Files
Agent-Reach/agent_reach/skill/references/web.md
T
Pnant f9b7241d47 feat(skill): refactor skill system with router + references structure (#192)
Refactors SKILL.md into a router + reference documentation system:
- Main SKILL.md now contains routing table and quick commands
- Detailed docs split into references/ (search, social, career, dev, web, video)
- CLI skill install copies entire directory including references/
- Resolves conflicts with recent merges (#210, #213)
- Fixes xreach→bird in quick commands

Original PR by @Citrus086, merged with conflict resolution.

Co-Authored-By: Citrus086 <Citrus086@users.noreply.github.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-31 11:21:33 +08:00

1.8 KiB

网页阅读

通用网页、微信公众号、RSS。

通用网页 (Jina Reader)

# 读取任意网页内容
curl -s "https://r.jina.ai/URL"

# 示例
curl -s "https://r.jina.ai/https://example.com/article"

适用场景: 大多数网页可以直接用 Jina Reader 读取。

Web Reader (MCP)

# 读取网页内容 (Markdown 格式)
mcporter call 'web-reader.webReader(url: "https://example.com")'

# 保留图片
mcporter call 'web-reader.webReader(url: "https://example.com", retain_images: true)'

# 纯文本格式
mcporter call 'web-reader.webReader(url: "https://example.com", return_format: "text")'

适用场景: 需要更精确控制输出格式时使用。

微信公众号 / WeChat Articles

注意: 微信公众号文章无法用 Jina Reader 或 curl 直接读取,必须使用专用工具。

搜索文章 (miku_ai)

python3 -c "
import asyncio
from miku_ai import get_wexin_article
async def s():
    for a in await get_wexin_article('query', 5):
        print(f'{a[\"title\"]} | {a[\"url\"]}')
asyncio.run(s())
"

读取文章 (Camoufox - 绕过微信反爬)

cd ~/.agent-reach/tools/wechat-article-for-ai && python3 main.py "https://mp.weixin.qq.com/s/ARTICLE_ID"

重要: 微信文章必须用 Camoufox 读取,其他方法会失败。

RSS (feedparser)

python3 -c "
import feedparser
for e in feedparser.parse('FEED_URL').entries[:5]:
    print(f'{e.title}{e.link}')
"

适用场景: 订阅博客、新闻源、播客等 RSS feed。

选择指南

场景 推荐工具
通用网页 Jina Reader (curl r.jina.ai)
需要图片/格式控制 web-reader MCP
微信公众号 Camoufox (读取) + miku_ai (搜索)
RSS 订阅 feedparser
微博/知乎等 Jina Reader