chii
983259836d
docs: 联网搜索服务架构方案全套（plan-final/design-arch/选型决策/整合导览/MCP文档/部署预设/联调手册） bench: 5 方案 + 代理 + 站点矩阵本机实测工程（无密钥） 部署目标：primary mgr1 先行测试（待批准后执行）
6 lines
5.5 KiB
JSON
6 lines
5.5 KiB
JSON
{"id": 15, "slug": "baike", "group": "domestic", "channel": "trafilatura-http", "start_url": "https://baike.baidu.com/item/%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD/9180", "used_url": "https://baike.baidu.com/item/%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD/9180", "discovered_url": null, "http_status": 403, "final_url": "https://baike.baidu.com/item/%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD/9180", "title": "百度安全验证", "title_ok": false, "text_len": 0, "html_len": 2514, "extractable": false, "intercept": "captcha", "elapsed_s": 0.147, "redirect_chain": [], "error": "HTTPError 403", "header_keys": ["Connection", "Content-Encoding", "Content-Length", "Content-Security-Policy-Report-Only", "Content-Type", "Date", "Server", "Set-Cookie"], "text_head": "", "scenario": "知识页", "known_risk": null}
|
||
{"id": 16, "slug": "zhihu", "group": "domestic", "channel": "trafilatura-http", "start_url": "https://www.zhihu.com/question/19550264", "used_url": "https://www.zhihu.com/question/19550264", "discovered_url": null, "http_status": 403, "final_url": "https://www.zhihu.com/question/19550264", "title": "", "title_ok": false, "text_len": 35, "html_len": 628, "extractable": false, "intercept": "waf", "elapsed_s": 0.138, "redirect_chain": [], "error": "HTTPError 403", "header_keys": ["Connection", "Date", "EO-Cache-Status", "EO-LOG-UUID", "Transfer-Encoding", "access-control-allow-credentials", "access-control-allow-methods", "alt-svc", "content-encoding", "content-type", "referrer-policy", "server", "set-cookie", "vary", "x-secng-response"], "text_head": "知乎，让每一次点击都充满意义 —— 欢迎来到知乎，发现问题背后的世界。", "scenario": "舆情", "known_risk": null}
|
||
{"id": 17, "slug": "govcn", "group": "domestic", "channel": "trafilatura-http", "start_url": "https://www.gov.cn/zhengce/content/202608/content_7078477.htm", "used_url": "https://www.gov.cn/zhengce/content/202608/content_7078477.htm", "discovered_url": null, "http_status": 200, "final_url": "https://www.gov.cn/zhengce/content/202608/content_7078477.htm", "title": "国务院关于修改《住房公积金管理条例》的决定_城乡建设（含住房）_中国政府网", "title_ok": true, "text_len": 0, "html_len": 48959, "extractable": false, "intercept": "empty", "elapsed_s": 0.165, "redirect_chain": [], "error": null, "header_keys": ["Access-Control-Allow-Credentials", "Access-Control-Allow-Headers", "Access-Control-Allow-Methods", "Access-Control-Allow-Origin", "Connection", "Content-Encoding", "Content-Type", "Date", "Transfer-Encoding", "Vary", "X-Cache", "X-Ser"], "text_head": "", "scenario": "政策", "known_risk": null}
|
||
{"id": 18, "slug": "newscn", "group": "domestic", "channel": "trafilatura-http", "start_url": "https://www.news.cn/", "used_url": "https://english.news.cn/home.htm", "discovered_url": "https://english.news.cn/home.htm", "http_status": 200, "final_url": "https://english.news.cn/home.htm", "title": "Xi attends SCO summit", "title_ok": true, "text_len": 151, "html_len": 42566, "extractable": false, "intercept": "none", "elapsed_s": 0.346, "redirect_chain": [], "error": null, "header_keys": ["Accept-Ranges", "Connection", "Content-Encoding", "Content-Length", "Content-Type", "Date", "Vary", "X-Cache", "X-Ser"], "text_head": "Chinese President Xi Jinping attended the 26th Meeting of the Council of Heads of State of the Shanghai Cooperation Organization (SCO) held on Tuesday.", "scenario": "行业资讯", "known_risk": null}
|
||
{"id": 19, "slug": "kr36", "group": "domestic", "channel": "trafilatura-http", "start_url": "https://www.36kr.com/", "used_url": "https://www.36kr.com/", "discovered_url": null, "http_status": 200, "final_url": "https://www.36kr.com/", "title": "", "title_ok": false, "text_len": 60, "html_len": 17501, "extractable": false, "intercept": "captcha", "elapsed_s": 0.389, "redirect_chain": [], "error": null, "header_keys": ["Cache-Control", "Connection", "Content-Length", "Content-Type", "Date", "Proxy-Status", "Server", "Vary", "X-TT-System-Error", "server-timing"], "text_head": "火山引擎 \n\n 正在进行安全检测...\n\n为保障您的访问安全，系统正在检测当前网络环境，该过程通常需要几秒钟，请耐心等待", "scenario": "行业资讯", "known_risk": null}
|
||
{"id": 20, "slug": "weibo", "group": "domestic", "channel": "trafilatura-http", "start_url": "https://weibo.com/rmrb", "used_url": "https://weibo.com/rmrb", "discovered_url": null, "http_status": 200, "final_url": "https://passport.weibo.com/visitor/visitor?entry=miniblog&a=enter&url=https%3A%2F%2Fweibo.com%2Frmrb&domain=weibo.com&ua=Mozilla%2F5.0%20%28Macintosh%3B%20Intel%20Mac%20OS%20X%2010_15_7%29%20AppleWebKit%2F537.36%20%28KHTML%2C%20like%20Gecko%29%20Chrome%2F151.0.7922.109%20Safari%2F537.36&_rand=1788243882346&sudaref=", "title": "Sina Visitor System", "title_ok": false, "text_len": 0, "html_len": 9062, "extractable": false, "intercept": "redirect", "elapsed_s": 0.344, "redirect_chain": [{"status": 302, "from": "https://weibo.com/rmrb", "to": "https://passport.weibo.com/visitor/visitor?entry=miniblog&a=enter&url=https%3A%2F%2Fweibo.com%2Frmrb&domain=weibo.com&ua=Mozilla%2F5.0%20%28Macintosh%3B%20Intel%20Mac%20OS%20X%2010_15_7%29%20AppleWebKit%2F537.36%20%28KHTML%2C%20like%20Gecko%29%20Chrome%2F151.0.7922.109%20Safari%2F537.36&_rand=1788243882346&sudaref="}], "error": null, "header_keys": ["ALB-X-Request-ID", "Cache-Control", "Connection", "Content-Encoding", "Content-Security-Policy", "Content-Type", "Date", "Expires", "Pragma", "Server", "Strict-Transport-Security", "Transfer-Encoding", "Vary"], "text_head": "", "scenario": "舆情", "known_risk": null}
|