cn-last30days

Aggregation of works across the entire web over the past 30 days (DouBaoYa)

Quack! With one keyword, this duck simultaneously pulls backXiaohongshu, Douyin, WeChat Official Accountsreal works from the past 30 days—all three platforms at once, view public opinion across platforms and compare topic angles, no need to flip through one platform at a time.

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

Applicable scenarios

Scenario	How to use	What you get
Cross-platform public opinion comparison	Search `大模型` to see what each of the three platforms is discussing	See at a glance which platform is hotter and where the differences in framing lie
Cross-platform topic angle comparison	Search `减脂` to compare Xiaohongshu recommendations / Douyin follow-up reviews / WeChat Official Account in-depth pieces	The entry points and angles of each platform on the same topic
Brand reputation monitoring	Search `某品牌` to see reputation and discussion across the three platforms	Multi-dimensional public opinion perspectives, cross-verification
Hot topic research	Search `2026 经济` to see trends across the entire web	As a foundation for research / reports
Historical backtracking	Add `--start-date` / `--end-date` to define the time window	Track trend evolution over a period of time

Platform signal quick read: Xiaohongshu = recommendation experience / tutorials and guides; Douyin = hotspot follow-up reviews / emotional spread; WeChat Official Accounts = industry depth / viewpoint output. Conclusions cross-verified across the three platforms are the most reliable.

Workflow (4 steps)

1. Understand the intent and extract keywords

Extract from the user's description thecore keyword, best condensed to 2–6 characters (e.g., AI 视频、大模型、职场). The shorter the word, the broader it is and the more hits; too long and too specific easily returns nothing. Search only one keyword at a time. When the topic is too vague (e.g., "tool," "method"), first ask the user to make it more specific before searching.

2. Call the aggregation script

python3 "$SKILL_PATH/scripts/search_cn30.py" "大模型"

Define the time window (optional, backtrack to any interval within the past 30 days):

python3 "$SKILL_PATH/scripts/search_cn30.py" "大模型" --start-date 2026-06-01 --end-date 2026-06-24

The script outputs the data from the success envelope as JSON to stdout.Run the script only once per query, read the complete stdout directly, do not use head / tail to preview or repeatedly call for the same keyword.

3. Render the three-platform table

The returned data contains three arrays (read defensively; leave missing fields blank and do not error):

Array key	Platform	Typical fields
`xhsResult`	Xiaohongshu	`title` / `authorName` / `likeCount` / `commentCount` / `publishTime` / link
`dyResult`	Douyin	`title` / `authorName` / likes / comments / shares / `publishTime` / link
`gzhResult`	WeChat Official Accounts	`title` / `accountName` / reads / likes / `publishTime` / link

Display method (choose one of two)：

Three tables by platform(Recommended): in the order WeChat Official Account → Xiaohongshu → Douyin, one table per platform, each taking several top-engagement items, with titles rendered as clickable links.

Title Author Engagement Publish time
Merge into one table: add a "Platform" column and merge the three groups of works into 平台 / 标题 / 互动 / 发布时间 one table for easy side-by-side comparison.

4. Give a cross-platform insight

After the tables, add one line in this duck's tone oncross-platform insight: the popularity gap for the same topic across the three platforms, the differences in angle on each platform, which angle has not yet been written thoroughly, and whether it is worth following. Keep it short and useful, don't pile on platitudes, and don't ask the user "what is the real purpose".

Get the key (secret key)

Open doubaoya.com
Log in(register first if you don't have an account)
Go to Key Center
Generate key(in the form dyh_…）

Configure it into 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 into 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, do not take the key to any other domain.

Dependencies: only the Python 3 standard library is used, no third-party packages need to be installed.

API and envelope

POST https://doubaoya.com/api/apis/multi/cn30-multi-search/call
Auth header:Authorization: Bearer $DOUBAOYA_API_KEY
Request body:{ "keyword": "大模型" }, optionally with startDate / endDate
- keyword: string, required
- startDate / endDate：YYYY-MM-DD，optional—when not passed, the server takes the default of the last 30 days; only include it when the user has given a time criterion

Return envelope:

{
  "success": true,
  "requestId": "...",
  "data": {
    "xhsResult": [ { "title": "...", "authorName": "...", "likeCount": 0, "publishTime": "..." } ],
    "dyResult":  [ { "title": "...", "authorName": "...", "publishTime": "..." } ],
    "gzhResult": [ { "title": "...", "accountName": "...", "publishTime": "..." } ]
  },
  "error": null
}

First check success: if it is true , then read data; otherwise read error.code / error.message。
Field defense: the field naming of each work in the three arrays may differ slightly and may also be missing; always "if it cannot be retrieved, give a default value", leave it blank if missing, and don't let one piece of data crash the whole table.

Error handling

When the script fails, print to stderr [error] CODE: message and exit 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 the Key Center to regenerate it (do not echo the key)
400	`VALIDATION_ERROR`	Invalid parameters (such as empty keyword or wrong date format)	Fix the parameters and retry
402	`INSUFFICIENT_CREDITS`	Insufficient quota	Go to doubaoya.com to top up / renew quota
404	`ENDPOINT_NOT_FOUND`	Wrong API path	Usually the script has been modified; restore the default endpoint path
502	`PROVIDER_FAILED`	Temporary upstream failure (refunded automatically）	Safe to retry
—	`NETWORK_ERROR`	Cannot connect to doubaoya.com	Check the network and retry

502 PROVIDER_FAILED will be refunded automatically; retrying is safe and will not double charge.

Directory structure

cn-last30days/
├── SKILL.md                  # 本文件
└── scripts/
    └── search_cn30.py        # 零依赖聚合脚本（urllib），调用 doubaoya.com

About the notice field in the response

After calling the doubaoya API corresponding to this skill, if 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 change in behavior is needed.