Individual skill
wxmp-article-harvester
抓取、筛选并导出微信公众号公开文章的独立 Skill。用户提到微信公众号、公众号文章、mp.weixin、wcx、搜索公众号、导出最近 N 天或某年度文章、批量抓取、断点续抓、正文补全、教程文章筛选、微信文章链接保存时使用。支持 Markdown/JSON/CSV，默认用 wcx 获取索引、Playwright 提取正文；付费 Metaso 兜底必须显式授权。
skills/wxmp-article-harvester/SKILL.md
Source commit d09cc28cd0915808534ea3bf199f17efa75553a6
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 10, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 786
- Repository last updated
- Nov 6, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- testing Derived category
- testing-browser Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 5,266 bytesSKILL.mdcore · 5,266 bytesSKILL.mdcore · 5,266 bytesSKILL.mdcore · 5,266 bytesagents/openai.yamlasset · 288 bytesevals/evals.jsonasset · 3,593 bytesreferences/troubleshooting.mddoc · 6,913 bytesscripts/browser_reader.pyruns · 10,576 bytesscripts/harvest_wxmp.pyruns · 61,501 bytesscripts/metaso_reader.pyruns · 6,328 bytesscripts/preflight.pyruns · 3,611 bytesscripts/refresh_token_playwright.pyruns · 4,124 bytesscripts/runtime_paths.pyruns · 5,213 bytesscripts/wcx_batch_fetch.pyruns · 6,212 bytesscripts/wcx_run.pyruns · 5,142 bytestests/test_harvester.pyruns · 14,970 bytes
Read excerpt
# wxmp-article-harvester
目标：把公开公众号文章稳定加工成可检索、可审计、可恢复的本地资料包。
## 运行架构
1. `preflight.py` 只检查依赖，不自动安装或升级任何软件。
2. `wcx_run.py` 搜索公众号、刷新登录态、抓元数据并导出索引。
3. `harvest_wxmp.py` 过滤日期和标题，复用一个 Playwright 上下文提取正文并保留图片顺序。
4. 首次命中微信验证码或风控页后打开浏览器熔断，停止本轮后续页面请求；刷新失败时保留已通过质量门的旧正文。
5. 没有可信正文时标记 `partial`。只有用户明确授权付费和第三方 URL 传输后，才加 `--allow-metaso`。
## 开始前
