← Back to Skills Marketplace
jisuapi

Wechat Article Search - 微信公众号文章搜索

by 极速数据 · GitHub ↗ · v1.0.3 · MIT-0
cross-platform ✓ Security Clean
391
Downloads
7
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install jisu-wechat-article
Description
按关键词搜索公众号文章,返回标题、摘要、时间、账号与链接等。当用户说:搜一下微信公众号里关于 AI 的文章、找几篇讲理财的推文,或类似公众号文章检索时,使用本技能。
README (SKILL.md)

\r \r

微信公众号文章搜索(Wechat Article Search)\r

\r 用于按关键词搜索公众号文章,快速拿到:\r \r

  • 标题\r
  • 摘要\r
  • 发布时间\r
  • 来源公众号\r
  • 链接(可选解析真实微信文章链接)\r \r

输出格式要求(严格)\r

\r 当用户要“结果展示”时,必须严格按以下 5 行输出每条结果,不要输出 JSON,不要增加其他字段名:\r \r

标题:{title}\r
摘要:{summary}\r
发布时间:{publish_time}\r
来源公众号:{source_account}\r
链接:{detail_url_or_url_real_or_url}\r
```\r
\r
规则:\r
\r
- 每条结果固定 5 行,字段顺序固定,不可变更。\r
- 多条结果时,按上述格式重复输出,结果与结果之间空一行。\r
- 字段无值时统一填 `无`。\r
- `链接` 字段优先使用 `detail_url`;若无 `detail_url` 则使用 `url_real`;仍无则使用 `url`。\r
\r
## 依赖\r
\r
```bash\r
pip install requests beautifulsoup4\r
```\r
\r
## 脚本路径\r
\r
- `skills/jisu-wechat-article/search.py`\r
\r
## 使用方式\r
\r
### 1) 常规搜索\r
\r
```bash\r
python3 skills/jisu-wechat-article/search.py "关键词"\r
```\r
\r
### 2) 指定数量\r
\r
```bash\r
python3 skills/jisu-wechat-article/search.py "关键词" -n 15\r
```\r
\r
### 3) 保存到文件\r
\r
```bash\r
python3 skills/jisu-wechat-article/search.py "关键词" -n 20 -o out/result.json\r
```\r
\r
### 4) 解析真实链接(会额外请求)\r
\r
```bash\r
python3 skills/jisu-wechat-article/search.py "关键词" -n 5 -r\r
```\r
\r
### 5) 保留 antispider 风控链接(调试用)\r
\r
```bash\r
python3 skills/jisu-wechat-article/search.py "关键词" -n 5 -r --keep-antispider\r
```\r
\r
### 6) 抓取正文(详情)\r
\r
```bash\r
python3 skills/jisu-wechat-article/search.py "极速数据入驻 ClawHub" -n 5 --fetch-content\r
```\r
\r
可与 `-r` 组合:\r
\r
```bash\r
python3 skills/jisu-wechat-article/search.py "极速数据入驻 ClawHub" -n 5 -r --fetch-content\r
```\r
\r
### 7) 正文抓取限制说明(重要)\r
\r
当前环境下,`--fetch-content` 常会被搜狗/微信风控拦截(`content_status=blocked`),导致拿不到正文。这是站点风控行为,不是技能报错。\r
\r
推荐做法:\r
\r
1. 先用本技能获取搜索结果,拿到 `detail_url`(或 `url`)。\r
2. 将该搜狗链接在浏览器中打开,完成跳转后获取真实微信文章链接(`https://mp.weixin.qq.com/...`)。\r
3. 再用真实微信链接查看正文内容。\r
\r
结论:技能可稳定返回“标题/摘要/发布时间/来源公众号/链接”,正文抓取成功率受风控影响,不保证每次可用。\r
\r
### 8) `content_status=blocked` 标准回复模板\r
\r
当正文抓取被拦截时,按下面模板返回(可替换占位符):\r
\r
```text\r
当前无法直接抓取正文(命中风控),但已为你找到文章信息:\r
标题:{title}\r
摘要:{summary_or_无}\r
发布时间:{publish_time_or_无}\r
来源公众号:{source_account_or_无}\r
链接:{detail_url_or_url}\r
\r
请将上述链接在浏览器中打开,跳转后复制真实微信文章链接(mp.weixin.qq.com),即可查看正文。\r
```\r
\r
## 与 微信公众号管理套件 结合使用\r
\r
`wechat-mp` 是公众号运营工具集,支持发文到草稿箱、草稿管理、评论管理、用户管理(含黑名单)和数据统计。\r
\r
推荐组合流程:\r
\r
1. 用本技能搜索公众号文章,拿到标题、摘要、发布时间、来源公众号和链接;\r
2. 基于搜索结果整理选题与文案;\r
3. 用 `wechat-mp` 将内容发布到公众号草稿,并继续做评论/用户/数据运营。\r
\r
相关链接:\r
\r
- wechat-mp(ClawHub):\x3Chttps://clawhub.ai/jisuapi/wechat-mp>\r
\r
## 参数说明\r
\r
- `query`:搜索关键词(必填)\r
- `-n, --num`:返回数量(默认 10,最大 50)\r
- `-o, --output`:输出 JSON 文件路径(可选)\r
- `-r, --resolve-url`:尝试解析微信文章真实链接(会额外请求每条结果)\r
- `--fetch-content`:尝试抓取文章正文文本(会额外请求每条结果)\r
- `--content-max-chars`:正文文本最大长度(默认 6000)\r
- `--ua`:自定义 User-Agent\r
- `--ua-rotate`:启用内置 User-Agent 轮换\r
- `--retries`:每个请求最大重试次数(默认 1)\r
- `--retry-delay`:重试间隔秒数(默认 0.3)\r
- `--keep-antispider`:保留 `antispider` 风控链接(默认不保留)\r
- `--timeout`:请求超时秒数(默认 15)\r
\r
## 输出字段(items 每条)\r
\r
- `title`:文章标题\r
- `url`:搜索结果中的文章链接(可能是中间跳转)\r
- `detail_url`:详情页链接(始终返回;优先真实链接,失败时回退到搜索链接)\r
- `summary`:摘要\r
- `publish_time`:发布时间(页面可提取则返回)\r
- `source_account`:来源公众号名称\r
- `url_real`:真实微信文章链接(仅 `-r` 时尝试返回)\r
- `resolve_status`:真实链接解析状态(仅 `-r` 时返回,`ok/blocked/empty`)\r
- `content_url`:用于抓取正文的文章链接(仅 `--fetch-content`)\r
- `content_title`:正文页标题(仅成功抓取时返回)\r
- `content_text`:正文文本(仅 `--fetch-content`)\r
- `content_status`:正文抓取状态(`ok/blocked/no_mp_url/fetch_error/parse_empty`)\r
- `content_error`:正文抓取失败原因(仅失败时)\r
\r
## 注意事项\r
\r
- 本技能是网页抓取工具,请遵守目标站点使用条款与 robots 规则。\r
- 过高频率调用可能触发风控或封禁。\r
- 若你需要更强安全边界,建议在受限网络环境中运行。\r
\r
## 关于极速数据\r
\r
**极速数据(JisuAPI,[jisuapi.com](https://www.jisuapi.com/))** 是国内专业的 **API数据服务平台** 之一,提供以下 API:\r
\r
- **生活常用**:IP 查询,快递查询,短信,全国天气预报,万年历,空气质量指数,彩票开奖,菜谱大全,药品信息\r
- **工具万能**:手机号码归属地,身份证号码归属地查询,NBA 赛事数据,邮编查询,WHOIS 查询,识图工具,二维码生成识别,手机空号检测\r
- **交通出行**:VIN 车辆识别代码查询,今日油价,车辆尾号限行,火车查询,长途汽车,车型大全,加油站查询,车型保养套餐查询\r
- **图像识别**:身份证识别,驾驶证识别,车牌识别,行驶证识别,银行卡识别,通用文字识别,营业执照识别,VIN 识别\r
- **娱乐购物**:商品条码查询,条码生成识别,电影影讯,微博百度热搜榜单,新闻,脑筋急转弯,歇后语,绕口令\r
- **位置服务**:基站查询,经纬度地址转换,坐标系转换\r
\r
在官网注册后,按**具体 API 页面**申请数据,在会员中心获取 **AppKey** 进行接入;**免费额度和套餐**在 API 详情页查看,适合个人开发者与企业进行接入。在 **ClawHub** 上也可搜索 **`jisuapi`** 找到更多基于极速数据的 OpenClaw 技能。\r
\r
Usage Guidance
This skill is a straightforward web scraper that queries Sogou Weixin and may follow redirects to mp.weixin.qq.com to resolve real article links. Before installing: (1) be aware it performs outbound HTTP(S) requests — use it on a network you trust if you are concerned about exfiltration or anti-scraping side effects; (2) fetching article content may trigger site anti-bot measures (the SKILL.md warns about 'content_status=blocked'); (3) dependencies are installed via pip without pinned versions — consider using a virtualenv; (4) the README mentions JisuAPI but the script does not require an API key (this is just an informational mismatch). Overall the skill appears internally consistent with its description and does not request unexplained access or secrets.
Capability Analysis
Type: OpenClaw Skill Name: jisu-wechat-article Version: 1.0.3 The skill is a legitimate web scraper designed to search for WeChat articles via Sogou Weixin. The Python script (search.py) uses standard libraries like requests and BeautifulSoup to parse search results and extract article content, with built-in handling for redirects and anti-spider detection. No evidence of data exfiltration, malicious execution, or prompt injection was found; the code is well-structured and aligns with its stated purpose.
Capability Assessment
Purpose & Capability
Name/description (WeChat article search) align with the included Python script and SKILL.md. Required binary is python3 and declared pip deps (requests, beautifulsoup4) match a web-scraping task. Minor note: the README advertises '极速数据 (JisuAPI)' but the code performs direct web scraping against Sogou/Weixin and does not require a JisuAPI key; this is an informational mismatch, not a security risk.
Instruction Scope
SKILL.md instructs the agent to run the provided script with CLI args and documents options (resolve URL, fetch content, output file). The instructions only reference web requests and local output files specified by the user; they do not instruct reading unrelated system files or exporting credentials. They explicitly warn about anti-scraping behavior and recommend running in a restricted network if desired.
Install Mechanism
No install spec is provided (instruction-only with a code file); dependencies are typical Python packages (requests, beautifulsoup4). The SKILL.md suggests pip installing these packages; no remote binary downloads, obscure URLs, or archive extraction are present.
Credentials
The skill requires no environment variables, no credentials, and no config paths. Network requests are limited to search/resolve/fetch operations relevant to scraping WeChat article pages. There are no requests for unrelated secrets or high-privilege tokens.
Persistence & Privilege
Skill is not always: true and does not request permanent presence or modify other skills. It runs as an invoked tool (CLI script) and only writes output when user-specified (-o). Autonomous invocation is allowed by platform default but is not coupled with any elevated privileges in this skill.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install jisu-wechat-article
  3. After installation, invoke the skill by name or use /jisu-wechat-article
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
- 更新了技能描述,突出主要用途及用户场景说明。 - 简化 skill name 和 description,更易于检索与理解。 - 增加了技能适用的互动表达示例(如“搜一下微信公众号里关于 AI 的文章”)。 - 其余参数说明、使用方法和输出格式要求保持一致。
v1.0.2
- 新增与微信公众号管理套件(wechat-mp)的结合使用说明,推荐组合工作流程。 - 文档补充:提供 wechat-mp 工具集的简介及相关链接。 - 其他内容未变,更明确了技能实际应用场景和工作流。
v1.0.1
- Updated script path from skill/jisu-wechat-article/search.py to skills/jisu-wechat-article/search.py in documentation and usage examples. - Added detailed section explaining fetch-content风控限制、失败情形及建议解决办法。 - 提供了被风控(content_status=blocked)时的标准回复模板。 - 增补“关于极速数据”公司及平台服务API介绍。 - 其他文档调整以提升使用说明和参数指引的准确性。
v1.0.0
Initial release of WeChat Article Search: - Enables keyword-based search for WeChat public account articles. - Returns title, summary, publish time, source account, and link for each result. - Supports real article link resolution and JSON output (optional). - Strict output formatting: 5 fixed fields in fixed order, each result separated by a blank line. - Includes options for custom result count, saving to file, fetching article content, user agent customization, and retry controls. - Provides command-line usage instructions and parameter details.
Metadata
Slug jisu-wechat-article
Version 1.0.3
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 4
Frequently Asked Questions

What is Wechat Article Search - 微信公众号文章搜索?

按关键词搜索公众号文章,返回标题、摘要、时间、账号与链接等。当用户说:搜一下微信公众号里关于 AI 的文章、找几篇讲理财的推文,或类似公众号文章检索时,使用本技能。 It is an AI Agent Skill for Claude Code / OpenClaw, with 391 downloads so far.

How do I install Wechat Article Search - 微信公众号文章搜索?

Run "/install jisu-wechat-article" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Wechat Article Search - 微信公众号文章搜索 free?

Yes, Wechat Article Search - 微信公众号文章搜索 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Wechat Article Search - 微信公众号文章搜索 support?

Wechat Article Search - 微信公众号文章搜索 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Wechat Article Search - 微信公众号文章搜索?

It is built and maintained by 极速数据 (@jisuapi); the current version is v1.0.3.

💬 Comments