{"slug":"agent-data-tools-revmesh2074-workers-dev-sitemap-d8717f","title":"Read one public XML sitemap or sitemap index as structured URLs and source-repor","host":"agent-data-tools.revmesh2074.workers.dev","method":"GET","resource":"https://agent-data-tools.revmesh2074.workers.dev/sitemap","category":"code","description":"Read one public XML sitemap or sitemap index as structured URLs and source-reported dates. Supports gzip, substring filtering and pagination. Maximum 512 KiB expanded input and 1000 entries. Does not crawl pages or follow child sitemaps. Invalid XML and execution errors are not charged; a valid empt","price_listed":0.002,"price_asked":0.002,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":33,"reported_calls_30d":3,"reported_payers_30d":2,"networks":["eip155:137","eip155:42161","eip155:8453","solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"method":"GET","queryParams":{"url":"https://www.sitemaps.org/sitemap.xml"},"type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"method":{"enum":["GET"],"type":"string"},"queryParams":{"properties":{"contains":{"description":"Optional case-insensitive URL substring, at most 200 characters","examples":["/protocol"],"type":"string"},"maxUrls":{"description":"Reported matching locations examined in one page (1-100, default 25); invalid/nonpublic locations may reduce returned entries","examples":[25],"type":"integer"},"offset":{"description":"Offset into distinct reported matching locations (0-1000, default 0); use nextOffset to continue","examples":[0],"type":"integer"},"url":{"description":"Absolute public HTTP(S) XML sitemap URL; child sitemaps are not fetched automatically","examples":["https://www.sitemaps.org/sitemap.xml"],"type":"string"}},"required":["url"],"type":"object"},"type":{"const":"http","type":"string"}},"required":["type","method"],"type":"object"},"output":{"properties":{"example":{"properties":{"contains":{"maxLength":200,"type":"string"},"contentHash":{"pattern":"^sha256:[a-f0-9]{64}$","type":"string"},"duplicateReportedLocations":{"minimum":0,"type":"integer"},"entries":{"items":{"properties":{"lastModified":{"description":"Source-reported value; not a verified modification time.","maxLength":80,"type":["string","null"]},"url":{"maxLength":2048,"type":"string"}},"required":["url","lastModified"],"type":"object"},"maxItems":100,"type":"array"},"fetchedAt":{"type":"string"},"finalUrl":{"type":"string"},"format":{"const":"text"},"hasMore":{"type":"boolean"},"hashFormat":{"const":"text"},"kind":{"enum":["urlset","sitemapindex"]},"matchingReportedLocations":{"description":"Distinct reported locations matching contains, before public-URL validation of the selected page.","minimum":0,"type":"integer"},"missingOrInvalidLocations":{"minimum":0,"type":"integer"},"nextOffset":{"minimum":0,"type":["integer","null"]},"offset":{"minimum":0,"type":"integer"},"rejectedLocationsInPage":{"minimum":0,"type":"integer"},"reportedEntries":{"maximum":1000,"minimum":0,"type":"integer"},"sourceHash":{"pattern":"^sha256:[a-f0-9]{64}$","type":"string"},"text":{"type":"string"},"uniqueReportedLocations":{"maximum":1000,"minimum":0,"type":"integer"},"url":{"type":"string"},"warnings":{"items":{"type":"string"},"type":"array"}},"required":["url","finalUrl","kind","entries","reportedEntries","uniqueReportedLocations","missingOrInvalidLocations","duplicateReportedLocations","rejectedLocationsInPage","matchingReportedLocations","contains","offset","nextOffset","hasMore","warnings","text","format","hashFormat","contentHash","sourceHash","fetchedAt"],"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-10-24","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.002,"price_match":true,"latency_ms":33,"error":null}],"description_full":"Read one public XML sitemap or sitemap index as structured URLs and source-reported dates. Supports gzip, substring filtering and pagination. Maximum 512 KiB expanded input and 1000 entries. Does not crawl pages or follow child sitemaps. Invalid XML and execution errors are not charged; a valid empty match is charged. Use to find which pages of a docs site to read before calling /extract.","last_updated":"2026-10-22T20:26:11.7Z","schemes":["exact"]}