Hydrafetch

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['urls'], 'properties': {'urls': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 25000, 'minItems': 1, 'description': 'The URLs to scrape.'}}}

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['batchId'], 'properties': {'batchId': {'type': 'string', 'description': 'The id returned by batch.'}}}

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['domain'], 'properties': {'domain': {'type': 'string', 'description': 'The company domain, e.g. stripe.com. A full URL works too.'}}}

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'The site to start from.'}, 'limit': {'type': 'integer', 'maximum': 500, 'minimum': 1, 'description': 'Maximum pages to scrape.'}, 'maxDepth': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': 0, 'description': 'How far from the seed to follow.'}}}

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['crawlId'], 'properties': {'crawlId': {'type': 'string', 'description': 'The id returned by crawl.'}}}

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['urls'], 'properties': {'urls': {'type': 'array', 'items': {'type': 'string'}, 'minItems': 1, 'description': 'The URLs to extract from.'}, 'prompt': {'type': 'string', 'description': 'Natural-language description of what to pull.'}, 'schema': {'type': 'object', 'description': 'A JSON schema the result must conform to.', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}, 'showSources': {'type': 'boolean', 'description': 'Return the list of URLs that were actually extracted.'}, 'showConfidence': {'type': 'boolean', 'description': 'For each field, return a confidence score and the exact source passage the value was drawn from.'}, 'preferStructure': {'type': 'boolean', 'description': 'Keep headings, lists and tables in the text handed to the model.'}}}

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'The page to harvest images from.'}}}

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['domain'], 'properties': {'type': {'enum': ['icon', 'wordmark'], 'type': 'string', 'description': 'The square mark, or the full logotype. Defaults to icon.'}, 'theme': {'enum': ['light', 'dark', 'auto'], 'type': 'string', 'description': 'The background the logo will sit on. Defaults to light.'}, 'domain': {'type': 'string', 'description': 'The company domain, e.g. stripe.com. A full URL works too.'}}}

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'The seed URL to map.'}, 'limit': {'type': 'integer', 'maximum': 5000, 'minimum': 1, 'description': 'Max URLs to return.'}}}

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'The URL to scrape.'}, 'formats': {'type': 'array', 'items': {'enum': ['markdown', 'html', 'rawHtml', 'links', 'structured'], 'type': 'string'}, 'description': 'Which outputs to return. Defaults to markdown.'}, 'preferStructure': {'type': 'boolean', 'description': "Keep headings, lists and tables as markdown. Default false optimises for raw content and can return unstructured text on marketing and listing pages. Turn on when the document structure matters, or retry with it if `structure` came back 'plain'."}}}

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'The URL to capture.'}, 'maxAge': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': 0, 'description': 'Reuse a stored screenshot younger than this many milliseconds. Defaults to 7 days, so a repeat returns the stored PNG without re-rendering and without applying waitFor. Pass 0 to force a fresh capture.'}, 'timeout': {'type': 'integer', 'maximum': 120000, 'minimum': 1000, 'description': 'Overall time budget for the capture, in milliseconds.'}, 'waitFor': {'type': 'integer', 'maximum': 30000, 'minimum': 0, 'description': 'Extra milliseconds to let the page settle before capture.'}, 'fullPage': {'type': 'boolean', 'description': 'Capture the whole scrollable page rather than the viewport.'}, 'viewport': {'enum': ['desktop', 'laptop', 'tablet', 'mobile'], 'type': 'string', 'description': 'Screen size to render at. Defaults to desktop (1920x1080). Ignored when width or height are given.'}, 'viewportWidth': {'type': 'integer', 'maximum': 3840, 'minimum': 320, 'description': 'Exact viewport width in pixels. Overrides viewport.'}, 'viewportHeight': {'type': 'integer', 'maximum': 2160, 'minimum': 240, 'description': 'Exact viewport height in pixels. Overrides viewport. With fullPage the capture still extends to the full page height.'}}}

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['query'], 'properties': {'limit': {'type': 'integer', 'maximum': 15, 'minimum': 1, 'description': 'Max results (default 5).'}, 'query': {'type': 'string', 'description': 'The search query.'}, 'scrapeResults': {'type': 'boolean', 'description': 'Also scrape each result to markdown, 1 extra credit per page (default false).'}, 'preferStructure': {'type': 'boolean', 'description': 'Keep headings, lists and tables in each scraped result.'}}}

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['domain'], 'properties': {'domain': {'type': 'string', 'description': 'The domain to read, e.g. stripe.com. A full URL works too.'}}}