ai-bot APIai-bot.cn ↗
Search and retrieve daily AI news articles from ai-bot.cn by keyword and date. Returns titles, content, sources, and links for the latest AI industry updates.
What is the ai-bot API?
The ai-bot.cn API exposes one endpoint, search_articles, that returns a curated feed of daily AI news articles covering approximately the last 3–4 months of workday updates. Each article object includes five fields — date, title, content, source, and link — and results can be filtered by keyword, date, or both, with up to 100 articles returned per request sorted newest first.
curl -X GET 'https://api.parse.bot/scraper/ac7c7d64-3549-47d0-8764-6686bdfb989e/search_articles?keyword=DeepSeek' \ -H 'X-API-Key: $PARSE_API_KEY'
Typed, relational, agent-ready
A generated client with real types, enums, and the links between objects — the structure a flat JSON response can't carry. Autocompletes in your editor and reads cleanly to coding agents.
- Fully typed · autocompletes
- Objects link to objects
- Typed errors & pagination
Typed Python client. Set up the SDK in your uv project, then pull this API’s typed client:
uv add parse-sdk uv run parse init uv run parse add --marketplace ai-bot-cn-api
uv run parse add --marketplace pulls a pinned snapshot of this canonical API — it won’t change underneath you. To customize it, subscribe and swap to your own copy.
"""Walkthrough: AI Bot Daily News — search and browse recent AI articles."""
from parse_apis.ai_bot_cn_api import AiBot, InputFormatInvalid
client = AiBot()
# Search for articles mentioning a keyword, capped at 5 results.
for article in client.articles.search(keyword="DeepSeek", limit=5):
print(article.date, article.title)
print(f" source: {article.source}")
print(f" {article.link}")
# Drill into a single article for a specific date.
latest = client.articles.search(date="2026-08-13", limit=1).first()
if latest is not None:
print(latest.title)
print(latest.content[:200])
# Demonstrate error handling for malformed input.
try:
client.articles.search(date="not-a-date", limit=1).first()
except InputFormatInvalid as e:
print(f"Bad input: {e.message}")
print("exercised: articles.search")
Search daily AI news articles by keyword and/or date. Fetches the latest news page (covering approximately the last 3-4 months of workday updates) and filters articles whose title or content contains the keyword. Returns articles sorted by date descending (newest first). Each request fetches the full page from the source (~450 articles); filtering is applied locally.
| Param | Type | Description |
|---|---|---|
| date | string | Filter articles to a specific date in ISO format YYYY-MM-DD (e.g. 2026-08-13). When omitted, articles from all available dates are returned. |
| limit | integer | Maximum number of articles to return. Clamped to 1-100. |
| keyword | string | Search keyword matched case-insensitively against article title and content. When omitted, no keyword filter is applied. |
{
"type": "object",
"fields": {
"total": "Total number of articles matching the filters before limit is applied",
"articles": "Array of article objects with date, title, content, source, and link"
},
"sample": {
"data": {
"total": 2,
"articles": [
{
"date": "2026-08-13",
"link": "https://mp.weixin.qq.com/s/XGzdn5Kk5jmaM9XYAy9JMg",
"title": "DeepSeek-V4-Pro 正式版上线",
"source": "DeepSeek",
"content": "DeepSeek 推出DeepSeek V4 Pro正式版，已同步在APP、网页端和API上线。该版本Agent能力显著增强，在Terminal Bench、DeepSWE等评测集上表现优异。"
},
{
"date": "2026-08-13",
"link": "https://mp.weixin.qq.com/s/mANdGRI4fO_sEbC1ECEoZQ",
"title": "DeepSeek Harness 开发者预览版开放测试",
"source": "DeepSeek Harness 团队",
"content": "DeepSeek Harness开发者预览版（v0.1 版本）面向全球 Harness 开发者开放测试，并同步以MIT协议开源。"
}
]
},
"status": "success"
}
}About the ai-bot API
What the API Returns
The search_articles endpoint queries a continuously updated archive of AI news curated by ai-bot.cn. Each article in the response carries a date (ISO format), title, content summary, source attribution, and a link to the full article. The total field in the response reports how many articles matched your filters before the limit was applied, which helps you understand result set size without paginating blindly.
Filtering Articles
Three optional parameters control what you get back. The keyword parameter matches case-insensitively against both title and content, so a search for "GPT" will surface articles where either field contains that string. The date parameter accepts an ISO date string (YYYY-MM-DD) and restricts results to articles from that specific workday. The limit parameter is clamped between 1 and 100; omitting it returns up to the default cap. Any combination of these three parameters can be used together.
Coverage and Freshness
The archive covers roughly the last 3–4 months of workday AI news as published on ai-bot.cn's daily news feed. Articles are sorted by date descending, so index position 0 is always the most recent item matching your filters. Coverage reflects workday publishing cadence — weekends and holidays may have gaps. The source is a Chinese-language AI news aggregator, so article titles and content are primarily in Simplified Chinese.
The ai-bot API is a managed, monitored endpoint for ai-bot.cn — not a raw scraper you maintain. Every endpoint is automatically health-checked on a schedule, and when ai-bot.cn changes and a check fails, the API is automatically queued for repair and re-verified. It is built to keep working as the site underneath it changes.
This isn't an official ai-bot.cn API — it's an independent, maintained REST wrapper over public data. Where the source has no official API (or only a limited one), Parse gives you a stable contract over a source that never promised one, and keeps it current. Need a new endpoint or field? You can revise it yourself in plain English and the agent rebuilds it against the live site in minutes — contributing the change back to the shared API is free.
Will this API break when the source site changes?+
Is this an official API from the source site?+
Can I fix or extend this API myself if I need a new endpoint or field?+
What happens if I call an endpoint that has an issue?+
- Monitor daily AI industry headlines by polling
search_articleswith today's date each morning. - Track coverage of a specific AI model or company by passing its name as the
keywordparameter. - Build a keyword-alert system that checks whether a term appears in
titleorcontentacross recent articles. - Aggregate
sourceattribution data to identify which media outlets most frequently cover AI topics. - Feed article
linkandtitlefields into a downstream summarization pipeline for briefing documents. - Audit how AI news volume varies by date by querying
totalacross a sequence of dates. - Populate a news widget filtered to a specific topic using
keywordwith alimitof 5–10 articles.
| Tier | Price | Credits/month | Rate limit |
|---|---|---|---|
| Free | $0/mo | 200 | 5 req/min |
| Hobby | $30/mo | 1,000 | 20 req/min |
| Developer | $100/mo | 5,000 | 100 req/min |
| Team | $300/mo | 20,000 | 300 req/min |
| Company | $1,000/mo | 100,000 | 500 req/min |
Each endpoint has a fixed posted price per successful call — most fall between 1 and 10 credits — shown on this API's page before you run it. Exceeding the rate limit returns a 429 response. Authenticate with the X-API-Key header.
Does ai-bot.cn have an official developer API?+
What does the `search_articles` endpoint return when no keyword or date is provided?+
limit parameter (1–100). The total field tells you the full untruncated count.How far back does the article archive go?+
search_articles. You can fork this API on Parse and revise it to target a different date range or a deeper archive endpoint if one becomes available on the source.Can I retrieve the full article body, not just a content summary?+
content field returned by search_articles is a summary or excerpt, not the full article body. Full article text is not currently exposed. The response does include a link field pointing to the original article. You can fork this API on Parse and revise it to add a separate endpoint that fetches and returns the full article body from that link.Are articles available in languages other than Chinese?+
title and content fields are primarily in Chinese. The API does not currently offer translated or English-language variants of the articles. You can fork this API on Parse and revise it to add a translation step before returning article fields.