{ "domain": "huaweicloud.com", "scanned_at": "2026-08-22T03:30:31.000Z", "score": 69, "fetch_ok": true, "http_status": 200, "final_url": "https://www.huaweicloud.com/", "html_bytes": 210862, "note": null, "grade": "C", "dimensions": { "reach": 40, "read": 19, "structure": 9, "attribute": 1 }, "blocks_training": 0, "blocks_answer": 0, "ua_blocked": false, "has_llms_txt": false, "llms_txt": { "present": false, "valid": false, "bytes": 0, "sections": 0, "links": 0, "issues": [] }, "sitemap": { "present": true, "source": "/sitemap.xml", "urls": 1518 }, "edge": "Cloudflare", "words_without_javascript": 2426, "schema_types": [], "bots": [ { "id": "gptbot", "label": "GPTBot", "operator": "OpenAI", "purpose": "train", "allowed": true, "rule": null, "probe_status": 200, "probe_blocked": false }, { "id": "oai-searchbot", "label": "OAI-SearchBot", "operator": "OpenAI", "purpose": "search", "allowed": true, "rule": null, "probe_status": 200, "probe_blocked": false }, { "id": "chatgpt-user", "label": "ChatGPT-User", "operator": "OpenAI", "purpose": "assist", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "oai-adsbot", "label": "OAI-AdsBot", "operator": "OpenAI", "purpose": "assist", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "claudebot", "label": "ClaudeBot", "operator": "Anthropic", "purpose": "train", "allowed": true, "rule": null, "probe_status": 200, "probe_blocked": false }, { "id": "claude-user", "label": "Claude-User", "operator": "Anthropic", "purpose": "assist", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "claude-searchbot", "label": "Claude-SearchBot", "operator": "Anthropic", "purpose": "search", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "anthropic-ai", "label": "anthropic-ai", "operator": "Anthropic", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "google-extended", "label": "Google-Extended", "operator": "Google", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "googlebot", "label": "Googlebot", "operator": "Google", "purpose": "search", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "googlebot-news", "label": "Googlebot-News", "operator": "Google", "purpose": "search", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "google-cloudvertexbot", "label": "Google-CloudVertexBot", "operator": "Google", "purpose": "assist", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "googleother", "label": "GoogleOther", "operator": "Google", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "applebot", "label": "Applebot", "operator": "Apple", "purpose": "search", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "applebot-extended", "label": "Applebot-Extended", "operator": "Apple", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "bingbot", "label": "Bingbot", "operator": "Microsoft", "purpose": "search", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "msnbot", "label": "msnbot", "operator": "Microsoft", "purpose": "search", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "perplexitybot", "label": "PerplexityBot", "operator": "Perplexity", "purpose": "search", "allowed": true, "rule": null, "probe_status": 200, "probe_blocked": false }, { "id": "perplexity-user", "label": "Perplexity-User", "operator": "Perplexity", "purpose": "assist", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "meta-externalagent", "label": "Meta-ExternalAgent", "operator": "Meta", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "meta-externalfetcher", "label": "Meta-ExternalFetcher", "operator": "Meta", "purpose": "assist", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "facebookbot", "label": "FacebookBot", "operator": "Meta", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "meta-webindexer", "label": "Meta-WebIndexer", "operator": "Meta", "purpose": "search", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "meta-externalads", "label": "Meta-ExternalAds", "operator": "Meta", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "facebookexternalhit", "label": "facebookexternalhit", "operator": "Meta", "purpose": "assist", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "bytespider", "label": "Bytespider", "operator": "ByteDance", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "tiktokspider", "label": "TikTokSpider", "operator": "ByteDance", "purpose": "assist", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "amazonbot", "label": "Amazonbot", "operator": "Amazon", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "amzn-searchbot", "label": "Amzn-SearchBot", "operator": "Amazon", "purpose": "search", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "amzn-user", "label": "Amzn-User", "operator": "Amazon", "purpose": "assist", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "ccbot", "label": "CCBot", "operator": "Common Crawl Foundation", "purpose": "archive", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "diffbot", "label": "Diffbot", "operator": "Diffbot", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "omgili", "label": "omgili", "operator": "Webz.io", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "omgilibot", "label": "omgilibot", "operator": "Webz.io", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "ai2bot", "label": "AI2Bot", "operator": "Allen Institute for AI", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "cohere-ai", "label": "cohere-ai", "operator": "Cohere", "purpose": "assist", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "cohere-training-data-crawler", "label": "cohere-training-data-crawler", "operator": "Cohere", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "mistralai-user", "label": "MistralAI-User", "operator": "Mistral AI", "purpose": "assist", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "mistralai-index", "label": "MistralAI-Index", "operator": "Mistral AI", "purpose": "search", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "mistralai-training", "label": "MistralAI-Training", "operator": "Mistral AI", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "duckassistbot", "label": "DuckAssistBot", "operator": "DuckDuckGo", "purpose": "assist", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "youbot", "label": "YouBot", "operator": "You.com", "purpose": "search", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "pangubot", "label": "PanguBot", "operator": "Huawei", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "timpibot", "label": "Timpibot", "operator": "Timpi", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "imagesiftbot", "label": "ImagesiftBot", "operator": "ImageSift (Hive)", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "kangaroo-bot", "label": "Kangaroo Bot", "operator": "Kangaroo LLM", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "semrushbot-ocob", "label": "SemrushBot-OCOB", "operator": "Semrush", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null }, { "id": "scrapy", "label": "Scrapy", "operator": "Zyte (open-source framework)", "purpose": "train", "allowed": true, "rule": null, "probe_status": null, "probe_blocked": null } ], "checks": [ { "id": "robots-missing", "state": "pass", "earned": 3, "weight": 3, "detail": "robots.txt served, 241 bytes, 1 group(s)." }, { "id": "robots-blocks-training", "state": "pass", "earned": 8, "weight": 8, "detail": "All 23 tracked training crawlers are allowed." }, { "id": "robots-blocks-answer-engines", "state": "pass", "earned": 12, "weight": 12, "detail": "All 24 answer-engine fetchers are allowed to retrieve pages for citation." }, { "id": "robots-blocks-all", "state": "pass", "earned": 5, "weight": 5, "detail": "The wildcard group does not disallow the entire site." }, { "id": "robots-crawl-delay", "state": "pass", "earned": 2, "weight": 2, "detail": "No Crawl-delay directive." }, { "id": "ua-block-detected", "state": "pass", "earned": 6, "weight": 6, "detail": "Live requests as 4 AI user agents were served normally." }, { "id": "meta-noindex", "state": "pass", "earned": 2, "weight": 2, "detail": "No noindex directive on the homepage." }, { "id": "meta-nosnippet", "state": "pass", "earned": 1, "weight": 1, "detail": "Snippets are not restricted by meta tags." }, { "id": "x-robots-tag", "state": "pass", "earned": 1, "weight": 1, "detail": "No restrictive X-Robots-Tag header." }, { "id": "ssr-content-thin", "state": "pass", "earned": 9, "weight": 9, "detail": "2426 words of text are present in the raw HTML. Most AI fetchers do not run JavaScript." }, { "id": "text-ratio-low", "state": "pass", "earned": 4, "weight": 4, "detail": "Text is 12.0% of the 206 KB document; 17 KB is inline script." }, { "id": "main-landmark-missing", "state": "fail", "earned": 0, "weight": 3, "detail": "No
or
element, so extractors must guess where the content starts." }, { "id": "heading-structure", "state": "fail", "earned": 0, "weight": 3, "detail": "0 H1 and 6 headings total." }, { "id": "title-quality", "state": "pass", "earned": 3, "weight": 3, "detail": "Title is 16 characters: \"华为云，用AI解行业难题-华为云\"" }, { "id": "description-missing", "state": "pass", "earned": 2, "weight": 2, "detail": "Meta description is 105 characters." }, { "id": "lang-missing", "state": "pass", "earned": 1, "weight": 1, "detail": "Declared language: zh-CN." }, { "id": "jsonld-missing", "state": "fail", "earned": 0, "weight": 7, "detail": "No JSON-LD structured data on the homepage." }, { "id": "jsonld-invalid", "state": "pass", "earned": 3, "weight": 3, "detail": "All JSON-LD blocks parse cleanly." }, { "id": "schema-type-coverage", "state": "fail", "earned": 0, "weight": 4, "detail": "No entity types that answer engines consume." }, { "id": "canonical-missing", "state": "pass", "earned": 3, "weight": 3, "detail": "Canonical: https://www.huaweicloud.com/" }, { "id": "sitemap-missing", "state": "pass", "earned": 2, "weight": 2, "detail": "Sitemap found at /sitemap.xml (1518 URLs on the first document)." }, { "id": "extractable-blocks", "state": "pass", "earned": 1, "weight": 1, "detail": "0 tables, 23 lists, 0 code blocks, 0 question headings." }, { "id": "llms-txt-missing", "state": "fail", "earned": 0, "weight": 4, "detail": "No /llms.txt." }, { "id": "author-missing", "state": "fail", "earned": 0, "weight": 3, "detail": "No author or Person entity, which weakens the authority signals answer engines use." }, { "id": "date-modified-missing", "state": "fail", "earned": 0, "weight": 3, "detail": "No publication or modification dates in structured data." }, { "id": "organization-schema-missing", "state": "fail", "earned": 0, "weight": 3, "detail": "No Organization entity, so the brand is harder to resolve to a known entity." }, { "id": "license-declared", "state": "warn", "earned": 1, "weight": 2, "detail": "No licence declaration, so reuse terms are ambiguous." } ], "report_url": "https://crawlcensus.com/site/huaweicloud.com", "license": "CC BY 4.0", "attribution": "Source: Crawl Census (crawlcensus.com)" }