WeChat Article Download API

Fetch and export WeChat public article content through down.mptext.top API. Use when testing this API, downloading a WeChat article, validating html/markdown...

Security Scan

The skill's code and instructions consistently implement a simple downloader that calls down.mptext.top and writes article outputs to local files; nothing in the package requests unrelated credentials or system access.

Purpose & Capability

Name/description say it fetches WeChat articles via down.mptext.top and the included script and docs do exactly that (HTTP GET to the API, save html/markdown/text/json). No unrelated capabilities or credentials are requested.

Instruction Scope

SKILL.md instructs running the bundled script with a target URL and output options. The instructions only perform the stated network call and local file writes; they do not ask the agent to read other files, credentials, or system state.

Install Mechanism

No install spec (instruction-only) and the script uses Python stdlib for HTTP. README mentions 'pip install requests' but the script actually uses urllib; this is a minor documentation mismatch but not a functional risk. No downloads from untrusted hosts occur during install.

Credentials

The skill requests no environment variables or secrets. The only external interaction is with the documented API endpoint (down.mptext.top). Users should note that article content is sent to that external service, which may have privacy implications for non-public content.

Persistence & Privilege

The skill does not request always=true, does not modify other skills or global settings, and only writes files to the user-specified output directory. Autonomous invocation is allowed by default but is not combined with broad privileges here.

Assessment

This package appears to do only what it claims: call https://down.mptext.top and save outputs. Before installing or invoking it: - Confirm you trust down.mptext.top, since article content (possibly sensitive) is sent to that external service. - The script writes files to the output directory you specify—run it in a controlled directory if you want to avoid clutter or overwriting files. - README mentions the 'requests' package but the script uses urllib; no extra dependencies are required. You can inspect scripts/fetch_wechat_article.py yourself (it is short and uses stdlib) before running. - If you plan to enable autonomous agent invocation, be aware the agent can call the external API without further prompts; consider limiting usage or monitoring logs if that matters to you.

Overview

Use this skill to call https://down.mptext.top/api/public/v1/download without API key, fetch a WeChat article by URL, and save outputs as html, markdown, text, or json.

Workflow

1. Confirm target article URL.
2. Pick output format(s): html, markdown, text, json.
3. Run scripts/fetch_wechat_article.py to request API and save files.
4. Check returned status, content type, and local file size.

Quick Commands

Fetch all 4 formats to current directory:

python scripts/fetch_wechat_article.py \
  --url "https://mp.weixin.qq.com/s/W-8MSBo5FwDY8OmCUN0cSw" \
  --formats html markdown text json

Set output directory and basename:

python scripts/fetch_wechat_article.py \
  --url "https://mp.weixin.qq.com/s/xxx" \
  --formats json \
  --outdir "d:/wechattxt/output" \
  --basename "wx_article"

Output Naming

Save files as {basename}.{ext}:

• html -> .html
• markdown -> .md
• text -> .txt
• json -> .json

Print one summary line per format:

• HTTP status code
• response Content-Type
• output file path
• byte size

Error Handling

Treat non-200 status as failure. Keep processing remaining formats unless --fail-fast is set. Raise process exit code 1 if any format fails.

Resources

• API details: references/api.md
• Runner script: scripts/fetch_wechat_article.py