{"api":"v1","generated_at":"2026-10-14T01:34:35.474Z","licence":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"TOLL, with a link to the page cited"},"page":"https://tollindex.com/e/api-qocgpiywhm-com-api-v1-tools-clean-web-content-3c42ed","pinned_page":"https://tollindex.com/e/api-qocgpiywhm-com-api-v1-tools-clean-web-content-3c42ed/at/2026-10-13T14-08Z","pinned":false,"method":"https://tollindex.com/ledger/method","snapshot_at":"2026-10-13T14:08:52.397Z","snapshot_stamp":"2026-10-13T14-08Z","endpoint":{"slug":"api-qocgpiywhm-com-api-v1-tools-clean-web-content-3c42ed","canonical_url":"https://api.qocgpiywhm.com/api/v1/tools/clean_web_content","resource":"https://api.qocgpiywhm.com/api/v1/tools/clean_web_content","http_method":"POST","type":"http","x402_version":2,"registries":["cdp"],"primary_registry":"cdp","curated_by_coinbase":false,"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 tried once in the same request. The HTTP body has correlation_id and data. The item array is data.results.","service_name":"Web Content Cleaner","declared_category":null,"declared_tags":["article","content","clean","markdown","readability"],"route_template":null,"registry_updated":"2026-10-11T17:51:21.425Z"},"derived":{"note":"fields no registry supplies; TOLL derives them and marks them derived on the page","title":"tools clean web content","category":"compute","first_observed_by_toll":"2026-10-10T21:42:09.511Z","last_observed_by_toll":"2026-10-13T14:08:52.397Z","observation_began":"2026-09-10"},"presence":{"listed_now":true,"first_absent_at":null,"delisting_confirmed_at":null,"events":[{"registry":"cdp","at":"2026-10-10T21:42:09.512Z","event":"listed"}]},"accepts":[{"registry":"cdp","ordinal":0,"network":"eip155:8453","asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","asset_name":"USD Coin","symbol":"USDC","decimals":6,"amount_display":"0.01 USDC","amount_units":0.01,"decimals_known":true,"pay_to":"0x3d9ffc73b637C46d7C7EE23b23635d0F6178A053","scheme":"upto"}],"counters":{"observed_at":"2026-10-13T14:08:52.397Z","calls_30d":18,"unique_payers_30d":4,"last_called_at":"2026-10-11T17:51:21.248Z"},"validation":{"latest":{"observed_at":"2026-10-13T09:50:14.917Z","state":"pass","failed_checks":[],"endpoint_http_status":402,"run_id":"daily-2026-10-13"},"uptime":[{"days":7,"observed":4,"passed":4,"ratio":1},{"days":30,"observed":4,"passed":4,"ratio":1},{"days":90,"observed":4,"passed":4,"ratio":1}],"history_90d":[{"observed_at":"2026-10-13T09:50:14.917Z","state":"pass","failed_checks":[],"run_id":"daily-2026-10-13","state_changed":false},{"observed_at":"2026-10-12T07:13:55.935Z","state":"pass","failed_checks":[],"run_id":"daily-2026-10-12","state_changed":false},{"observed_at":"2026-10-11T05:39:28.928Z","state":"pass","failed_checks":[],"run_id":"daily-2026-10-11","state_changed":false},{"observed_at":"2026-10-10T21:45:21.352Z","state":"pass","failed_checks":[],"run_id":"new-after-daily-2026-10-10","state_changed":true}]},"seller":{"wallet":"0x3d9ffc73b637C46d7C7EE23b23635d0F6178A053","page":"https://tollindex.com/seller/0x3d9ffc73b637C46d7C7EE23b23635d0F6178A053","endpoints":6,"hosts":1},"reports":0,"registry_record":{"cdp":[{"tags":["article","content","clean","markdown","readability"],"type":"http","accepts":[{"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","extra":{"name":"USD Coin","version":"2","facilitatorAddress":"0xE74817F4cDC15844314812B2271276E64e890fAE","assetTransferMethod":"permit2"},"payTo":"0x3d9ffc73b637C46d7C7EE23b23635d0F6178A053","amount":"10000","scheme":"upto","network":"eip155:8453","maxTimeoutSeconds":300}],"quality":{"lastCalledAt":"2026-10-11T17:51:21.248Z","l30DaysTotalCalls":18,"l30DaysUniquePayers":4},"resource":"https://api.qocgpiywhm.com/api/v1/tools/clean_web_content","extensions":{"bazaar":{"info":{"input":{"body":{"url":"https://en.wikipedia.org/wiki/HTTP_402","include_title":true,"output_format":"text"},"type":"http","method":"POST","bodyType":"json"},"output":{"type":"json","schema":{"type":"object","$defs":{"CleanItemData":{"type":"object","title":"CleanItemData","required":["content","word_count","format"],"properties":{"title":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Title","default":null},"format":{"enum":["text","markdown"],"type":"string","title":"Format"},"content":{"type":"string","title":"Content"},"word_count":{"type":"integer","title":"Word Count"}}},"CleanItemMeta":{"type":"object","title":"CleanItemMeta","required":["extraction_profile_requested","extraction_profile","fallback_used"],"properties":{"url":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Url","default":null},"retries":{"anyOf":[{"type":"integer","maximum":5,"minimum":0},{"type":"null"}],"title":"Retries","default":null,"description":"Extra attempts on the winning fetch hop. 0 = first try of that hop."},"final_url":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Final Url","default":null},"truncated":{"type":"boolean","title":"Truncated","default":false},"via_proxy":{"anyOf":[{"type":"boolean"},{"type":"null"}],"title":"Via Proxy","default":null,"description":"True if the winning fetch used hop-2 residential proxy."},"status_code":{"anyOf":[{"type":"integer"},{"type":"null"}],"title":"Status Code","default":null},"content_type":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content Type","default":null},"fallback_used":{"type":"boolean","title":"Fallback Used","description":"True if the other profile ran in this request."},"extraction_method":{"type":"string","title":"Extraction Method","default":"trafilatura"},"extraction_profile":{"$ref":"#/$defs/CleanExtractProfile","description":"Profile that filled data.content, or requested if none."},"javascript_rendered":{"anyOf":[{"type":"boolean"},{"type":"null"}],"title":"Javascript Rendered","default":null},"extraction_profile_requested":{"$ref":"#/$defs/CleanExtractProfile","description":"Extract profile the caller asked for (content or index)."}}},"CleanErrorCode":{"enum":["fetch_failed","timeout","redirect_loop","non_html","no_main_content","too_large","worker_chunk_failed","destination_denied"],"type":"string","title":"CleanErrorCode"},"CleanItemResult":{"type":"object","title":"CleanItemResult","required":["meta"],"properties":{"data":{"anyOf":[{"$ref":"#/$defs/CleanItemData"},{"type":"null"}],"default":null,"description":"Extracted text payload, or null on failure."},"meta":{"$ref":"#/$defs/CleanItemMeta","description":"Fetch and extraction metadata."},"error":{"anyOf":[{"$ref":"#/$defs/CleanErrorCode"},{"type":"null"}],"default":null,"description":"Clean error code, or null on success."},"detail":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Detail","default":null,"description":"Failure detail, or null on success."}}},"CleanExtractProfile":{"enum":["content","index"],"type":"string","title":"CleanExtractProfile","description":"Fixed extract profiles for clean tools (DEC0304 / REQ0294)."}},"title":"CleanWebContentResponse","required":["results"],"properties":{"results":{"type":"array","items":{"$ref":"#/$defs/CleanItemResult"},"title":"Results","description":"Per-item clean results."}}},"example":{"data":{"results":[{"data":{"title":"List of HTTP status codes - Wikipedia","format":"text","content":"This article lists standard and notable non-standard HTTP response status codes. 402 Payment Required is reserved for future use.","word_count":20},"meta":{"url":"https://en.wikipedia.org/wiki/HTTP_402","retries":0,"final_url":"https://en.wikipedia.org/wiki/HTTP_402","truncated":false,"via_proxy":false,"status_code":200,"content_type":"text/html; charset=UTF-8","fallback_used":false,"extraction_profile":"content","javascript_rendered":false,"extraction_profile_requested":"content"},"error":null,"detail":null}]},"correlation_id":"00000000-0000-4000-8000-000000000001"}}},"schema":{"type":"object","$defs":{"CleanWebUrlItem":{"type":"object","title":"CleanWebUrlItem","required":["url"],"properties":{"url":{"type":"string","title":"Url","format":"uri","maxLength":2083,"minLength":1,"description":"Page URL to fetch (https)."},"timeout":{"type":"integer","title":"Timeout","default":10,"maximum":12,"minimum":1,"description":"Per-item fetch timeout in seconds."},"max_length":{"anyOf":[{"type":"integer","maximum":500000,"minimum":1},{"type":"null"}],"title":"Max Length","default":null,"description":"Maximum characters of extracted content to return."},"user_agent":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"User Agent","default":null,"description":"Override User-Agent for this request. Omit to use the platform default."},"include_title":{"type":"boolean","title":"Include Title","default":true,"description":"If true, include the page title in the result."},"output_format":{"$ref":"#/$defs/CleanOutputFormat","default":"text","description":"Result format: text (default) or markdown."}},"description":"URL-fetch clean item.","additionalProperties":false},"CleanOutputFormat":{"enum":["text","markdown"],"type":"string","title":"CleanOutputFormat"}},"$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","properties":{"url":{"anyOf":[{"type":"string","format":"uri","maxLength":2083,"minLength":1},{"type":"null"}],"title":"Url","default":null,"description":"Page URL to fetch (https)."},"items":{"anyOf":[{"type":"array","items":{"$ref":"#/$defs/CleanWebUrlItem"}},{"type":"null"}],"title":"Items","default":null,"description":"Batch of items. Do not also send a single-item field."},"timeout":{"type":"integer","title":"Timeout","default":10,"maximum":12,"minimum":1,"description":"Per-item fetch timeout in seconds."},"max_length":{"anyOf":[{"type":"integer","maximum":500000,"minimum":1},{"type":"null"}],"title":"Max Length","default":null,"description":"Maximum characters of extracted content to return."},"user_agent":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"User Agent","default":null,"description":"Override User-Agent for this request. Omit to use the platform default."},"include_title":{"type":"boolean","title":"Include Title","default":true,"description":"If true, include the page title in the result."},"output_format":{"$ref":"#/$defs/CleanOutputFormat","default":"text","description":"Result format: text (default) or markdown."}}},"type":{"type":"string","const":"http"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"schema":{"type":"object"},"example":{"type":"object"}}}}}},"payment-identifier":{"info":{"required":false},"schema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["required"],"properties":{"id":{"type":"string","pattern":"^[a-zA-Z0-9_-]+$","maxLength":128,"minLength":16},"required":{"type":"boolean"}}}}},"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 tried once in the same request. The HTTP body has correlation_id and data. The item array is data.results.","lastUpdated":"2026-10-11T17:51:21.425Z","serviceName":"Web Content Cleaner","x402Version":2}]}}