ClawHub

Zhihu Keyword Content Search

v1.0.0

爬取知乎问题和回答。当用户要求爬取知乎、抓取知乎数据、搜索知乎问答，或提到"知乎"+"爬虫/爬取/抓取/搜索"时使用此技能。支持按关键词搜索问题、按回答数排序、抓取全部回答并保存为JSON和纯文本。

⭐ 0· 68·0 current·0 all-time
by@taiyuexiao
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description match the included Python script (zhihu_crawl.py) and README: the code searches Zhihu, ranks by answer count, fetches answers, and writes JSON/plaintext outputs. No unrelated binaries, services, or credentials are requested.
ℹ
Instruction Scope
SKILL.md instructs running the provided script with a --cookie argument and explains how to copy the browser cookie. The instructions do not attempt to read unrelated system files or send data to third-party endpoints. However, asking users to paste their full browser Cookie is sensitive — it is within scope for accessing logged-in Zhihu APIs but should be handled cautiously.
✓
Install Mechanism
No install spec; dependency is requests (not bundled). The skill is instruction+source-file only, so nothing is downloaded from external URLs or installed silently. Risk from install mechanism is low.
ℹ
Credentials
No environment variables or external service credentials are declared, which matches the registry metadata. The script requires a Zhihu login cookie passed as a CLI argument; this is necessary to access certain Zhihu APIs but is sensitive (session tokens). No unrelated credentials (AWS, GitHub, etc.) are requested.
✓
Persistence & Privilege
Skill does not request always:true and does not modify other skills or system-wide settings. It runs as a normal, on-demand script and writes only to the configured output directory.
Assessment
This skill is coherent with its description, but it asks you to provide your full Zhihu login Cookie (a session token). That token can grant access to your account if leaked — only paste it into code you trust. Recommendations: (1) review the included zhihu_crawl.py locally before running; (2) run the script on an isolated or throwaway account if possible; (3) do not paste cookies into third-party web UIs or share them; (4) be aware of Zhihu's terms of service and rate limits; (5) ensure you have 'requests' installed in a controlled Python environment. If you are uncomfortable providing a full login cookie, do not install or run this skill.

Like a lobster shell, security has layers — review code before you run it.

crawlervk973h7gv2qggc8qg9jq7acm4rs840rqxdatavk973h7gv2qggc8qg9jq7acm4rs840rqxlatestvk973h7gv2qggc8qg9jq7acm4rs840rqxzhihuvk973h7gv2qggc8qg9jq7acm4rs840rqx

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments