Fetch articles and video content from URLs and convert them to Markdown.
npx skills add https://github.com/peachest/skills --skill fetch-article-peachest
Please help me install this Agent Skill. Skill: fetch-article Source: https://github.com/peachest/skills/tree/main/research/fetch-article Command: npx skills add https://github.com/peachest/skills --skill fetch-article-peachest
High-intent search queries and answers about installing and using this skill.
Run fetch.py with the mp.weixin.qq.com URL and the --json flag. The WeChat adapter uses curl with a MicroMessenger user agent and Referer header to get the server-rendered page, then converts it with markitdown and extracts metadata via beautifulsoup4.
The generic adapter uses a three-layer fallback: Scrapling CLI first, then curl with HTML stripping, then the r.jina.ai reader proxy which returns Cloudflare-protected pages as Markdown. Setting JINA_API_KEY avoids anonymous rate limits on the proxy.
No, the Bilibili adapter only downloads audio via the WBI-signed API or saves CC subtitles directly when available. For ASR transcription of the downloaded audio, use the separate bilibili-transcriber skill.
Yes, the YouTube adapter uses yt-dlp to fetch manual or auto subtitles first, deduplicating the VTT into plain text. Audio is only downloaded as a fallback when no subtitles exist, and https_proxy is honored for restricted networks.
WeChat returns a captcha page when your IP is rate-limited, or a JS shell page when the user agent is wrong. The adapter detects both conditions and fails loudly; retry later or use a headless-browser fetcher for that URL.
Core requirements are Python 3.10+, curl, markitdown, beautifulsoup4, and requests. Bilibili needs aria2c and optionally imageio-ffmpeg; YouTube needs yt-dlp; the generic adapter optionally uses Scrapling for anti-bot bypass.
NomaDamasSearch GeekNews RSS/Atom entries by keyword and inspect item details.
papachongSearch Brave Search headlessly and extract page content as markdown.
Animism001Transcribe Bilibili videos using CC subtitles, AI subtitles, or Whisper fallback.
RooseveltAdvisorsScrape websites and crawl multiple pages using progressive fetching and browser automation.
