gzh-search

Official Account Search Crawler (Doubaoya)

This duck specializes inbatch data gatheringThis tier: with one keyword, scoop up a batch of official account articles in this track, and the terminal lays them out directly into a clickable table — for you to dotopic insightwith, not to read a single article. For chasing hotspots, scraping competitors, and stockpiling material, first use this duck to sweep open the "surface", then go pick the "points" worth a closer look.

Data goes through doubaoya.com in one line, authentication uses your own key (environment variable DOUBAOYA_API_KEY, in the form dyh_…）。

Want to precisely tracka certain official accountfor updates/retrospectives, go doubaoya and hit POST /api/apis/gongzhonghao/gongzhonghao-work-list/call(pull the article list by account); want to dig by popularity + time range forviral articles, use wechat-hot-article. This duck is a "keyword → a batch of articles" surface-sweeping tool.

---

Applicable scenarios

Scenario	How to use	What you get
Industry hotspot scan	Search AI 工具 to scoop up a batch of recent articles in this track	See at a glance what angles everyone is writing about right now
Competitor content inventory	Search 大模型 for batch data gathering to inventory opponents' topic selection	Find out which angles the same track is competing for
Topic material collection	Search 职场沟通 to scrape a batch of referable viral angles	Stockpile first-hand material for the next piece
Public opinion trend monitoring	Search 品牌名 to see the discussion trend on the official account side	Quickly judge the direction of public opinion
Trend research groundwork	Search 2026 经济 for batch data gathering as research groundwork	Lay out data for reports/research

---

Workflow (4 steps)

1. Extract keywords

Pull out from the user's description thecore keyword— keep it concise, 2~6 characters is best (e.g. AI 工具、大模型、职场). The shorter the word, the broader and the more hits; too long and too narrow easily sweeps up nothing. Crawl only one keyword at a time.

2. Call the crawl script

python3 "$SKILL_PATH/scripts/crawl_gzh.py" "AI 工具"

To stack more material, paginate:

python3 "$SKILL_PATH/scripts/crawl_gzh.py" "AI 工具" --page 2

The script prints the data from the success envelope as JSON to stdout.Run the script only once per keyword, read the full stdout directly, don't use head/tail to preview, and don't call repeatedly for the same keyword.

3. Lay out into an article table

Take fields from data.items(article array), and lay them out into Markdown per the table below. Dodefensive reading——title / accountNamefor fields — (author/official account) / publishTime(publish time) may be missing; if missing, leave blank and don't error. Render the title as aclickable link(pointing to the article's original URL).

Title	Author	Publish time
Sample article title	Some Official Account	2026-06-20

Want to sort this batch of articles? You can add a "Composite Index" column (keyword relevance + read popularity + freshness) and sort descending, with higher read counts first for ties—this is display-layer processing, no change to API calls.

4. Give a one-sentence topic insight

After the table, add a sentence in this duck's voicetopic insight: what angle this batch of articles is competing for, which angle no one has written thoroughly yet, and whether it's worth following. Keep it short and useful, don't pile on clichés, and don't ask the user "what is your real purpose".

---

Get the key (secret key)

1. Open doubaoya.com
2. Log in
3. Go to Key Center
4. Generate key(in the form dyh_…）

Set it in an environment variable (the script only recognizes this one):

export DOUBAOYA_API_KEY="dyh_你的密钥"

Iron rule: never print the key, never write it to a file, never echo it back to the user. The script itself also never outputs the key. All requests are sent only to doubaoya.com, don't take the key to any other domain.

---

API and envelope

• POST https://doubaoya.com/api/apis/gongzhonghao/search-article/call
• Auth header:Authorization: Bearer $DOUBAOYA_API_KEY
• Request body:{ "keyword": "AI 工具", "page": 1 }
  • keyword: string, required
  • page: integer, optional (default 1)
• Return envelope:

  {
    "success": true,
    "requestId": "...",
    "data": { "items": [ { "title": "...", "accountName": "...", "publishTime": "..." } ] },
    "error": null
  }
  

• First check success: if it is true , then read data; otherwise read error.code / error.message。

---

Error handling

When the script fails, it prints to stderr [error] CODE: message and exits with code 1. Common cases:

HTTP	code	Meaning	Handling
401	MISSING_API_KEY / UNAUTHORIZED	No key provided or invalid key	Check DOUBAOYA_API_KEY, go to Key Center to regenerate
400	VALIDATION_ERROR	Invalid parameter (e.g. keyword is empty)	Fix the keyword and retry
402	INSUFFICIENT_CREDITS	Insufficient quota	Go to doubaoya.com to top up/renew quota
502	PROVIDER_FAILED	Temporary upstream failure (automatically refunded）	Safe to retry

502 PROVIDER_FAILED will be automatically refunded, retrying is safe, and you won't be charged twice.

---

Directory structure

gzh-search/
├── SKILL.md                  # 本文件
└── scripts/
    └── crawl_gzh.py          # 零依赖爬取脚本（urllib），调用 doubaoya.com

About the notice field in the response

After calling the doubaoya API corresponding to this skill, if the top level of the returned JSON contains a notice field, please relay this sentence to the user verbatim—this is a notice that this skill has an update, it does not affect the result of this call, and no retry or behavior change is needed.