{ "slug": "readability-extractor", "name": "gizza-ai/readability-extractor", "version": "0.1.0", "title": "Readability Extractor — Get the Article from Messy HTML — gizza.ai", "description": "Paste a web page's HTML and extract just the main article — title and body — with navigation, ads, and boilerplate stripped. Free, runs in your browser.", "tags": [ "readability", "extract article", "strip boilerplate", "reader mode", "clean html", "article extractor" ], "category": "text", "urls": { "page": "https://gizza.ai/tools/readability-extractor/", "markdown": "https://gizza.ai/tools/readability-extractor/index.md", "descriptor": "https://gizza.ai/tools/readability-extractor/tool.json", "deep_link_example": "https://gizza.ai/tools/readability-extractor/?html=%3Chtml%3E%E2%80%A6paste%20the%20article%20page%20source%E2%80%A6%3C%2Fhtml%3E&format=text" }, "cli": "gizza tool readability-extractor \"…paste the article page source…\"", "tool": { "description": "Extract the main article content (title + body) from cluttered HTML, stripping navigation, ads, and boilerplate (a Readability-style extraction). Pass the page HTML as `html`; set format='text' (default) for readable plain text or 'html' for cleaned article HTML.", "parameters": { "additionalProperties": false, "properties": { "format": { "default": "text", "description": "Output the cleaned article as plain 'text' (default) or cleaned 'html'.", "enum": [ "text", "html" ], "type": "string" }, "html": { "description": "The cluttered HTML (article page source) to extract the main content from.", "type": "string" } }, "required": [ "html" ], "type": "object" } } }