{"slug":"api-qocgpiywhm-com-api-v1-tools-clean-web-content-3b074d","title":"Use to extract the main article or document text from a single-page URL","host":"api.qocgpiywhm.com","method":"POST","resource":"https://api.qocgpiywhm.com/api/v1/tools/clean_web_content","category":"code","description":"Use to extract the main article or document text from a single-page URL. Not for homepages or hubs (Web Index Cleaner) and not a link inventory (Link Extractor). Server HTML only; JavaScript is not run. Output is text or markdown. If the requested extract has no main content, the other profile is tr","price_listed":0.01,"price_asked":0.01,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":603,"reported_calls_30d":3,"reported_payers_30d":3,"networks":["eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"include_title":true,"output_format":"text","url":"https://en.wikipedia.org/wiki/HTTP_402"},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$defs":{"CleanOutputFormat":{"enum":["text","markdown"],"title":"CleanOutputFormat","type":"string"},"CleanWebUrlItem":{"additionalProperties":false,"description":"URL-fetch clean item.","properties":{"include_title":{"default":true,"description":"If true, include the page title in the result.","title":"Include Title","type":"boolean"},"max_length":{"anyOf":[{"maximum":500000,"minimum":1,"type":"integer"},{"type":"null"}],"default":null,"description":"Maximum characters of extracted content to return.","title":"Max Length"},"output_format":{"$ref":"#/$defs/CleanOutputFormat","default":"text","description":"Result format: text (default) or markdown."},"timeout":{"default":10,"description":"Per-item fetch timeout in seconds.","maximum":12,"minimum":1,"title":"Timeout","type":"integer"},"url":{"description":"Page URL to fetch (https).","format":"uri","maxLength":2083,"minLength":1,"title":"Url","type":"string"},"user_agent":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"description":"Override User-Agent for this request. Omit to use the platform default.","title":"User Agent"}},"required":["url"],"title":"CleanWebUrlItem","type":"object"}},"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"include_title":{"default":true,"description":"If true, include the page title in the result.","title":"Include Title","type":"boolean"},"items":{"anyOf":[{"items":{"$ref":"#/$defs/CleanWebUrlItem"},"type":"array"},{"type":"null"}],"default":null,"description":"Batch of items. Do not also send a single-item field.","title":"Items"},"max_length":{"anyOf":[{"maximum":500000,"minimum":1,"type":"integer"},{"type":"null"}],"default":null,"description":"Maximum characters of extracted content to return.","title":"Max Length"},"output_format":{"$ref":"#/$defs/CleanOutputFormat","default":"text","description":"Result format: text (default) or markdown."},"timeout":{"default":10,"description":"Per-item fetch timeout in seconds.","maximum":12,"minimum":1,"title":"Timeout","type":"integer"},"url":{"anyOf":[{"format":"uri","maxLength":2083,"minLength":1,"type":"string"},{"type":"null"}],"default":null,"description":"Page URL to fetch (https).","title":"Url"},"user_agent":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"description":"Override User-Agent for this request. Omit to use the platform default.","title":"User Agent"}},"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"type":"object"},"schema":{"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-10-11","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.01,"price_match":true,"latency_ms":603,"error":null}],"description_full":"Use to extract the main article or document text from a single-page URL. Not for homepages or hubs (Web Index Cleaner) and not a link inventory (Link Extractor). Server HTML only; JavaScript is not run. Output is text or markdown. If the requested extract has no main content, the other profile is tried once in the same request. The HTTP body has correlation_id and data. The item array is data.results.","last_updated":"2026-10-11T17:51:21.425Z","schemes":["upto"]}