Web Page Fetcher, Readability Extractor & HTML Parser
scrape_readable_articleFetches any public HTTP/HTTPS URL and extracts article text, headings, author bylines, and raw html_content. Use as the universal URL fetcher before downstream HTML parsing tools (parse_html_tables, isolate_css_selectors, extract_clean_markdown); for converting full raw HTML without fetching, pass html_content directly. Stateless edge call (max 32 KB, 60 RPM): accepts 'url' or 'html_content' ('readability_profile' defaults to 'article_body_strict'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "scrape_readable_article"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | The public HTTP or HTTPS web page URL to fetch and extract. | |
| html_content | No | Target web page HTML containing the article, editorial post, or blog content. | |
| include_byline | No | Whether to parse author names, affiliations, and editorial publication dates. | |
| readability_profile | No | Content isolation heuristic: strict article body, technical documentation, or forum thread. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | The resolved web page URL. | |
| title | Yes | Extracted main article headline. | |
| byline | Yes | Author credit or publishing editorial team. | |
| excerpt | Yes | Short leading synopsis or meta description. | |
| content_text | Yes | Sanitized primary article narrative text. | |
| html_content | No | Raw fetched HTML document for piping into downstream HTML parsers. | |
| reading_time_minutes | Yes | Estimated reading duration in minutes based on 220 WPM. |