SkillAgentSearch skills...

gzh-search-crawler

公众号搜索爬虫 — 通过关键词搜索微信公众号文章,终端表格展示(标题/作者/阅读/点赞/分享/收藏/发布时间/文章链接),自动导出 CSV 并生成交互式 HTML 报告。当用户需要搜索、爬取或浏览公众号文章时使用;也适用于行业热点追踪、竞品内容分析、素材灵感搜集等场景。

Install / Use

npx skills add redfox-data/redfox-community --skill gzh-search

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

85/100

Supported Platforms

Universal

Our assessment of gzh-search-crawler

gzh-search-crawler scores 85/100 on our quality scale, 413th of 588 Data & Analytics skills we index.

Its SKILL.md is 3.3 KB long, well organised into 12 sections with 2 code examples: a solid amount of guidance for an agent.

It has 412 GitHub stars, a meaningful sign that others use it.

Substance
26/30
Structure
18/20
Description
15/15
Adoption
11/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 11 days ago, so gzh-search-crawler is actively maintained.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-05. Automated pattern scan on 2026-10-05. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

gzh-search-crawler compared with similar skills

All 4 of these similar skills score higher than gzh-search-crawler; compare them before choosing.

SkillScoreStarsUpdatedFormat
gzh-search-crawler (this skill)by redfox-data8541211d agoSKILL.md
Agent-Reachby Panniantong10091.8k20d agoCLAUDE.md
headroomby headroomlabs-ai10074.5ktodayCLAUDE.md
Scraplingby D4Vinci10085.8k1d agoMCP Server
crawl4aiby unclecode10084.8ktodayMCP Server

Frequently asked questions

How do I install gzh-search-crawler?
Run npx skills add redfox-data/redfox-community --skill gzh-search-crawler. The install tabs above show the steps for each supported agent.
Which AI agents does gzh-search-crawler work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is gzh-search-crawler safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is gzh-search-crawler still maintained?
The repository was last updated 11 days ago, so gzh-search-crawler is actively maintained.

name: gzh-search-crawler description: 公众号搜索爬虫 — 通过关键词搜索微信公众号文章,终端表格展示(标题/作者/阅读/点赞/分享/收藏/发布时间/文章链接),自动导出 CSV 并生成交互式 HTML 报告。当用户需要搜索、爬取或浏览公众号文章时使用;也适用于行业热点追踪、竞品内容分析、素材灵感搜集等场景。

公众号搜索爬虫

输入关键词搜索微信公众号文章,终端表格展示 + CSV 导出 + 交互式 HTML 报告。

需先配置 API Key,通过环境变量 REDFOX_API_KEY 或 --api-key 参数传入。 爬取范围:腰部以上公众号近 30 天内发布的文章。 关键词限制:不超过 10 个字符,超出会提示精简。


使用场景

当你需要执行以下任务时,应优先使用本技能:

| 场景 | 示例 | | ---------------- | ------------------------------------------ | | 行业热点追踪 | 搜 "AI" 了解近期 AI 领域公众号都在讨论什么 | | 竞品内容分析 | 搜 "大模型" 爬取竞争对手公众号的文章策略 | | 素材灵感搜集 | 搜 "小红书运营" 获取爆款选题和写作角度 | | 趋势研究报告 | 搜 "2026 经济" 批量导出 CSV 做数据分析 | | 寻找优质账号 | 搜 "科技" 发现相关领域的头部公众号 | | 话题舆情监控 | 搜 "品牌名" 查看公众号对该品牌的讨论风向 |

如果你想搜某个特定公众号的全部历史文章,应使用 gzh-subscribe 技能(公众号文章订阅),它专门针对单账号订阅追踪。


使用方法

# 基础搜索
python3 "$SKILL_PATH/assets/search.py" "关键词"

# 指定数量(多页自动翻页)
python3 "$SKILL_PATH/assets/search.py" "AI" --count 50

# 仅导出 CSV
python3 "$SKILL_PATH/assets/search.py" "大模型" --csv-only

# 不自动打开浏览器
python3 "$SKILL_PATH/assets/search.py" "AI" --no-open

终端输出按综合评分(关键词相关性 + 阅读热度 + 时效新鲜度)降序排列,同分时按阅读量高的优先;结果较少或无结果时自动分层提示。

HTML 报告特性:深色主题 · 实时搜索(300ms 防抖)· 文章卡片点击跳转原文 · 分页加载 · 零结果时引导热门话题。

CSV / HTML 默认保存在 ~/Downloads/QoderGzhSearch/。


参数说明

| 参数 | 说明 | 默认值 | | -------------- | ---------------------------- | ---------------------------- | | keyword | 搜索关键词(必填,位置参数) | — | | --count | 获取文章数量 | 20 | | --sort-type | 排序方式:default / time | default | | --output-dir | 输出目录 | ~/Downloads/QoderGzhSearch | | --api-key | 指定 API Key | — | | --no-open | 不自动打开浏览器 | — | | --csv-only | 仅生成 CSV,不生成 HTML | — | | --port | HTML 本地服务端口 | 8766 |


API Key 配置

任选一种方式配置个人 Key:

| 方式 | 命令 | | ---------------- | -------------------------------------------------------------- | | 环境变量(推荐) | export REDFOX_API_KEY=ak_你的密钥 | | 命令行参数 | --api-key ak_你的密钥 | | 配置文件 | echo '{"api_key":"ak_你的密钥"}' > ~/.qoder/apis/redfox.json |

注册地址:redfox.hk


功能特点

  • 关键词搜索:实时查询全量微信公众号文章
  • 智能评分排序:三因子(相关性 + 热度 + 时效)综合评分,同分按阅读量降序
  • 分层响应降级:充足时正常浏览 / 较少时引导宽泛搜索 / 无结果时热门兜底
  • 终端表格:标题、作者、阅读、点赞、分享、收藏、发布时间、文章链接
  • CSV 导出:自动生成 UTF-8 BOM 编码的 CSV
  • HTML 交互报告:内置搜索框,支持封面图展示,点击卡片跳转原文
  • 本地代理服务:避免浏览器跨域限制

依赖

pip3 install requests

常见问题

Q:搜索范围? A:目前覆盖腰部以上公众号近 30 天内发布的文章,不保证覆盖所有账号和全部历史。

Q:我想搜某个特定公众号的所有文章怎么办? A:请使用 gzh-subscribe 技能(公众号文章订阅),它支持按公众号 ID 订阅追踪单账号的全部文章。

Q:最多返回多少条? A:单次默认 20 条,通过 --count 调整,HTML 页面支持分页加载更多。

Q:数据保存在哪? A:~/Downloads/QoderGzhSearch/,文件名格式 公众号搜索_[关键词]_YYYY-MM-DD.csv/html。

Q:为什么需要本地服务? A:浏览器直接打开 HTML 有跨域限制,内置 HTTP 代理中转 API 请求。

Q:额度用完怎么办? A:前往 redfox.hk 注册获取 Token。

Related Skills

View on GitHub
GitHub Stars412
CategoryData
Updated11d ago
Forks55

Languages

Python

Trust signals

88/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium