Collecting Weibo comments and Xiaohongshu notes for a thesis, without coding (2026)
Have an AI call the API and make the table. Connect DataXAPI to Claude or Cursor and say “export the comments under this Weibo post to a spreadsheet”; it fetches page by page and writes a CSV. A page of Weibo comments is $0.0020 (about 20), a page of Xiaohongshu note search $0.0200. The free trial covers up to 333 calls; a failed call is not charged.
Updated 2026-11-06
Four steps
1. Settle what you study: a topic, an event, a brand, or particular posts and notes, and the period.
2. Connect the AI: sign up for a key (a free trial, no card) and paste the sentence below to the AI.
3. Ask in plain words: “Search Weibo for October posts on 预制菜进校园, take the 20 most reposted, get every comment under each, and save one table with the post link, comment text, likes, time posted and IP location.”
4. Analyse the table: open the CSV in Excel, or load it into SPSS, NVivo or Python for coding, sentiment and word counts.
To connect: paste this to your AI assistant: “Read https://dataxapi.com/agents.md and set up DataXAPI here. My API key is dx_…; use it for every DataXAPI call.” A client that takes a remote MCP server can be given https://api.dataxapi.com/mcp with the header Authorization: Bearer <key> instead.
Which fields come back?
The ones most used are below; field names are the same on every platform, and each endpoint's page has a recorded real response.
| You want | Endpoint | Fields |
|---|---|---|
| Weibo posts by keyword | weibo.posts.search | Text, author, reposts, comments, likes, time posted |
| A Weibo post's comments | weibo.posts.comments.list | Text, commenter, likes, replies, time posted, IP location |
| Xiaohongshu notes by keyword | xiaohongshu.notes.search | Title, author, likes, saves, comments, time posted |
| A note's text and comments | xiaohongshu.notes.get, xiaohongshu.notes.comments.list | Text, topics, images, comment text and likes |
How do I state the data source in the thesis?
Every answer carries the time it was fetched, meta.fetched_at, and a request_id. Note the keywords, the period, the day fetched and the endpoints used, and put them in your method, so anyone can do it again.
It reads only what is publicly visible on the platform. When you quote comments in the thesis, leave out user names and avatars.
What does it come to?
Charged by the page; a failed call is not charged. A page of Weibo comments is about 20, at $0.0020; 5 pages under each of 20 posts is 100 calls. The free trial covers up to 333 calls: try a small sample on it first.
Why DataXAPI
- Steady: endpoints were available 99.9% of the last 30 days, on a public status page you can check.
- Fast: a paid call took 2.5 seconds at the median over the last 7 days (counted 2026-11-06).
- Fewer tokens: across 226 endpoints, one recorded real response each, the platform's own JSON comes to 9.2M tokens and what an AI reads through DataXAPI's MCP server to 452k, 95% fewer; the JSON of a direct API call is 90% fewer too (counted 2026-11-06). Every platform answers in one shape: the author in
author, counts inmetrics, the next page inpage.next_cursor, so another platform needs no new parser. - See before you pay: every endpoint's page shows a recorded real response, field by field.
- Spending you control: a failed call is not charged; each key can have a limit,
X-Max-Pricecaps one call, and the sameIdempotency-Keywithin 24 hours is never charged twice. - Ready for AI: a remote MCP server listed in the official MCP registry as
com.dataxapi/mcp, usable from Claude, Cursor and ChatGPT. - Free trial of up to 333 calls, no card.
Endpoints
Each with its price; every page has the parameters, the fields and a recorded response.
Start with one key.
230 endpoints on 21 platforms, from $0.0003 a call. Errors and timeouts are not charged.