HTML Table to Structured JSON & Markdown Parser
parse_html_tablesDetects and parses HTML table elements from live URLs or raw HTML into structured JSON record arrays and GitHub-Flavored Markdown tabular grids. Accepts either 'url' to fetch directly or raw 'html_content' from upstream scrape_readable_article; for extracting full article body text, use scrape_readable_article instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'url' or 'html_content' ('output_format' defaults to 'markdown_and_json'), 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": "parse_html_tables"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | Optional web page URL to fetch and parse directly, bypassing an out-of-band fetch step. | |
| min_rows | No | Minimum rows required for a table to be parsed and retained. | |
| html_content | No | Raw HTML string containing one or more table, thead, tbody, or tr elements. | |
| output_format | No | Tabular export formatting standard: markdown and JSON, JSON records only, or CSV string. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| tables_found | Yes | Count of valid HTML tables detected and transformed. | |
| markdown_tables | Yes | List of GitHub-Flavored Markdown formatted table strings. | |
| structured_records | Yes | Parsed array of row objects keyed by header column titles. |