百度百科
https://baike.baidu
采集机器人 (2)2023/04/01
数据采集
{ "bookSourceComment": "", "bookSourceGroup": "普通", "bookSourceName": "百度百科", "bookSourceType": 0, "bookSourceUrl": "https:\/\/baike.baidu", "bookUrlPattern": "", "customOrder": 0, "enabled": true, "enabledExplore": false, "lastUpdateTime": 1601820029543, "loginUrl": "", "ruleBookInfo": { "name": "", "tocUrl": "@js:\nbaseUrl.indexOf('error.html')>-1?'https:\/\/baike.baidu.com\/search\/none?word='+java.get('key')+'&pn=0&rn=10&enc=utf8':baseUrl" }, "ruleContent": { "content": "@js:String(org.jsoup.Jsoup.parse(result).select('h2,.reference-title,.para,.reference-list,.basic-info')).replace(\/<h2 class=\"block-title\">目录<\\\/h2>\/,'').replace(\/<h2.*?>\/g,'-----📖').replace(\/<\\\/h2>\/g,'📖-----').replace(\/<span class=\"title-prefix\">.*?span>\/g,'').replace(\/<dt class=\"basicInfo-item name\">\/g,'---------')", "imageStyle": "full", "replaceRegex": "##src=\"[^\"]+\" data-src##src" }, "ruleExplore": {}, "ruleSearch": { "author": "@js:'百度百科'", "bookList": "class.lemmaWgt-lemmaTitle-title||tag.html", "bookUrl": "", "kind": "", "name": "@get:{key}" }, "ruleToc": { "chapterList": "class.item!0:1||class.search-list@dd||class.lemmaWgt-lemmaTitle-title@tag.h1.0", "chapterName": "tag.a.0@text||tag.span@text||text", "chapterUrl": "tag.a.0@href" }, "searchUrl": "https:\/\/baike.baidu.com\/item\/{{key}}\n@js:java.put('key',key);result", "weight": 0 }