URL Extract
Extract readable main content from Xiaohongshu and other web pages.
What it does
Extracting clean, readable content from web pages — especially Xiaohongshu, WeChat, or JavaScript-heavy sites — is painful. This connector returns the main content of any URL as structured Markdown, with title, canonical URL, and content length.
Inputs
| Parameter | Format | Example | Required |
|---|---|---|---|
url | string | https://www.xiaohongshu.com/explore/abcd1234 | Yes |
Outputs
| Field | Type | Description |
|---|---|---|
title | string | The page title extracted from the document |
url | string | The canonical URL of the page |
contentLength | number | Character count of the extracted main content |
Example output
Input
url: "https://www.xiaohongshu.com/explore/abcd1234"
Output
# URL Extract - Title: 10 Hidden Cafes in Shanghai You Must Visit - URL: https://www.xiaohongshu.com/explore/abcd1234 - Content Length: 2,340 characters
What it means
The Xiaohongshu note was successfully extracted. The main content is 2,340 characters and covers hidden cafe recommendations in Shanghai.
Last tested: 2026-03-10
How to install
Via CLI
Via web
- Visit the connector catalog and find URL Extract.
- Click Install connector and acknowledge any training requirements.
- Complete authorization if prompted.
- Use the connector from Chat or the CLI.
Auth and permissions
| OAuth required | No |
| Managed auth | Included, no API key needed |
| Bring your own key (BYOK) | Not supported in v1 |
| Audit logged | Every request is logged with input, result, cost, and timestamps |
| Training acknowledgment | Not required |
Admins can restrict this connector via blacklist or whitelist in the admin panel.
Limits and edge cases
- •Pages behind login walls or CAPTCHAs may fail to extract.
- •Very large pages (over 100KB of content) may be truncated.
- •Dynamic SPA pages that require extensive JavaScript rendering may return incomplete content.
- •Xiaohongshu and WeChat article URLs are specifically supported and tested.
Common use cases
Read a Xiaohongshu note and extract key points
Paste a note URL and get the title, content, and character count.
Extract article content for summarization
Feed a URL to this connector, then chain the output to a summarizer.
Frequently asked questions
Which sites are supported?
Any publicly accessible web page. Xiaohongshu and WeChat articles are specifically tested and optimized.
Does this return the full page HTML?
No. It extracts the main readable content (similar to reader mode) and returns it as Markdown.
What happens with login-required pages?
Extraction will fail for pages that require authentication. Only publicly accessible content is supported.