+    }
+});
+
+test('上传失败保留原文；富文本丢图片时回滚；取消覆盖不上传', async () => {
+    for (const options of [{failUpload:true,existing:true},{loseImages:true,existing:true}]) {
+        const h=harness(options);
+        await h.api.stageFiles(articleFiles());
+        await assert.rejects(h.api.importPrepared());
+        assert.equal(h.ids.get('subject').value,'原标题');
+        assert.equal(h.win.getEditorContents(),'原正文');
+        assert.equal(h.api.getState().busy,false);
+    }
+    const h=harness({existing:true}); h.win.confirm=()=>false;
+    await h.api.stageFiles(articleFiles());
+    assert.equal((await h.api.importPrepared()).cancelled,true);
+    assert.equal(h.requests.length,0);
+});
+
+// New integration guards must not prompt or overwrite a user's draft.
+test('自动导入：非空编辑器停止，不弹窗、不上传', async () => {
+ const h=harness({existing:true});h.win.confirm=()=>{throw new Error('unexpected prompt');};
+ await h.api.stageFiles(articleFiles());
+ await assert.rejects(h.api.importPrepared({automatic:true}),/编辑器已有内容/);
+ assert.equal(h.requests.length,0);assert.equal(h.ids.get('subject').value,'原标题');
+});
+test('自动导入：预先终止不上传，不填写', async () => {
+ const h=harness();await h.api.stageFiles(articleFiles());const c=new AbortController();c.abort(new Error('stopped'));
+ await assert.rejects(h.api.importPrepared({automatic:true,signal:c.signal}),/stopped/);
+ assert.equal(h.requests.length,0);assert.equal(h.ids.get('subject').value,'');
+});
+test('自动导入：上传中终止不会填写正文或继续下一张', async () => {
+ const h=harness();await h.api.stageFiles(articleFiles());const c=new AbortController();
+ const original=h.win.fetch;h.win.fetch=async (...args)=>{const result=await original(...args);c.abort(new Error('stopped'));return result;};
+ await assert.rejects(h.api.importPrepared({automatic:true,signal:c.signal}),/stopped/);
+ assert.equal(h.requests.length,1);assert.equal(h.ids.get('subject').value,'');
+});
diff --git a/test/serve_fixture.py b/test/serve_fixture.py
new file mode 100644
index 0000000..c437987
--- /dev/null
+++ b/test/serve_fixture.py
@@ -0,0 +1,19 @@
+"""Temporary local UI fixture; never contacts the news API or forum."""
+from pathlib import Path
+import sys
+import tempfile
+from http.server import ThreadingHTTPServer
+ROOT = Path(__file__).resolve().parents[1]
+sys.path.insert(0, str(ROOT))
+from app import Controller, make_handler
+with tempfile.TemporaryDirectory() as temp:
+    controller = Controller(Path(temp) / 'data', Path(temp) / 'downloads', ledger=None)
+    controller.store.enqueue(ROOT / 'test/fixtures/article')
+    server = ThreadingHTTPServer(('127.0.0.1', 8771), make_handler(controller))
+    print('UI fixture listening on 8771', flush=True)
+    try:
+        server.serve_forever()
+    except KeyboardInterrupt:
+        pass
+    finally:
+        server.server_close()
diff --git a/test/test_controller.py b/test/test_controller.py
new file mode 100644
index 0000000..f43d03d
--- /dev/null
+++ b/test/test_controller.py
@@ -0,0 +1,75 @@
+import json
+from pathlib import Path
+import sys
+import tempfile
+import threading
+import unittest
+from http.server import ThreadingHTTPServer
+from urllib.request import Request, urlopen
+from urllib.error import HTTPError
+
+ROOT = Path(__file__).resolve().parents[1]
+sys.path.insert(0, str(ROOT))
+from app import Controller, make_handler
+
+
+class ControllerTests(unittest.TestCase):
+    def setUp(self):
+        self.tmp = tempfile.TemporaryDirectory()
+        self.root = Path(self.tmp.name)
+        self.controller = Controller(self.root / 'data', self.root / 'downloads', ledger=None)
+        self.server = ThreadingHTTPServer(('127.0.0.1', 0), make_handler(self.controller))
+        self.thread = threading.Thread(target=self.server.serve_forever, daemon=True)
+        self.thread.start()
+        self.url = 'http://127.0.0.1:' + str(self.server.server_port)
+
+    def tearDown(self):
+        self.server.shutdown();self.server.server_close();self.thread.join();self.tmp.cleanup()
+
+    def request(self, path, body=None, token=None, origin=None, host=None):
+        headers = {}
+        if token: headers['X-Session-Token'] = token
+        if origin: headers['Origin'] = origin
+        if host: headers['Host'] = host
+        if body is not None: headers['Content-Type'] = 'application/json'
+        request = Request(self.url + path, data=None if body is None else json.dumps(body).encode(), headers=headers)
+        with urlopen(request, timeout=5) as response:
+            return response.status, response.read()
+
+    def test_auth_and_origin_boundaries(self):
+        for path, kwargs in [('/api/state', {}), ('/api/state', {'token': self.controller.bridge_token}),
+                            ('/api/state', {'token': self.controller.ui_token, 'origin': 'https://example.com'}),
+                            ('/bridge/heartbeat', {'token': self.controller.ui_token})]:
+            with self.assertRaises(HTTPError) as error:
+                self.request(path, {}, **kwargs)
+            self.assertEqual(error.exception.code, 403)
+        with self.assertRaises(HTTPError):
+            self.request('/api/session', host='attacker.example')
+        code, body = self.request('/api/state', {}, token=self.controller.ui_token)
+        self.assertEqual(code, 200)
+        self.assertNotIn(self.controller.bridge_token, body.decode())
+
+    def test_static_and_unknown_routes(self):
+        self.assertIn('新闻工作台', self.request('/')[1].decode())
+        self.assertEqual(self.request('/browser/auto-news.user.js')[0], 200)
+        with self.assertRaises(HTTPError):
+            self.request('/../store.py')
+        with self.assertRaises(HTTPError):
+            self.request('/bridge/scan', {}, token=self.controller.bridge_token)
+
+    def test_download_to_queue_without_network(self):
+        self.controller.manager.requester = lambda *_: {'code': 1, 'data': {'list': [dict(title='模拟新闻', src='模拟来源', content='
模拟正文
', url='https://example.com/news')]}}
+        self.controller.ui('download', dict(key='fake-key', channel='模拟频道', target=1))
+        self.controller.manager.thread.join(5)
+        state = self.controller.ui('state', {})
+        self.assertEqual(state['download']['saved'], 1)
+        self.assertEqual(len(state['jobs']), 1)
+        self.assertEqual(state['jobs'][0]['state'], 'queued')
+        self.assertTrue(state['jobs'][0]['source_keys'])
+        self.assertNotIn('fake-key', json.dumps(state))
+        self.controller.scan(self.controller.manager.root)
+        self.assertEqual(len(self.controller.store.state()['jobs']), 1)
+
+
+if __name__ == '__main__':
+    unittest.main()
diff --git a/test/test_download_core.py b/test/test_download_core.py
new file mode 100644
index 0000000..449852d
--- /dev/null
+++ b/test/test_download_core.py
@@ -0,0 +1,165 @@
+import base64
+import json
+from pathlib import Path
+import sys
+import tempfile
+import threading
+import unittest
+from http.server import ThreadingHTTPServer
+
+import requests
+sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
+from app import downloader
+Downloader, make_handler, fingerprints = downloader.Downloader, downloader.make_handler, downloader.fingerprints
+from article_writer import save_article
+
+
+def article(i):
+    return dict(title=f'新闻{i}', content=f'
第{i}篇新闻内容
', url=f'https://example.com/{i}', src='测试来源', time='2026-10-31')
+
+
+class DownloadTests(unittest.TestCase):
+    def setUp(self):
+        self.temp = tempfile.TemporaryDirectory()
+        self.root = Path(self.temp.name)
+
+    def tearDown(self):
+        self.temp.cleanup()
+
+    def run_job(self, manager, target):
+        manager.start('test-key', '头条', target)
+        manager.thread.join(10)
+        self.assertFalse(manager.thread.is_alive())
+        return manager.snapshot()
+
+    def test_format_and_local_image(self):
+        data = article(1)
+        image = 'data:image/png;base64,' + base64.b64encode(b'\x89PNG\r\n\x1a\nexample').decode()
+        data['content'] += f''
+        result = save_article(data, self.root)
+        body = Path(result.markdown).read_text()
+        self.assertTrue(body.startswith('# 新闻1\n\n第1篇新闻内容'))
+        self.assertNotIn('发布时间：2026-10-31', body)
+        self.assertNotIn('\n---\n', body)
+        self.assertTrue(body.endswith('来源：测试来源，如有侵权，请联系删除。\n'))
+        self.assertEqual(len(result.images), 1)
+        self.assertEqual(body.count('image001.png'), 2)
+        self.assertNotIn('data:image', body)
+        second = save_article(data, self.root)
+        self.assertEqual(Path(second.markdown).name, '新闻1 (2).md')
+
+    def test_bad_image_cleans_partial(self):
+        data = article(1)
+        data['content'] += ''
+        with self.assertRaises(Exception):
+            save_article(data, self.root)
+        self.assertEqual(list(self.root.iterdir()), [])
+
+    def test_duplicate_then_fill_and_restart(self):
+        items = [article(1), article(1), article(2), article(3)]
+        calls = []
+        def request(key, endpoint, params):
+            calls.append(params.copy())
+            return {'code': 1, 'data': {'list': items[params['start']:params['start']+params['num']]}}
+        manager = Downloader(self.root, request)
+        state = self.run_job(manager, 3)
+        self.assertEqual((state['status'], state['saved'], state['skipped']), ('completed', 3, 1))
+        self.assertEqual([c['start'] for c in calls], [0, 3])
+        restarted = Downloader(self.root, request)
+        state = self.run_job(restarted, 3)
+        self.assertEqual((state['status'], state['saved'], state['skipped']), ('partial', 0, 4))
+        self.assertEqual(len(list(self.root.glob('*/*.md'))), 3)
+
+    def test_offset_limit_and_partial_progress(self):
+        offsets = []
+        def request(key, endpoint, params):
+            offsets.append(params['start'])
+            return {'code': 1, 'data': {'list': [article(i) for i in range(params['start'], params['start']+params['num'])]}}
+        state = self.run_job(Downloader(self.root, request), 500)
+        self.assertEqual(state['status'], 'partial')
+        self.assertEqual(state['saved'], 440)
+        self.assertEqual(max(offsets), 400)
+
+    def test_error_and_key_redaction(self):
+        def request(*args):
+            return {'code': 10001, 'msg': 'invalid test-key'}
+        manager = Downloader(self.root, request)
+        state = self.run_job(manager, 10)
+        self.assertEqual(state['status'], 'error')
+        self.assertNotIn('test-key', json.dumps(state))
+
+    def test_stop_and_concurrent_start(self):
+        entered, release = threading.Event(), threading.Event()
+        def request(*args):
+            entered.set()
+            release.wait(2)
+            return {'code': 1, 'data': {'list': [article(1)]}}
+        manager = Downloader(self.root, request)
+        manager.start('key', '头条', 10)
+        self.assertTrue(entered.wait(2))
+        with self.assertRaises(ValueError):
+            manager.start('key', '头条', 10)
+        manager.stop.set()
+        release.set()
+        manager.thread.join(3)
+        self.assertEqual(manager.snapshot()['status'], 'cancelled')
+        self.assertEqual(manager.snapshot()['saved'], 0)
+
+    def test_failed_save_can_retry_next_job(self):
+        attempts = []
+        def writer(data, root):
+            attempts.append(1)
+            if len(attempts) == 1:
+                raise ValueError('模拟图片失败')
+            return save_article(data, root)
+        def request(key, endpoint, params):
+            return {'code': 1, 'data': {'list': [article(1)] if params['start'] == 0 else []}}
+        manager = Downloader(self.root, request, writer)
+        self.assertEqual(self.run_job(manager, 1)['failed'], 1)
+        self.assertEqual(self.run_job(manager, 1)['saved'], 1)
+
+    def test_fingerprint_content_and_tracking(self):
+        a, b = article(1), article(2)
+        b['content'] = a['content'].replace('
', '
').replace('
', '
')
+        self.assertTrue(set(fingerprints(a)) & set(fingerprints(b)))
+        b['content'] = '其他内容'
+        b['url'] = a['url'] + '?utm_source=abc#fragment'
+        self.assertTrue(set(fingerprints(a)) & set(fingerprints(b)))
+
+    def test_log_cap(self):
+        manager = Downloader(self.root)
+        for i in range(400):
+            manager.log(str(i))
+        self.assertEqual(len(manager.snapshot()['logs']), 300)
+        self.assertEqual(manager.snapshot()['logs'][0]['message'], '100')
+
+    def test_http_routes_and_access(self):
+        def request(key, endpoint, params=None):
+            return {'code': 1, 'data': {'list': ['头条', '科技']}}
+        manager = Downloader(self.root, request)
+        server = ThreadingHTTPServer(('127.0.0.1', 0), make_handler(manager, 'token'))
+        worker = threading.Thread(target=server.serve_forever, daemon=True)
+        worker.start()
+        url = f'http://127.0.0.1:{server.server_port}'
+        try:
+            self.assertIn('新闻下载器', requests.get(url).text)
+            self.assertEqual(requests.get(url+'/api/state').json()['status'], 'idle')
+            self.assertEqual(requests.post(url+'/api/channels', json={'key': 'test'}).status_code, 403)
+            self.assertEqual(requests.get(url, headers={'Host':'evil.example'}).status_code, 403)
+            headers = {'X-Session-Token': 'token'}
+            self.assertEqual(requests.post(url+'/api/channels', headers=headers, json={'key':'test'}).json()['channels'], ['头条','科技'])
+            invalid = requests.post(url+'/api/start', headers=headers, json={'key':'test', 'target':0,'channel':'头条'})
+            self.assertEqual(invalid.status_code, 400)
+            invalid = requests.post(url+'/api/debug', headers=headers, json={'key':'test','endpoint':'index','num':41,'start':0})
+            self.assertEqual(invalid.status_code, 400)
+            debug = requests.post(url+'/api/debug', headers=headers, json={'key':'test','endpoint':'channel'})
+            self.assertEqual(debug.status_code, 200)
+            self.assertNotIn('key=test', debug.text)
+        finally:
+            server.shutdown()
+            server.server_close()
+            worker.join()
+
+
+if __name__ == '__main__':
+    unittest.main()
diff --git a/test/test_queue.py b/test/test_queue.py
new file mode 100644
index 0000000..298fa1b
--- /dev/null
+++ b/test/test_queue.py
@@ -0,0 +1,155 @@
+import hashlib
+import json
+from pathlib import Path
+import shutil
+import sys
+import tempfile
+import unittest
+
+ROOT = Path(__file__).resolve().parents[1]
+sys.path.insert(0, str(ROOT))
+from articles import inspect_article, short_title
+from store import Store
+
+
+class QueueTests(unittest.TestCase):
+    def setUp(self):
+        self.tmp = tempfile.TemporaryDirectory()
+        self.root = Path(self.tmp.name)
+        self.article = self.root / 'article'
+        self.article.mkdir()
+        self.md = self.article / 'a.md'
+        self.md.write_text('# 测试新闻\n\n正文内容。\n\n来源：测试来源，如有侵权，请联系删除。\n')
+        self.store = Store(self.root / 'queue.sqlite3')
+        self.store.configure(dict(fid=125, minimum=1, maximum=1, interval=0, history_checked=True))
+        self.owner = dict(owner='tab-a', account=dict(uid='123', name='测试账号'), extension={'idle': True})
+
+    def tearDown(self):
+        self.tmp.cleanup()
+
+    def begin(self):
+        self.store.enqueue(self.article)
+        self.store.control('start')
+        return self.store.next(self.owner)['job']
+
+    def transition(self, job, state, **extra):
+        return self.store.event(dict(owner='tab-a', id=job['id'], state=state, epoch=self.store.run['epoch'], **extra))
+
+    def submit(self, job):
+        for state in ('importing', 'formatting', 'awaiting_user_review'):
+            self.transition(job, state)
+        self.transition(job, 'user_submitting', snapshot={'title': job['title']})
+
+    def accept(self, job):
+        return self.store.accept(dict(owner='tab-a', id=job['id'], post_url='https://www.dww11.com/thread/12345.html',
+            author_uid='123', fid=125, title=job['title'], state='accepted_pending_moderation', evidence={'test': 'fixture only'}))
+
+    def test_stable_identity_and_original_preserved(self):
+        before = self.md.read_bytes()
+        item = inspect_article(self.article)
+        copy = self.root / 'renamed'
+        shutil.copytree(self.article, copy)
+        (copy / 'a.md').write_text(self.md.read_text().replace('测试新闻', '改标题'))
+        self.assertEqual(inspect_article(copy)['article_key'], item['article_key'])
+        self.assertEqual(self.md.read_bytes(), before)
+        self.assertEqual(item['source'], '测试来源')
+
+    def test_title_does_not_break_emoji(self):
+        short = short_title('😀' * 50)
+        self.assertTrue(short.endswith('...'))
+        self.assertLessEqual(len(short.encode('utf-16-le')) // 2, 80)
+        self.assertEqual(short_title('短标题'), '短标题')
+
+    def test_unsupported_images_stop_before_queue(self):
+        (self.article / 'a.webp').write_bytes(b'webp')
+        with self.assertRaisesRegex(ValueError, '暂不支持'):
+            self.store.enqueue(self.article)
+        self.assertEqual(self.store.state()['jobs'], [])
+
+    def test_missing_and_outside_image_rejected(self):
+        for image in ('missing.png', '../outside.png', 'https://example.com/a.png'):
+            self.md.write_text('# 标题\n\n正文 ![](' + image + ')\n\n来源：测试，如有侵权，请联系删除。')
+            with self.assertRaises(ValueError):
+                self.store.enqueue(self.article)
+
+    def test_no_duplicate_queue_or_cross_tab_claim(self):
+        job = self.begin()
+        self.assertIn('已在队列', self.store.enqueue(self.article))
+        self.assertEqual(self.store.next({**self.owner, 'owner': 'tab-b'})['action'], 'other_tab')
+        self.assertEqual(self.store.next(self.owner)['job']['id'], job['id'])
+
+    def test_stop_invalidates_old_continuation(self):
+        job = self.begin()
+        epoch = self.store.run['epoch']
+        self.store.control('stop')
+        self.store.control('start')
+        with self.assertRaisesRegex(ValueError, '过期'):
+            self.store.event(dict(owner='tab-a', id=job['id'], state='importing', epoch=epoch))
+
+    def test_restart_pauses_and_preserves_claim(self):
+        job = self.begin()
+        restarted = Store(self.root / 'queue.sqlite3')
+        self.assertFalse(restarted.run['running'])
+        self.assertEqual(restarted.run['active'], job['id'])
+        self.assertEqual(restarted.run['batch']['target'], 1)
+
+    def test_accept_requires_manual_submission(self):
+        job = self.begin()
+        with self.assertRaisesRegex(ValueError, '人工提交'):
+            self.accept(job)
+
+    def test_accept_is_atomic_and_idempotent(self):
+        job = self.begin()
+        self.submit(job)
+        self.accept(job)
+        self.accept(job)
+        self.assertEqual(self.store.run['batch']['count'], 1)
+        self.assertIn('已受理', self.store.enqueue(self.article))
+        with self.assertRaisesRegex(ValueError, '已受理'):
+            self.store.resolve(dict(id=job['id'], confirmed_not_accepted=True, retry=True))
+
+    def test_unknown_never_requeues_automatically(self):
+        job = self.begin()
+        self.submit(job)
+        self.transition(job, 'submit_unknown')
+        self.assertEqual(self.store.next(self.owner)['job']['state'], 'submit_unknown')
+        self.assertEqual(self.store.run['batch']['count'], 0)
+        self.assertIsNone(self.store.run['switch'])
+
+    def test_migrate_real_ledger_shape(self):
+        record = dict(markdown_sha256=hashlib.sha256(self.md.read_bytes()).hexdigest(), block_repost=True,
+                      markdown_path=str(self.md), status='accepted_pending_moderation', post_id='12345')
+        self.store.import_history([record])
+        self.assertIn('已受理', self.store.enqueue(self.article))
+
+    def test_switch_only_after_target_and_with_more_work(self):
+        job = self.begin()
+        self.submit(job)
+        self.accept(job)
+        other = self.root / 'other';shutil.copytree(self.article, other)
+        (other / 'a.md').write_text(self.md.read_text().replace('正文内容', '另一篇内容'))
+        self.store.enqueue(other)
+        self.assertEqual(self.store.next(self.owner)['action'], 'switch')
+        self.assertEqual(self.store.next(self.owner)['action'], 'switch')
+        self.store.switch_begin({'owner': 'tab-a'})
+        with self.assertRaisesRegex(ValueError, '禁止重复'):
+            self.store.switch_begin({'owner': 'tab-a'})
+        self.assertEqual(self.store.next(self.owner)['action'], 'switch_wait')
+        next_job = self.store.next({**self.owner, 'account': {'uid': '456', 'name': '新测试账号'}})
+        self.assertEqual(next_job['action'], 'prepare')
+        self.assertEqual(self.store.run['batch']['count'], 0)
+
+    def test_no_switch_when_queue_done(self):
+        job = self.begin();self.submit(job);self.accept(job)
+        self.assertEqual(self.store.next(self.owner)['action'], 'idle')
+        self.assertIsNone(self.store.run['switch'])
+
+    def test_bad_result_does_not_increment(self):
+        job = self.begin();self.submit(job)
+        with self.assertRaises(ValueError):
+            self.store.accept(dict(owner='tab-a', id=job['id'], post_url='https://example.com/thread/12345.html'))
+        self.assertEqual(self.store.run['batch']['count'], 0)
+
+
+if __name__ == '__main__':
+    unittest.main()
diff --git a/test/验证记录.md b/test/验证记录.md
new file mode 100644
index 0000000..598e334
--- /dev/null
+++ b/test/验证记录.md
@@ -0,0 +1,22 @@
+# 本轮验证记录
+
+日期：2026-10-31。测试均未使用真实账号，未向新闻 API 请求内容，未向论坛上传或发布。
+
+| 范围 | 结果 |
+| --- | --- |
+| Python 下载器、队列与 HTTP 接口 | 27/27 通过 |
+| JavaScript 导入器与停止/覆盖保护 | 11/11 通过 |
+| 连接桥旧响应与终止竞态 | 1/1 通过 |
+| 本地前端 | 配置保存、开始/停止、桌面与手机布局通过，无页面脚本错误、无手机横向溢出 |
+| 模拟编辑器 | 导入→排版→待人工审核；来源唯一、重复排版保持一致；程序无自动发帖点击 |
+| 模拟人工发表与未知结果 | 真实测试点击被记录；候选结果页未适配时暂停，不调用受理接口 |
+| 模拟换号插件 | 启动请求尚未返回时终止，返回后调用暂停，不执行登录；状态明确 paused |
+| JavaScript 语法 | 合并脚本、连接脚本、更新后的插件 content.js 通过 |
+
+浏览器使用本机 Chrome 的独立临时配置。对论坛域名的所有请求均被测试 HTML 拦截。后端使用临时目录和 SQLite，不写入正式任务库。
+
+页面截图：`artifacts/desktop.png`、`artifacts/mobile.png`。
+
+测试中曾发现模拟网页未声明 UTF-8，导致中文登录入口无法匹配；已修正测试响应编码并重新通过。真实网页编码未由此假定。
+
+尚未验证：用户浏览器中油猴本地通信权限、真实网站当前的导入与附件转换、真实换号账号链路、结果页受理/审核/公开状态。按用户决定，结果页 HTML 待提供，自动核对暂不实现；因此当前不宣称全流程批量处理已完成在线验收。
diff --git a/发布流程操作记录与自动化规范.md b/发布流程操作记录与自动化规范.md
new file mode 100644
index 0000000..b94dd29
--- /dev/null
+++ b/发布流程操作记录与自动化规范.md
@@ -0,0 +1,167 @@
+# 广谈大湾网：下载、导入排版、人工发布与换号
+
+本文中的帐号名称和用户编号已匿名化；真实记录保存在本地排除目录中。
+
+记录日期：2026-10-31（北京时间）。本文依据用户指导、Chrome 实际操作和现有源码检查编写。它是后续实现的流程依据；需求不等于功能已经实现。
+
+## 1. 不可改变的边界
+
+- **“发表帖子”只能由用户亲手点击。** 自动化只下载、选择、上传、填写、排版、校验、提示审核、观察提交结果和记录计数。禁止模拟点击发布、调用提交函数、直接发送发帖请求或通过快捷键提交。
+- 标题被截断、正文或来源被修改后，都必须重新进入人工审核。发生标题过长错误后，“重新尝试发表”也由用户再次点击。
+- 用户决定分区和文章根目录；“理财财经”只是本次例子，不能成为所有文章的固定分区。
+- 全流程页面常驻“终止流程”按钮。点击后立即取消后续动作、重试、队列领取和自动换号，不自动恢复。已经到达网站的请求不能撤回，需保留记录并核对。
+- 已发表或已被网站接收待审核的文章不能再次排入发布队列，换账号也不能绕过去重。
+
+## 2. 本次演示记录
+
+| 项目 | 结果 |
+| --- | --- |
+| 站点 | https://www.dww11.com/ |
+| 当前账号 | 示例用户，页面用户编号 <已匿名> |
+| 分区 | 理财财经，fid=125 |
+| 入口 | 首页右上角“免费发布信息”→ 分区页“理财财经” |
+| 分区页 | https://www.dww11.com/special/post/ |
+| 新帖页 | https://www.dww11.com/forum.php?mod=post&action=newthread&fid=125 |
+| 标签行为 | 点击分区后新开标签，原分区页保留 |
+| 测试标题 | 刚靠新电影赚23亿票房，周星驰就卖掉内地影院 |
+| 原标题长度 | 22 个 Unicode 码点；本篇无需截断。网站计数方式尚未实测 |
+| 目录 | `<项目根目录>/tanshuapi_news_downloader/downloads/刚靠新电影赚23亿票房，周星驰就卖掉内地影院` |
+| 目录内容 | 1 个 Markdown + 26 张 JPG，共 27 个文件 |
+| 来源 | 洲洲影视娱评（取文章末尾来源，不取正文“信息来源”截图） |
+| 导入 | 已完成；面板提示“已填写标题、正文和 26 张配图” |
+| 排版 | 已完成，正文 4 号黑色，尾注 1 号银色 |
+| 核对 | 编辑器 DOM 中图片 26 张，最终来源尾注仅 1 条 |
+| 发布 | 用户已亲手点击；网站已受理，详情页显示“审核中” |
+| 帖子链接 | https://www.dww11.com/thread/23697411.html |
+| 帖子标识 | 主题 ID 23697411；首帖 PID 238766 |
+| 数量 | 已明确受理 1 篇；已确认审核通过并公开 0 篇 |
+| 发布后图片 | 正文 21 张 + 附件区 5 张，共 26 张 |
+| 换号 | 未执行；本次未设置最小值和最大值 |
+
+本次页面没有“终止流程”按钮。用户明确同意本次演示暂用浏览器控制条停止，常驻页面按钮仍是后续自动化的必备条件。该例外只适用于本次演示。
+
+本次已验证导入、排版、用户亲手发表以及网站受理后的帖子详情页；页面明确显示“审核中”。尚未验证审核通过后的访客可见性、标题超限错误或换号链路。用户称发表后自动回首页，但本次实际读取的原编辑器标签已导航至帖子详情页，不能将“提交后必然自动回首页”写成网站行为。应在结果登记后主动回首页并核对。
+
+## 3. 用户操作步骤与自动化对应
+
+1. 启动前让用户选择分区、下载目录、待处理文章范围，并填写每个账号发布数量的最小值和最大值。展示当前账号。先初始化常驻终止按钮与持久任务记录。
+2. 从下载器接收完整落盘的文章目录。检查正文、图片引用、来源和去重记录；保存中或缺文件的目录不进入导入队列。
+3. 点击“免费发布信息”，展示实际可用分区，由用户选择。等待新标签打开并核对分区名称及 fid；不能继续操作旧标签或仅凭坐标判断。
+4. 在右下角“本地文章导入 · 1.0”选择“选择文章目录”。日常演示选择单篇目录，目录应包含 Markdown 和全部配图；不要只选 `.md`。如果选择根目录导致出现多个 Markdown，必须明确选中哪一篇。
+5. 在系统文件选择器进入用户指定根目录，再选择对应文章文件夹。系统“Upload”是把所选文件提供给页面读取，不是发表帖子；浏览器另有目录文件数量确认。
+6. 阅读导入面板标题、正文预览、图片数量和告警。点击“上传配图并填写”后才开始向网站上传正文引用的图片。等待明确完成提示，不能用固定等待时间代替完成判断。
+7. 读取文章最后的标准尾注 `来源：名称，如有侵权，请联系删除。`，只取名称。本篇是“洲洲影视娱评”；用户先前茅台文章例子是“酒业内参”，不能硬编码。
+8. 点击编辑工具栏绿色“一键排版”（不是网站自带“自动排版”，也不是“一键导入微信公众号并排版”）。实际弹窗要求输入**来源公众号名称**，并非标题。本篇填“洲洲影视娱评”，确认后会提示排版完成。
+9. 标题由本地导入器填入页面标题框；仍需核对完整标题。当前“一键排版”不弹标题输入框。如果用户说“输入标题”，应在标题框填写和确认，而不是填到来源弹窗。
+10. 校验标题、正文、图片数量和顺序、尾注唯一性、账号和分区。保留用户原文；本篇的发布时间、“打开网易新闻 查看精彩图片”等原始文字未擅自清理。需要清理时应成为用户可见的规则。
+11. 页面提示“已完成，等待人工审核，请自行点击发表帖子”。自动化停止修改编辑器，保留终止按钮，等待用户操作；不自动保存草稿或发表。网站原有自动保存仍可能运行。
+12. 用户自行点击“发表帖子”。自动化只观察结果。若标题超长，按第 5 节修正，重新提示审核，等待用户再次点击。
+13. 收集帖子链接/编号、作者、分区和结果证据后记账。审核中单独记录并阻止重发；结果不明时先核对，不能自动重试发布。
+14. 已明确成功后先持久保存发布记录与计数，再回到首页。达到当前账号目标篇数且没有未决提交时，点击页面顶部“登陆下一帐号”，核对登录成功后再处理下一篇。
+
+## 4. 页面适配依据与当前缺口
+
+以下选择器来自本次可见页面或本地源码，未来运行时须重新检查，不能保证网站改版后仍成立。
+
+| 控件 | 当前依据 | 注意事项 |
+| --- | --- | --- |
+| 当前用户 | `#mumucms_username` | 同时读取页面用户名与用户链接编号 |
+| 下一账号 | `#dww11-extension-next` | 完成记录后才允许换号；核对成功，不以按钮点击作为成功 |
+| 标题 | `#subject` | 本次读取到 maxLength=-1，不能只依赖 HTML maxlength |
+| 可视化正文 | `iframe#e_iframe` 内的 body | 图文与尾注检查应在 iframe 内进行 |
+| 纯文本开关 | `#e_switchercheck` | 不将 Markdown 直接当网站 BBCode |
+| 一键排版 | `#dww11-format-oneclick` | 原生 prompt 输入来源，随后 alert 提示完成 |
+| 发表 | `#postsubmit` | 仅用于识别状态和观察人工提交，禁止自动触发 |
+| 导入面板 | 油猴脚本面板，包含 choose/import 等控件 | 面板可能位于 Shadow DOM；普通页面选择器未必能定位，优先按可见控件操作 |
+
+本次实际遇到的兼容问题：
+
+- 浏览器连接器直接设置目录文件被“允许访问文件网址”权限阻止。本次没有更改扩展权限，改用 Chrome 原生系统选择器完成。后续实现应优先复用本地文章包接口，减少对文件对话框的依赖。
+- macOS 路径含中文，逐键输入曾丢失中文；通过文本框完整赋值成功定位。输入后必须核对完整路径，不能只看末级数字或英文。
+- 导入器能完成 26 张图片上传，并临时禁用发表按钮；上传完成后恢复。上传过程中不允许换号。
+- **来源重复：** 一键排版保留了导入正文中的原尾注，又追加银色尾注。本次在编辑器中删除原来的那一条，保留银色尾注，复查最终只出现一次。后续应在排版适配器中精确处理末尾标准尾注，不能全局删除正文中的“来源”。
+- 页面“还可输入 80 个字符”在导入后仍显示 80，不能将这个显示值当作可靠的标题长度校验结果。
+- 页面有“上次未提交成功的数据”恢复提示；本次没有点击恢复，避免把旧稿混入新稿。后续遇到已有正文或恢复冲突必须暂停处理。
+
+## 5. 标题超过 80 字符
+
+保留 `original_title`，派生 `submitted_title`。超过站点限制时截取前缀并追加字面量 `...`，总长不超过 80；即长度允许时保留前 77 个字符再加 3 个点。示例中的“标题文本...”表示实际标题前缀和省略号，不额外加入中文括号。
+
+当前站点的“字符”计数方式尚未通过超长标题实测。实现时兼容中文和 emoji，不能切断代理对；先按保守规则校验，再根据站点明确错误调整。若站点按字节计数，则按其实际字节预算截取，不能反复盲目减少。
+
+现有导入器在读取阶段对超过 80 个 Unicode 码点的标题直接报错。后续需把截断放在导入前，否则到不了人工审核阶段。截断不覆盖原 Markdown 标题，也不改变文章去重身份。
+
+如果用户点击发表后才收到标题超限提示：确认网站明确未接受 → 修正标题 → 显示新旧标题 → 重新人工审核 → 用户再次点击。任何自动修正都不等于用户已批准发表。
+
+## 6. 发布记录、去重与恢复
+
+建议独立 SQLite 发布任务库，与下载去重库分开；下载成功不能视为发布成功。本次先保存演示任务 JSON，尚未实现自动数据库或网站历史帖子同步。
+
+稳定文章身份优先采用下载器原始文章 ID 或规范化源 URL，同时保存正文与图片内容指纹用于发现重新下载/改名副本。禁止只按本地目录名、截断标题或当前账号去重。默认整个站点跨账号、跨版块不重复发表同一篇；如以后需要重发，必须由用户显式决定。
+
+建议字段：article_key、source_url/source_id、content_hash、原始/最终标题、目录、来源、状态、账号 UID、fid、附件映射、排版版本、人工提交时间、提交尝试编号、帖子 ID/URL、网站受理/审核/公开状态、错误、创建和更新时间。日志不保存密码、Cookie 或上传凭证。
+
+主状态：
+
+```text
+downloaded → queued → importing → formatting → awaiting_user_review
+  → user_submitting → published / accepted_pending_moderation
+```
+
+分支：`stopped`、`needs_attention`、`submit_unknown`、`rejected`。未决提交不得重新上传或领取同一文章。单批次串行，跨标签领取加持久锁；刷新后先恢复状态，不自动启动。
+
+去重记录需要覆盖用户已发表帖子：优先导入原有记录，或从“修改/删除信息”进入本人帖子列表进行核对。仅标题相同只能标记疑似重复，不能据此自动认定是同一正文。本次未扫描历史帖子，后续批量运行前必须完成历史对账；本次文章已记为“网站已受理、审核中”，已有帖子 ID 与 URL，必须阻止重发；不能误写为等待用户点击，也不能写为审核通过。
+
+成功记录与计数使用同一个事务：帖子唯一键（站点+帖子 ID）防止页面刷新重复加一。先记录再返回首页。遇到网络超时、页面关闭或不明确提示，记录 `submit_unknown`，人工/页面核对后再决定，禁止自动重复发表。
+
+网站明确受理待审核时，记 `accepted_pending_moderation` 并锁住文章。本规范建议把明确受理计入账号本轮提交数量一次，另存公开发表数量；后续审核通过只改变公开状态，不再加本轮数量。本次已观察到网站审核中状态，因此本地记录明确受理数为 1、已确认公开数为 0；批量自动记账尚未实现。驳回不自动补发或重投。
+
+## 7. 每个账号随机篇数与换号
+
+用户填写整数 `min`、`max`，要求 `1 ≤ min ≤ max`。首次为当前账号创建发布批次及每次确认换号成功后，从闭区间 `[min,max]` 均匀抽取整数 n，保存目标和当前计数。min=max 时固定该数量。不要按每篇重新抽 n，刷新、暂停或重启也不重抽。
+
+- 本轮计数只含当前发布批次明确成功/明确受理的唯一文章，不含上传、排版、等待人工审核、失败和结果不明。
+- 达到 n 后先保存记录与 `switch_pending`，回首页，核对没有待提交草稿，再点击“登陆下一帐号”。
+- 观察并确认实际 UID/用户名变化且登录成功，再建立下一账号批次、重置批次计数并抽新 n。不可在不确定结果时重复点击换号。
+- 验证码、账号异常、频率限制、登录失败或账号池无可用账号时暂停，保留当前文章与计数；不把受限文章换账号重投。
+- 用户手动改变账号时立即暂停，重新关联批次与上传附件；不能沿用旧账号附件上下文。
+- 队列已经处理完时直接结束，不为“凑满 n”重复文章，也不无意义换号。
+
+本次没有给定 min/max，所以不随机设置目标，也不执行换号。账号扩展现有自己的抽号/登录持久记录，应复用其登录流程，不另存账号密码。
+
+## 8. 常驻终止按钮的实现要求
+
+按钮在首页、分区页、新帖页、结果页、换号页面保持可见，不依赖折叠的导入面板。跨标签共享同一批次停止状态，导航后先恢复按钮和停止状态再执行任务。
+
+点击立即写入持久 `stopped` 并提升运行版本号，取消定时器、队列和可取消的上传/下载请求；每个异步步骤返回时检查停止标志和版本，过期回调不得再填写、跳转或换号。浏览器自带模态弹窗会阻挡网页按钮，因此自动流程应把来源/审核提示改成页面内面板，保留停止入口。
+
+已被服务器接收的图片/帖子不能被停止按钮撤回。停止后允许被动记录已在途请求的最终结果，但不得继续业务动作；需要清楚显示“已停止，已发出的请求可能仍已完成”。人工终止后必须由用户明确重新启动，不能因刷新或服务重启自动恢复。
+
+## 9. 后续实现与验收清单
+
+1. 优先实现常驻终止按钮、持久队列、站点级去重和历史发布对账，再接批量导入。
+2. 改造导入前标题截断、唯一来源尾注和可重复执行排版；保留原文与本地文件。
+3. 建立本地任务服务与浏览器执行器之间的配对通信，只传当前文章所需数据，不传下载 API Key 或账号库。
+4. 人工发布边界验收：没有用户点击时，等待任意时间都不会发表；标题修正后仍等待新的用户点击。
+5. 验证缺图、上传部分失败、重复来源、长标题、emoji、多 Markdown、非空编辑器、人工修改、刷新/断网、多标签竞争。
+6. 用户实际发布后，补录成功页或审核中页面证据、帖子 URL/ID，并验证重复打开不会增加计数。
+7. 给定 min/max 后验证 n 范围、每账号仅抽一次、达到目标换号、核对新 UID、恢复不丢计数。
+8. 在下载、上传、排版、等待审核、观察结果和换号各阶段点击终止，确认不再触发后续动作。
+
+## 10. 当前交接
+
+用户已亲手点击发表。原编辑器标签现为帖子详情页，标题与作者“示例用户”一致，面包屑为理财财经，显示“审核中”。已保存主题 ID、首帖 PID、URL、受理数量与去重记录，禁止再次发同一文章。登记后已点击网站首页入口，并核对 URL 为 `https://www.dww11.com/`，当前账号仍为示例用户（UID <已匿名>）；没有设置 min/max，因此未换号。
+
+发布结果检查发现正文内有 21 张图片，另外 5 张在附件区：image009.jpg、image014.jpg、image016.jpg、image025.jpg、image026.jpg，总数 26 张；来源尾注仅一条。发布后的正文与初次待审稿存在差异（例如原发布时间及“打开网易新闻 查看精彩图片”文字已不在结果正文中）。本次未记录用户审核期间的具体编辑动作，无法将差异归因于用户修改、编辑器同步或网站转换；后续需在用户点击的时刻保存最终待提交快照，再与结果对照。不得自动编辑或重发这篇已受理的帖子。
+
+截图：`test/history/周星驰文章_待人工审核.jpg`（历史待审稿）、`test/history/周星驰文章_网站审核中.jpg`（网站受理结果）。演示任务：`test/history/演示任务记录.json`；站点级去重登记：`发布去重记录.json`。记录保存本次结果，不代表完整历史同步或批量程序已经实现。
+
+
+## 11. 发布结果判断与本次补录
+
+- 用户点击后，不按“回到首页”判断成功；先记录实际跳转 URL 和页面结果。
+- 本次 URL 为 `/thread/23697411.html`，页面标题、理财财经面包屑、楼主示例用户及“审核中”共同确认网站已受理。DOM 首帖容器为 `#postmessage_238766`。
+- 网站审核中并非失败，不能为追求公开状态而再次提交；也不能仅凭当前登录用户能看到详情，宣称所有访客可见。
+- 刷新、重复读取或后来审核通过时，都用站点+主题 ID 保证受理数量只计一次。
+- 本次没有出现标题超限，相关处理仍是待验证需求。
+- 完整历史对账、常驻终止按钮、随机数量和自动换号仍属后续实现及验收范围。
diff --git a/实施计划.md b/实施计划.md
new file mode 100644
index 0000000..60d719a
--- /dev/null
+++ b/实施计划.md
@@ -0,0 +1,178 @@
+# 新闻下载、导入排版、人工发表与换号实施计划
+
+本文中的帐号名称和用户编号已匿名化；真实记录保存在本地排除目录中。帖子编号仍用于说明既有受理证据，不代表当前公开状态。
+
+更新日期：2026-10-31（北京时间）。本版整体替换早期自动发帖设想，依据当前源码、[发布流程操作记录与自动化规范](发布流程操作记录与自动化规范.md)、[演示任务记录](演示任务记录.json)和[发布去重记录](发布去重记录.json)重新梳理。
+
+本次进行了本地源码与记录核对，未重新操作线上页面、下载新闻、上传图片或发表帖子。下文“演示已验证”引用既有操作记录；“源码已有”不等于最新版本已在线上重新验收。
+
+## 1. 当前目标与确定规则
+
+目标是：自动下载、选文、上传、填写、排版和校验，等待用户亲手发表，然后观察结果、记录数量，达到账号目标后换号，继续下一篇。
+
+- **发表及重试发表必须由用户亲手点击。** 不模拟点击、不调用提交函数、不直接发送发帖请求、不通过快捷键提交。自动化没有发布接口。
+- 用户选择分区、文章根目录、处理范围及每账号篇数 min/max；理财财经 fid=125 是演示样例，不硬编码为全部任务的目标。
+- 标题、正文或来源修改后重新进入人工审核；等待审核期间自动化不继续修改编辑器。
+- 全流程常驻“终止流程”按钮，跨标签、导航和换号保持生效；停止后不因刷新或服务重启自动恢复。
+- 同一文章在整个站点跨账号、跨版块去重。已公开发表或已受理待审核均阻止再次入队；结果不明时先核对。
+- 新下载文章不额外插入接口发布时间和分隔线。历史文件及源正文中原有的时间、文字不因此自动删除。
+
+结论：工作流可行，单篇人工链路已有实机记录，但持久队列、本地桥接、统一终止、自动计数和与换号扩展联动仍需实现。实施重点从“寻找全部页面元素”转为“连接已有组件并保证停止、审核、去重和结果核对”。
+
+## 2. 本轮变化与现状
+
+| 模块 | 当前确认 | 后续工作 |
+| --- | --- | --- |
+| 排版脚本 `dww11-wechat-oneclick.user.js` v1.0.9 | 新增独立“一键排版”；`existingSource()` 识别文末来源/作者及版权行；`runFormat()` 取出原尾注后交给 `formatBody()` 重新排版；无来源才弹窗补充 | 提供可等待、可取消、无模态弹窗的程序接口；验证复杂尾注与编辑器转换后重复执行 |
+| 下载保存 `article_writer.py` | 标题后直接接正文；不再插入接口 time；移除无文字且无图片的空标题节点；末尾仍生成标准来源尾注 | 输出持久文章清单与结构化来源/源网址/指纹，建立完整保存后的入队衔接 |
+| 下载调度 `app.py` | 频道、分页、下载去重、进度、停止；历史库仍只有指纹到目录映射；状态接口含汇总、日志、输出目录 | 独立发布队列、每篇完成登记、重启对账；不能拿日志当可靠文章队列 |
+| 导入器 v1.0.0 | `stagePackage()`、`importPrepared()`、附件上传及登记、编辑器填写校验 | 接入取消信号、无弹窗冲突状态、持久恢复；导入前处理长标题 |
+| `dww11_make_package.py` | 已能生成 v1 Markdown/base64 图片包 | 包大小限制、当前任务按需传输、引用完整性校验 |
+| 换号扩展 v3.0.4 | 自有账号库、抽号、登录、暂停与持久流程；下一账号按钮已有 ID | 接收统一终止、输出可核对的换号结果，与发文批次计数协调；不能假定网站脚本能直接调用扩展内部路由 |
+| `auto_news_upload/` | 操作规范和两份 JSON 记录已存在 | 尚无完整自动执行程序或 SQLite 发布任务库 |
+
+新版排版的“保留来源”指保留识别到的尾注文字；内部会规范化空白并重建为纯文本格式节点，不保证原 HTML、链接或空格逐字不变。自动化应展示提取结果，疑似误识别时暂停。
+
+旧操作记录中“每次输入来源”和“排版后手工删除重复来源”属于当时演示行为。当前 v1.0.9 的独立排版入口已针对已有来源提供处理，不能再把这一功能整体列为未实现；仍需回归验证。微信 URL 采集入口仍走另一条流程，本项目只接独立排版逻辑。
+
+下载器测试文件已含不插入发布时间的断言，本次未重跑测试。新下载文件的时间格式已明确，不再列为待确认项；这不授权清理历史稿件。
+
+## 3. 已有实机证据与尚未解决的问题
+
+既有演示记录：账号示例用户（UID <已匿名>），理财财经 fid=125，文章“刚靠新电影赚23亿票房，周星驰就卖掉内地影院”，来源“洲洲影视娱评”。用户亲手发表后，网站返回主题 23697411、首帖 PID 238766，记录时显示审核中。
+
+- 已明确受理 1 篇；已确认公开 0 篇。不得根据旧记录推断现在已审核通过，也不得重发这篇文章。
+- 导入阶段编辑器有 26 张图片；结果页正文 21 张、附件区 5 张。总数齐全不能证明正文位置和顺序正确。
+- 附件区图片为 image009.jpg、image014.jpg、image016.jpg、image025.jpg、image026.jpg。需要以附件 ID 与正文引用逐一对照，不只比较文件名或总数量。
+- 结果正文与待审稿有文字差异；记录未覆盖用户审核期间编辑动作，不能归因于网站转换或用户操作。
+- 本次未重新读取线上结果页；原演示未验证审核后的访客可见性、超长标题报错、随机数量与换号链路。
+
+后续准备完成时保存基线快照，用户亲手点击时再捕获最终标题、编辑器正文、图片引用和附件映射，记录内容修订号与提交尝试。持久化可能来不及完成时要能识别缺失证据；不能为补记状态而代替用户重新提交。发布后分别检查受理状态与内容完整性，内容异常只标记待处理，不自动编辑或重发。
+
+## 4. 目标工作流与架构
+
+```text
+用户设置分区、根目录、处理范围、min/max
+  → 初始化终止按钮与持久批次
+  → 历史去重对账
+  → 已完整下载文章校验 / 持续接收新文章
+  → 单篇领取与文章包准备
+  → 确认新帖标签、账号、分区
+  → stagePackage → importPrepared
+  → 独立一键排版 → 标题/正文/图片/尾注检查
+  → 等待人工审核与用户亲手点击发表
+  → 只观察提交结果
+  → 原子登记受理记录、去重与本轮计数
+  → 回首页并核对
+  → 未达目标：下一篇；达到目标且仍有任务：换号并核对
+  → 队列结束：结束批次
+```
+
+建议继续采用“本地 Python 任务服务 + 浏览器执行器 + 网站适配层”，复用导入器与换号扩展。第一步验证油猴特权请求与回环服务通信；若目标浏览器不兼容，再改为扩展桥接，不同时维护多套主链路。
+
+本地服务仅监听回环地址，使用配对凭据和限定接口；只向网站传当前文章内容，不传下载 API Key 或账号库。不能把现有下载器 `/api/session` 直接当作对任意网页开放的任务授权入口。导入器是 `@grant none`，排版器有特权权限，必须实测页面与脚本隔离上下文间的调用，不能简单假定合并后仍可访问原来的 `window` 对象。
+
+文件传递优先复用文章包，不依赖自动操作系统目录选择器。原生选择器可作为人工导入备选。同一版块的点击可能打开新标签，任务必须绑定实际标签及导航版本，不能在旧分区页继续执行。
+
+电脑、本地服务及浏览器需保持运行；没有新增定时无人值守发表需求。发布始终需要用户点击。新任务的下载 Key 仍按现有方式在内存中使用，不默认落盘。
+
+## 5. 数据接入、格式与来源
+
+### 完整落盘与元数据
+
+复用下载器现有保存及去重逻辑，新增每篇成功结果清单，至少保存稳定身份候选、原始标题、来源、源 URL、目录、Markdown 路径、图片清单和校验值。新发布记录写入失败时可通过清单对账补录，不应为回滚发布登记而删除完整文章。
+
+当前保存器先创建最终目录，再逐个移动文件，扫描到目录并不代表下载结束。新下载采用成功回调/完成标记与清单协调入队；旧目录在确认非保存中且引用完整后显式导入。下载历史库失败时原下载器自有清理行为，与未来发布登记失败处理分开。
+
+### 标题
+
+保留 `original_title`，派生 `submitted_title`。超过 80 字符时按允许的计数预算截取前缀并追加字面量 `...`，不能截断 emoji 代理对；站点实际按码点、UTF-16 或字节计数仍需实测。当前页面曾读到 maxLength=-1，“还可输入80个字符”也未随填入更新，不能作为可靠校验。
+
+截断必须发生在导入器 `compile()` 之前。现有 `preparePackage()` 已接受 `data.title`，可以由适配层提供派生标题，不改原 Markdown；现有打包器本身尚未生成这个覆盖值。显示新旧标题并进入人工审核。若人工提交后收到明确超限拒绝，修正后仍由用户再次点击；结果不明时不改稿重投。
+
+### 来源与正文
+
+复用 v1.0.9 的 `existingSource()` 与 `formatBody()`，保留 4 号黑色正文、1 号银色尾注、图文间隔及图片适配。识别末尾来源时保留整段来源/版权文字，不只抽出名称再拼回默认句子。没有来源则在页面内要求补充，不能让原生 prompt 阻挡终止按钮。
+
+需要验证：标准下载尾注、多行版权说明、重复尾注、正文中出现“来源”、来源后有图片、嵌套 FONT、纯文本换行、编辑器来回切换、重复排版。不得全局删除正文中的来源文字；原稿本身已有多条来源时应提示核对，而非宣称新函数能语义去重。
+
+正文清理只沿用已确认规则；不自动删除历史发布时间、“打开网易新闻 查看精彩图片”等文字。下载器新生成格式与旧文件格式并存，文章身份不能仅靠整个 Markdown 的精确哈希判断。
+
+### 图片与编辑器
+
+下载器支持 WebP/AVIF/SVG，打包器和导入器仍只支持 JPG/JPEG/PNG/GIF。先在入队前拦截不兼容格式，不能等打包时静默漏掉；如后续增加转码，生成派生副本并重写引用，保留原文件。上传大小同时遵守导入器 20 MB 和网站当前限制。
+
+校验顺序为：本地引用完整 → 上传附件返回编号 → 网站附件登记 → BBCode/可视化图片关联 → 排版前后附件引用保持 → 人工提交时最终快照 → 结果页正文与附件区对照。现有缓存仅在页面内有效，持久复用必须绑定账号与上传上下文并重新验证。
+
+遇到旧稿恢复提示、非空编辑器或上传期间人工修改，暂停并保留现场。导入器现有 confirm 弹窗需要转换为页面内状态；不能自动确认覆盖。
+
+## 6. 持久状态、发布去重与观察
+
+独立 SQLite 任务库与下载历史库分开。启动前先迁入两份现有 JSON 的已受理记录，保证主题 23697411 不再入队；保留原 JSON 作为证据。再核对原有发布记录或本人历史帖子列表。标题相同只标记疑似重复，不能据此确认同一正文。完整历史对账尚未完成，不能把这一个样本当全量历史。
+
+稳定身份优先关联原始文章 ID/规范化源 URL，同时保存正文与图片指纹、文件版本哈希和身份别名。当前下载历史只有指纹与目录，原始 URL/来源并未形成完整持久清单；历史稿无法恢复的信息要标为未知，不能猜造。跨账号、跨版块去重，改名、标题截断、删除后重新下载均不改变已受理身份。
+
+建议记录：article_key、身份别名、source_url/source_id、内容及图片指纹、原始/提交标题、来源尾注、目录、账号 UID、fid、附件映射、排版版本、内容修订号、任务状态、批次 ID、领取租约/执行版本、尝试 ID、用户点击时间、最终快照、帖子 ID/URL、受理/审核/公开状态和错误。
+
+```text
+downloaded → queued → importing → formatting → awaiting_user_review
+  → user_submitting → published / accepted_pending_moderation
+```
+
+异常分支为 `needs_attention`、`submit_unknown`、`rejected`、`stopped`。其中 `published` 仅在有公开发表证据时使用；提交意图或点击事件不是网站受理证据。人工修改后记录新修订，继续等待人工审核。
+
+- 自动化只监听用户操作及网站结果，不主动触发提交。点击前预登记候选尝试，点击时关联最终快照；即使快照写入失败，也不能自动补交。
+- 结果需综合帖子 ID/URL、作者、分区、标题和受理/审核提示；跳转到首页、HTTP 200 或按钮变灰均不能单独证明成功。
+- 以“站点+帖子 ID”唯一键登记受理记录，并在同一事务更新去重与批次计数。重复打开、刷新及后续审核通过不重复加一。
+- 审核中计入明确受理数一次，公开数量另记；驳回不自动补发。结果页内容异常单独记录，不撤销受理去重。
+- 网络中断、关闭标签或证据不足进入 `submit_unknown`，先对账；租约过期也不能重投未决文章。
+- 多标签单篇互斥；刷新或服务重启先显示恢复状态，等待用户明确继续。已停止批次不得自动恢复。
+
+## 7. 账号目标与统一终止
+
+用户填写整数 `1 ≤ min ≤ max`。首次建立当前账号批次、以及确认换号成功后，从闭区间均匀抽取目标 n 并持久化。每账号批次只抽一次；暂停、刷新和重启不重抽。没有 min/max 时不能擅自设值或启动自动换号。
+
+本轮只计明确受理的唯一文章，导入、排版、等待审核、失败和结果不明不计。达到 n 后，先完成记账，确认没有未决提交，回首页并核对，再触发现有“登陆下一帐号”。核对扩展流程结束和实际账号 UID/用户名；无法确认时暂停，不连续点换号。账号池只有一个可用账号等导致 UID 未变化时不能假装换号成功，应显示原因等待处理。
+
+队列空时结束，不为凑数重发，也不无意义换号。账号手动变化、验证码、限制或登录异常时暂停，不带着旧附件上下文继续。账号密码继续由现有扩展管理。
+
+统一终止必须覆盖首页、分区页、新帖页、结果页和换号页面。点击先持久写入 stopped 并更新执行版本；立即禁止新领取、下一张上传、排版写入、跳转和换号，取消可取消请求。所有异步返回重新检查停止状态，过期回调不得继续。
+
+**现有组件的停止并不贯通：** 下载器停止是等待当前请求/保存结束；导入器没有对外取消接口；换号扩展有独立流程；排版仍使用模态弹窗。仅在外层增加按钮不能满足全流程终止。需要给这些模块增加取消/暂停衔接，尤其要在扩展开始退出/登录前以及后续各步骤检查共享停止状态。不能把扩展内部消息接口当作已公开的油猴 API。
+
+停止不撤回已经发出的请求，允许被动核对其最终结果，但不继续业务动作。原演示使用浏览器控制条停止的例外不延续至正式实现。
+
+## 8. 页面适配依据与剩余信息
+
+| 环节 | 已有依据 | 仍需核对 |
+| --- | --- | --- |
+| 分区入口 | `/special/post/`；演示选择后新开标签 | 用户实际目标分区及各区必填项，不固定 fid=125 |
+| 当前账号 | `#mumucms_username`，用户名/用户链接编号 | 登录失效与换号成功的稳定判定 |
+| 标题/正文 | `#subject`、`#e_textarea`、`#e_iframe`、`#e_switchercheck` | 当前网站编辑器同步与标题计数 |
+| 导入 | `window.DWW11Importer`，面板在 Shadow DOM | 实际浏览器中程序接口与停止信号 |
+| 排版 | `#dww11-format-oneclick` | v1.0.9 来源识别与发布后往返结果；目前没有公开排版 API |
+| 发表 | `#postsubmit`、`#postform` | 只观察人工操作；失败、超限、审核及成功提示适配 |
+| 受理结果 | `/thread/23697411.html`；样本首帖 `#postmessage_238766` | 从当前结果提取动态帖子 ID/PID，不硬编码样本 |
+| 换号 | `#dww11-extension-next` | 扩展完成/暂停状态及全局终止联动 |
+| 历史对账 | “修改/删除信息”进入本人帖子列表 | 列表 URL、分页、审核项与重复证据 |
+
+无需重新提供已记录的完整单篇演示。下一批所需输入主要是：实际分区与文章范围、min/max、其他版块必填项、历史帖子入口及异常提示样本。标题计数、5 张图片落到附件区的原因、审核后的公开状态需要针对性验证。不需要密码、Cookie 或 API Key 值进入文档。
+
+## 9. 实施顺序与验收
+
+| 阶段 | 工作 | 完成条件 |
+| --- | --- | --- |
+| 1：基础状态与停止 | 独立任务库、现有 JSON 迁入、历史对账、统一终止状态和常驻按钮；确定各组件取消协议 | 已受理样本不可重入队；跨标签互斥；刷新不自动运行；停止后无后续动作 |
+| 2：文章衔接 | 完整落盘清单、文章身份、包传输、图片检查、导入前标题派生、本地配对通信 | 新旧格式均可处理；半成品不入队；长标题不改原稿；缺图和不兼容格式明确报错 |
+| 3：排版与人工审核 | 封装 v1.0.9 独立排版接口，替换模态提示，接入导入取消和编辑冲突检查 | 尾注文字保留、标准来源只出现一次；反复排版及编辑器转换无累积问题；附件引用与顺序不变 |
+| 4：人工提交观察 | 提交快照、动态结果解析、审核/公开区分、唯一受理计数、正文与附件核对 | 不经用户点击永不发表；用户修改后重新审核；刷新不重复计数；结果不明不重投；定位图片落附件区问题 |
+| 5：批次与换号 | min/max 持久目标、记账后回首页、复用登录流程、账号核对、终止联动 | 每批仅抽一次目标；达到目标且队列非空才换号；异常不连续换号；无旧账号附件串用 |
+| 6：小批实机验收 | 覆盖故障恢复与多个页面场景 | 下载/上传/排版/待审/结果/换号各阶段终止均有效；断网、重启、多标签和人工改稿状态正确 |
+
+重点回归场景：普通/多图/重复图片、空标题节点、多行尾注、来源后图片、重复排版、长标题与 emoji、非空编辑器、旧稿恢复、部分上传失败、上传超时、用户提交后响应丢失、审核中、驳回和换号中终止。先模拟验证，再做用户亲手提交的少量实机验收；不以已受理样本重发来测试。
+
+## 10. 目录与本次交付范围
+
+新实现仍放在 `auto_news_upload/`，后续规划为 `service/`、`browser/`、`tests/`、`data/` 和启动说明；当前这些实现尚未建立。保留原下载目录、原历史库及现有演示记录。复用源码时记录版本，明确安装时启用的脚本组合，避免重复工具争用编辑器。
+
+本次仅重写本实施计划，未修改业务脚本和历史记录。历史操作规范用于追溯当时实机行为；当前组件能力以本轮核对的源码为准，人工发表、去重、终止和换号规则继续遵循操作规范。
diff --git a/流程检查与Git文件清单.md b/流程检查与Git文件清单.md
new file mode 100644
index 0000000..d01f8d5
--- /dev/null
+++ b/流程检查与Git文件清单.md
@@ -0,0 +1,150 @@
+# dww11 自动化流程检查与 Git 文件清单
+
+检查日期：2026-10-31（北京时间）。本轮仅检查本地说明、源码和离线测试；没有访问网站、消耗下载 API 额度、登录、上传或发表，最初检查时未执行 Git 操作。用户随后已确认仓库范围并授权本地初始化和首次提交；下面保留检查发现，并补充本次整理结果。
+
+## 一、检查结论
+
+当前是可以人工衔接的组件集合，尚不是已实现的端到端自动流程。
+
+```text
+探数 Key → 下载 Markdown 和图片
+  → 手工选择文章目录，或运行打包器生成文章包
+  → 已登录的论坛新帖页面导入并上传图片
+  → 点击独立“一键排版”并核对标题、正文、配图和来源
+  → 用户审核并亲手点击发表
+  → 核对受理/审核结果，登记去重，再决定下一篇或换号
+```
+
+发表与再次尝试发表均由用户亲手点击，这是现有流程规范要求。下载器、打包器、导入器、排版器和换号扩展之间没有完整的任务调度连接。
+
+## 二、逐环节检查
+
+| 环节 | 主要文件 | 当前能力 | 缺口或注意事项 |
+| --- | --- | --- | --- |
+| 下载 | `tanshuapi_news_downloader/app.py`、`article_writer.py`、`static/` | 频道、分页、正文图片落盘、下载历史去重、进度和停止 | 下载历史仅保存指纹与目录，没有供发布队列可靠消费的完整文章清单和完成标记；停止需要等待当前请求/保存结束 |
+| 打包 | `dww11_make_package.py` | 将目录转换为 v1 Markdown/base64 图片包；可直接作为 Python 函数调用 | 不会自动把文章送进浏览器；仅收集 JPG/JPEG/PNG/GIF，没有完整的 Markdown 引用预检或整包大小上限 |
+| 导入 | `dww11-article-importer.user.js` | 选目录或文章包、预览、按正文引用上传、附件登记、填写校验与失败回滚 | 标题超过 80 个 Unicode 码点直接拒绝；没有对外取消接口；非空编辑器确认仍使用模态弹窗 |
+| 排版 | `dww11-wechat-oneclick.user.js` v1.0.9 | 独立“一键排版”，识别文末来源并重建尾注；无来源时要求补充 | 没有公开可等待/取消的排版接口，仍有 prompt/alert；复杂尾注、重复执行和发布后的图片位置仍需浏览器回归 |
+| 发布 | `auto_news_upload/` 两份流程文档和两份记录 JSON | 已有单篇人工操作的历史记录 | 本目录没有完整发布执行程序、持久任务库、自动受理计数、全量历史对账或统一终止功能 |
+| 换号 | `dww11-extension/` v3.0.4 | CSV 导入、扩展 IndexedDB 帐号库、抽号与登录、暂停恢复 | 未与文章任务的 min/max、受理计数和统一终止联动；扩展内部路由不能直接视作油猴接口 |
+
+### 优先处理的问题
+
+1. **图片格式衔接不一致。** 下载器可保存 WebP/AVIF/SVG，打包器和导入器只支持 JPG/JPEG/PNG/GIF。打包器会跳过不支持格式，导入时可能报缺图；应在打包/入队前给出明确错误，或另外实现保留原文件的转码。
+2. **长标题衔接未实现。** 规范要求保留原题并派生截断标题，现导入器却在编译时直接拒绝超过 80 字的标题。需在导入前生成并展示提交标题，站点真实计数方式仍需实测。
+3. **缺少可靠调度和统一终止。** 下载完成不等于可以发布；目录存在也不等于完整保存。现有模块停止行为不贯通，不能直接启动无人看管的批量链路。
+4. **发布去重仍是手工记录。** 下载去重不能替代跨帐号、跨版块的发布去重。需要持久队列、未决结果核对、唯一受理登记及恢复逻辑。
+5. **历史样本的图片位置有异常。** 原记录显示 26 张图片中正文 21 张、附件区 5 张，总数相同不能证明位置正确。应按附件 ID 对照最终待提交快照与结果页。
+6. **旧路径已整理。** 原导入测试与打包说明引用了搬迁前目录；首次提交准备时改用 `tests/fixtures/article/` 的自造 Markdown 和 PNG，消除 legacy 依赖。
+7. **扩展测试资料缺失。** 扩展 README 提到 `tests/core.test.mjs`、`tests/browser-integration.mjs`、`tests/browser-restart.mjs` 和 `测试说明.md`，当前项目中未找到，不能把文档中的历史测试声明当成本轮复验结果。
+
+历史记录中的主题 23697411 已被网站受理并显示审核中，必须保留其本地去重证据。本轮没有核实现在是否已经公开。
+
+## 三、运行时需要帐号或凭据的文件
+
+下表区分“程序需要凭据才能运行”和“源码里保存真实凭据”。程序需要登录不代表源码不能进入 Git。
+
+| 文件 | 所需帐号/凭据 | 使用和保存方式 | Git 建议 |
+| --- | --- | --- | --- |
+| `tanshuapi_news_downloader/app.py` | 探数 API Key | 调用新闻 API；Key 从页面传入，在运行内存使用 | 源码可纳入；不写入真实 Key |
+| `tanshuapi_news_downloader/static/app.js`、`static/index.html` | 用户填写探数 API Key | 页面输入和内存变量，经本机会话接口传给服务；源码未配置固定 Key | 可纳入 |
+| `dww11-article-importer.user.js` | 已登录的大湾网帐号及页面上传凭据 | 从当前页面读取上传参数，使用当前登录会话上传图片；无须写入密码 | 可纳入源码 |
+| `dww11-wechat-oneclick.user.js` | 发布页面的登录会话 | 独立排版入口在当前编辑器操作；微信 URL 入口属于另一条采集路径 | 可纳入源码 |
+| `dww11-extension/manager.js`、`manager.html`、`core.js` | 帐号 CSV | 选择、解析、确认导入帐号和密码 | 可纳入程序及虚拟模板，排除真实 CSV |
+| `dww11-extension/db.js`、`service.js` | 扩展帐号库 | 明文密码保存在浏览器扩展来源的 IndexedDB；列表返回时去除密码 | 可纳入程序；排除浏览器资料及数据库备份 |
+| `dww11-extension/background.js`、`content.js` | 当前抽取的帐号和密码 | 扩展消息传递，并填入目标网站登录表单 | 可纳入程序 |
+| `today-jobs.user.js` | 可访问招聘管理列表的登录帐号/权限 | 使用当前页面和同源会话读取职位 | 辅助功能，按需纳入 |
+| `dww-today-threads.user.js` | 论坛后台管理权限与页面 formhash | 使用当前管理会话执行统计查询 | 辅助功能，按需纳入 |
+| `legacy/acc_switch_lite_python_legacy/server.py`、两个 lite 目录的 `import_excel.py` 与换号油猴脚本 | 旧版帐号文件、Excel 和网站登录 | 旧版实现；与当前扩展分开 | 不属于当前主链路；归档时排除真实数据 |
+| `legacy/acc_switch_heavy_sqlite_legacy/init_db.py`、`import_excel.py` | 旧版帐号 Excel/数据库 | 可生成并导入保存密码的 `accounts.db` | 不属于当前主链路；数据库不纳入 |
+
+`dww11_make_package.py` 仅处理本地文件，不需要帐号、API Key 或网站 Cookie。
+
+## 四、已经存在的帐号数据文件：排除真实版本
+
+| 文件 | 本轮确认 | 建议 |
+| --- | --- | --- |
+| `账号密码-去重可导入.csv` | 表头外 1152 条数据行、3 列；为真实帐号导入文件 | 本地保留，不纳入 Git |
+| `legacy/acc_switch_lite/accounts.json` | 169 条帐号记录，169 个非空 password 字段 | 本地保留，不纳入 Git |
+| `legacy/acc_switch_lite_python_legacy/accounts.json` | 169 条帐号记录，169 个非空 password 字段 | 本地保留，不纳入 Git |
+
+以上仅统计结构和数量，不展示用户名、密码或密钥。没有执行帐号有效性验证，也没有核对 CSV 行与 JSON 记录之间的对应关系。
+
+当前扩展运行帐号库在浏览器内，不在 `dww11-extension/` 源码目录。不要把浏览器配置目录、Cookie 导出文件或 IndexedDB 备份作为源码提交。`example.csv` 是示例模板，需保持为虚拟凭据。
+
+## 五、拟纳入 Git 的文件清单
+
+### A. 当前主链路源码与说明
+
+```text
+dww11_make_package.py
+dww11-article-importer.user.js
+dww11-wechat-oneclick.user.js
+本地文章导入脚本使用说明.md
+tanshuapi_news_downloader/app.py
+tanshuapi_news_downloader/article_writer.py
+tanshuapi_news_downloader/requirements.txt
+tanshuapi_news_downloader/start.command
+tanshuapi_news_downloader/README.md
+tanshuapi_news_downloader/.gitignore
+tanshuapi_news_downloader/static/index.html
+tanshuapi_news_downloader/static/app.js
+tanshuapi_news_downloader/static/style.css
+tanshuapi_news_downloader/tests/test_downloader.py
+dww11-extension/manifest.json
+dww11-extension/background.js
+dww11-extension/content.js
+dww11-extension/core.js
+dww11-extension/db.js
+dww11-extension/service.js
+dww11-extension/manager.html
+dww11-extension/manager.js
+dww11-extension/manager.css
+dww11-extension/example.csv
+dww11-extension/README.md
+auto_news_upload/实施计划.md
+auto_news_upload/发布流程操作记录与自动化规范.md
+auto_news_upload/流程检查与Git文件清单.md
+```
+
+两份流程文档的帐号名称、UID 和电脑绝对路径已匿名化，原版保存在被排除的 `auto_news_upload/local-records/`。历史帖子编号与链接保留为受理证据说明。本文不含密码，但也引用了本地敏感文件名和数量，可按仓库公开范围进一步精简。
+
+### B. 修复或检查后再决定
+
+- `test-dww11-importer.cjs`：已改用仓库内自造测试稿与三张 PNG，一并纳入首次提交。
+- `auto_news_upload/演示任务记录.json`、`发布去重记录.json`：属于真实运行状态。建议保留本地，另提供匿名结构模板；不因 Git 排除而删除原去重记录。
+- `dww11-extension-3.0.4.zip`：本轮逐文件比对，与当前扩展目录的 11 个文件一致。可作为发行附件；日常优先跟踪源码，避免双份维护。
+- `today-jobs.user.js`、`dww-today-threads.user.js`：辅助工具，不是四步主流程的必需文件，按你的范围选择。
+- `.wechat-script-test/`：本地排版验证页、源码副本、截图和结果，需整理为可复现测试后再选择纳入。
+- `legacy/`：默认不进入主链路首批提交；若保留历史实现，必须逐项排除帐号数据、虚拟环境、缓存及下载文章。
+- `credits-video/`：滚动字幕视频工具，与本次流程无直接关系，默认不纳入本批。
+
+### C. 建议排除的本地产物
+
+真实帐号 CSV/JSON、下载文章及图片、下载历史数据库、真实发布记录与截图、文章包 `*.dww11.json`、浏览器配置和 Cookie、`.venv/`、`__pycache__/`、`*.pyc`、`.DS_Store`、视频输出和临时诊断文件。
+
+首次提交准备时已增加根目录 `.gitignore`，覆盖真实帐号、运行记录、下载目录及本批范围之外的组件；按白名单添加源码和说明。
+
+## 六、本轮验证结果
+
+| 检查 | 结果 |
+| --- | --- |
+| Git 状态 | 当前目录不是 Git 仓库；本轮没有新建仓库 |
+| 原始导入测试 `node --test test-dww11-importer.cjs` | 8 项中 3 项通过、5 项因旧素材目录不存在失败 |
+| 只在内存中修正素材路径后执行同一测试 | 8/8 通过，覆盖打包与直接导入一致、缺图/长标题拦截、上传失败保留原文、富文本丢图回滚、无发表请求；磁盘测试文件未修改 |
+| 下载器单元测试 | 默认 Python 3.15 与 Python 3.12 均因缺少 `requests` 无法加载测试；未安装依赖，不能认定通过或认定下载逻辑失败 |
+| JavaScript 语法 | 6 个扩展 JS 按 ES 模块检查通过；4 个根目录油猴脚本检查通过 |
+| Python 语法 | 打包器、下载器 app 与保存器均通过语法解析 |
+| 扩展 ZIP | 11 个文件与源码目录逐一一致 |
+| 在线验收 | 本轮未执行；历史文档中的单篇演示不等于当前版本全链路验收 |
+
+## 七、首次提交整理范围
+
+用户已授权新建本地仓库并完成 initial commit，范围为总流程文档、当前换号扩展、新闻下载器、文章打包/导入/排版及相关说明与测试。
+
+- 增加根目录 README 与 `.gitignore`。
+- 导入测试改用项目自有测试稿及三张程序生成的 PNG，修正打包说明路径。
+- 原始流程说明备份到本地排除目录，再匿名化仓库文档中的帐号名称、UID 与电脑路径。
+- 真实帐号、下载历史、演示 JSON、截图及原始说明均保留本地，不纳入提交。
+- 下载器测试仍需先安装依赖，扩展缺失的测试文件尚未补齐；不以首次提交表示全流程已经完成。
+- 本次只建立本地版本历史，未配置远程仓库或推送。