[ { "path": ".gitignore", "content": ".DS_Store\nnode_modules\nlinks\ntemp" }, { "path": ".npmignore", "content": "links\ntemp\n.DS_Store\ntest\n" }, { "path": "README.MD", "content": "# we-extract\n\n## 介绍\n\n`we-extract` 用以解析微信公众号文章的账号及文章信息，居家旅行、采集微信公众号文章必备工具。\n\n`we-extract` 是微信公众号 RSS 订阅服务 `WeRss` 的核心解析工具，欢迎使用：\n\n

\n
\n \n \n \n

\n\n## 安装\n\n```\nnpm install we-extract\n\n// or\n\nyarn add we-extract\n```\n\n## 使用\n\n> Node 版本需要支持 async\n\n\n``` js\nconst extract = require('we-extract').extract\n\nconst rs = await extract('微信文章 url 或者 文章内容')\n\n// 选项\nconst rs = await extract('微信文章 url 或者 文章内容', {\n shouldReturnContent: true, // 是否返回内容，默认返回\n shouldExtractMpLinks: false, // v2.1.0 是否返回文章中出现的所有公众号文章链接，如果为 true，将返回 mp_links 数组\n shouldExtractTags: false, // v2.2.0 是否解析文章中的收录标签\n shouldExtractRepostMeta: false // v2.2.3 是否解析转载文章来源\n})\n```\n\n## 返回结果说明\n\n\n> 正确返回\n\n``` js\n{\n done: true,\n code: 0,\n data: {\n account_name: '微信派',\n account_alias: 'wx-pai',\n account_avatar: 'http://wx.qlogo.cn/mmhead/Q3auHgzwzM7Xb5Qbdia5AuGTX4AeZSWYlv5TEqD1FicUDOrnEIwVak1A/132',\n account_description: '微信第一手官方活动信息发布，线下沙龙活动在线互动平台。独家分享微信公众平台优秀案例，以及权威专家的精彩观点。',\n account_id: 'gh_bc5ec2ee663f',\n account_biz: 'MjM5NjM4MDAxMg==',\n account_biz_number: 2396380012,\n account_qr_code: 'https://open.weixin.qq.com/qr/code?username=gh_bc5ec2ee663f',\n msg_has_copyright: false, // 是否原创\n msg_content: '省略的文章内容',\n msg_author: null, // 作者\n msg_sn: '9a0a54f2e7c8ac4019812aa78bd4b3e0',\n msg_idx: 1,\n msg_mid: 2655078412,\n msg_title: '重磅 | 微信订阅号全新改版上线！',\n msg_desc: '今后，头图也很重要',\n msg_link: 'http://mp.weixin.qq.com/s?__biz=MjM5NjM4MDAxMg==&mid=2655078412&idx=1&sn=9a0a54f2e7c8ac4019812aa78bd4b3e0&chksm=bd5fc40f8a284d19360e956074ffced37d8e2d78cb01a4ecdfaae40247823e7056b9d31ae3ef#rd',\n msg_source_url: null, // 音频，视频时，此处为音频、视频链接\n msg_cover: 'http://mmbiz.qpic.cn/mmbiz_jpg/OiaFLUqewuIDldpxsV3ZYJzzyH9HTFsSwOEPX82WEvBZozGiam3LbRSzpIIKGzj72nxjhLjnscWsibDPFmnpFZykg/0?wx_fmt=jpeg',\n msg_article_type: null, // 文章分类\n msg_publish_time: '2018-06-20T10:52:35.000Z', // date 类型\n msg_publish_time_str: '2018/06/20 18:52:35',\n msg_type: 'post', // 可能为 post text repost voice video image\n mp_links: [{ // 在 shouldExtractMpLinks = true 时返回\n title: '',\n href: ''\n }],\n tags: [{ // 在 shouldExtractTags = true 时返回\n id: '',\n url: '',\n name: '',\n count: 1\n }],\n repost_meta: { // 在 shouldExtractRepostMeta = true 时返回\n account_name: '文章来源账号名字'\n }\n }\n}\n```\n\n> 错误返回\n\n``` js\n{\n done: false,\n code: 2002,\n msg: '链接已过期'\n}\n```\n\n## 常见错误\n\n`we-extract` 定义了详细的错误信息方便开发和出错处理，`1` 开头错误表示可能需要重试(或者暂时将内容保存下来 debug)，`2` 表示没有疑问的错误，可以不处理。\n\n请使用 code(数字类型) 来判断而不是 message 内容，因为 message 可能会变化。\n\n``` js\nmodule.exports = {\n '1000': '解析失败，可能文章内容不完整',\n '1001': '字段缺失',\n '1002': '请求文章内容失败',\n '1003': '请求文章内容为空',\n '1004': '访问过于频繁(URL模式)', // 可以换 ip 重新请求，注意与 2010 的区别\n '1005': 'js 变量解析出错',\n\n '2001': '参数缺失',\n '2002': '链接已过期',\n '2003': '该内容被投诉且经审核涉嫌侵权，无法查看',\n '2004': '公众号迁移但文章未同步',\n '2005': '该内容已被发布者删除',\n '2006': '此内容因违规无法查看',\n '2007': '涉嫌违反相关法律法规和政策发送失败',\n '2008': '微信文章系统出错',\n '2009': '链接不正确',\n '2010': '访问过于频繁(HTML模式)', // 解析参数为直接的文章内容，此时该篇内容已经无效，可以丢弃\n '2011': '由用户投诉并经平台审核，涉嫌过度营销、骚扰用户',\n '2012': '此帐号已被屏蔽',\n '2013': '此帐号已自主注销',\n '2014': '不实信息',\n '2016': '冒名侵权'\n}\n\n```\n\n## 经验\n\n+ 一个微信由 biz+mid+idx 组成，mid 在单个公众号内唯一。\n+ 文章所属账号信息以文章解析结果为准，采集搜狗时不要相信账号名字，因为搜狗显示的可能是改名或者迁移前的账号信息。\n+ 如果在搜狗微信搜不到账号，极有可能是因为公众号改了名字，试试以前的名字应该能搜索到。\n+ 微信链接的 search 拼接符可能为 `&` 需要做一个替换处理，否则解析链接参数时会有问题。\n+ 一个 ip 获取微信文章内容有限制，需要限制速率或者轮换 ip。\n\n\n## 链接类型\n\n图片：https://mp.weixin.qq.com/s/5tpbsFR1k_3744P0Egdnxg" }, { "path": "errors.js", "content": "module.exports = {\n '1000': '解析失败，可能文章内容不完整',\n '1001': '字段缺失',\n '1002': '请求文章内容失败',\n '1003': '请求文章内容为空',\n '1004': '访问过于频繁(url模式)', // 可以换 ip 重新请求，注意与 2010 的区别\n '1005': 'js 变量解析出错',\n '1006': '链接重定向', // 开启不 follow transfer link 后会有这个错误\n\n '2001': '参数缺失',\n '2002': '链接已过期',\n '2003': '该内容被投诉且经审核涉嫌侵权，无法查看',\n '2004': '公众号迁移但文章未同步',\n '2005': '该内容已被发布者删除',\n '2006': '此内容因违规无法查看',\n '2007': '涉嫌违反相关法律法规和政策发送失败',\n '2008': '微信文章系统出错',\n '2009': '链接不正确',\n '2010': '访问过于频繁(HTML模式)', // 解析参数为直接的文章内容，此时该篇内容已经无效，可以丢弃\n '2011': '由用户投诉并经平台审核，涉嫌过度营销、骚扰用户',\n '2012': '帐号已被屏蔽, 内容无法查看',\n '2013': '此帐号已自主注销',\n '2014': '不实信息',\n '2015': '此帐号处于帐号迁移流程中',\n '2016': '冒名侵权'\n}\n" }, { "path": "index.js", "content": "const qs = require('qs')\nconst dayjs = require('dayjs')\nconst request = require('request-promise')\nconst cheerio = require('cheerio')\nconst parseUrl = require('./parse-wechat-url')\nconst errors = require('./errors')\nconst unescape = require('lodash.unescape')\nconst {\n getParameterByName,\n normalizeUrl\n} = require('./util')\n\nconst video = require('./video')\n\nconst defaultConfig = {\n shouldReturnRawMeta: false,\n shouldReturnContent: true,\n shouldFollowTransferLink: true,\n shouldExtractMpLinks: false,\n shouldExtractTags: false,\n shouldExtractRepostMeta: false\n}\n\nconst basic = {}\nbasic.accountId = ''\nbasic.accountAvatar = ''\n\nbasic.accountBiz = null\nbasic.accountBizNumber = null\nbasic.accountName = null\n\nconst getError = function(code) {\n return {\n done: false,\n code: code,\n msg: errors[code]\n }\n}\n\nconst extract = async function(html, options = {}) {\n const {\n shouldReturnRawMeta,\n shouldReturnContent,\n shouldFollowTransferLink,\n shouldExtractMpLinks,\n shouldExtractTags,\n shouldExtractRepostMeta\n } = Object.assign({}, defaultConfig, options)\n\n let paramType = 'HTML' // 参数为 URL 还是 HTML\n let url = null\n let rawUrl = null\n\n if (options.url) {\n url = normalizeUrl(options.url)\n }\n\n let type = 'post'\n let hasCopyright = false\n let shareContentTpl\n\n if (!html) {\n return getError(2001)\n }\n\n // 参数错误\n\n // 支持地址\n if (/^http/.test(html)) {\n html = normalizeUrl(html)\n if (!/http(s?):\\/\\/mp.weixin.qq.com/.test(html) && !/http(s?):\\/\\/weixin.sogou.com/.test(html)) {\n return getError(2009)\n }\n paramType = 'URL'\n rawUrl = html\n if (!url) {\n url = html\n }\n let host = 'mp.weixin.qq.com'\n if (/http(s?):\\/\\/weixin.sogou.com/.test(html)) {\n host = 'weixin.sogou.com'\n }\n try {\n html = await request({\n uri: html,\n method: 'GET',\n headers: {\n 'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36',\n 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',\n 'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',\n 'Cache-Control': 'max-age=0',\n 'Connection': 'keep-alive',\n 'Host': host\n }\n })\n\n // unknown purpose\n // if (html.includes('location.replace')) {\n // const rs = html.match(/([\\s\\S]*?)<\\/script>/gi)\n // if (rs && rs[0]) {\n // const code = rs[0].split('\\n').filter(one => {\n // return !one.includes('location.replace') && !one.includes('script>')\n // }).join('\\n') + '\\n return url;'\n\n // try {\n // const fn = new Function(code)\n // return await extract(fn(), options)\n // } catch (e) {\n // return getError(1005)\n // }\n // }\n // }\n } catch (e) {\n return getError(1002)\n }\n } else {\n html = html.replace(/\\\\n/g, '')\n }\n\n if (!html) {\n return getError(1003)\n }\n\n if (html.includes('访问过于频繁') && !html.includes('js_content')) {\n return paramType === 'URL' ? getError(1004) : getError(2010)\n } else if (html.includes('链接已过期') && !html.includes('js_content')) {\n return getError(2002)\n } else if (html.includes('被投诉且经审核涉嫌侵权，无法查看')) {\n return getError(2003)\n } else if (html.includes('该公众号已迁移')) {\n const match = html.match(/var\\stransferTargetLink\\s=\\s'(.*?)';/)\n if (match && match[1]) {\n if (shouldFollowTransferLink) {\n return await extract(match[1])\n } else {\n return {\n ...getError(1006),\n url: match[1]\n }\n }\n } else {\n return getError(2004)\n }\n } else if (html.includes('该内容已被发布者删除')) {\n return getError(2005)\n } else if (html.includes('此内容因违规无法查看')) {\n return getError(2006)\n } else if (html.includes('此内容发送失败无法查看')) {\n return getError(2007)\n } else if (html.includes('由用户投诉并经平台审核，涉嫌过度营销、骚扰用户')) {\n return getError(2011)\n } else if (html.includes('此帐号已被屏蔽') && !html.includes('id=\"js_content\"')) {\n return getError(2012)\n } else if (html.includes('此帐号已自主注销') && !html.includes('id=\"js_content\"')) {\n return getError(2013)\n } else if (!html.includes('id=\"js_content\"') && html.includes('此帐号处于帐号迁移流程中')) {\n return getError(2015)\n } else if (html.includes('page_rumor') && !html.includes('id=\"js_content\"')) {\n return getError(2014)\n } else if (html.includes('投诉类型') && html.includes('冒名侵权')) {\n return getError(2016)\n } else if (!html.includes('id=\"js_content\"') && html.includes('参数错误') && html.includes('appmsg/error.html')) {\n return getError(2009)\n } else if (!html.includes('id=\"js_content\"') && !html.includes('id=\\\\\"js_content\\\\\"')) {\n // http://mp.weixin.qq.com/s?__biz=MjM5ODIyMTE0MA==&mid=2650971473&idx=1&sn=f529f2a74fac89ed2a8ca8f7a44d93b3&chksm=bd38396a8a4fb07ce4ebab564de2ef01c2d50d60a225328c987cbf66e6167d067bc45f1527d3#rd\n // 图片类型但是没有 js_content 容器\n if (html.includes('cover_url')) {\n type = 'image'\n } else {\n return getError(1000)\n }\n }\n\n html = html.replace('>微信号', ' id=\"append-account-alias\">微信号')\n .replace('>功能介绍', ' id=\"append-account-desc\">功能介绍')\n .replace(/\\n\\s+\n \n\n \n \n\n\n\n\n\n \n\n \n \n\n\n\n\n\n\n\n \n\n\n\n\n\n\n\n\n\n\n\n\n
\n\n
\n\n
\n\n\n\n\t\t
\n\n\t\t
\n\n\n\n\n\n
\n\n

\n\n\n\n两家大行行长空缺\n

\n
\n \n 轻金融\n \n\n \n \n 轻金融 \n
\n
\n 轻金融\n \"\"\n\n

\n \n Qjinrong\n

\n\n

\n \n 影响力最大的银行自媒体之一，深度影响大量银行业、金融科技行业中高层，覆盖30万+银行从业者。\n

\n\n
\n \n \n \n \n
\n \n \n
\n\n\n
\n\n
收录于话题
\n
\n
\n
\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
\n\n\n\n\n\n\n

年末银行业又一起重量级高管变动



来源：轻金融

近日，多家媒体报道，工商银行行长谷澍拟接替周慕冰，担任农业银行党委书记，并将担任董事长一职，成为2020年末又一次银行高管重量级人事变动。53岁的谷澍，也将成为五大行中最年轻的董事长。
据21世纪经济报道，目前，邮储银行是六大行中领导团队人数最多、最齐的银行；中行、建行、交行均是“一正三副”或“一正四副”；而建行和工行一样出现了行长的空缺。
轻金融据Wind资讯统计，整理了六大行目前高管与其他重要人员情况，以及2020年高管团队变动情况。详情如下：

一、工行

1、工行高管团队及其他重要人员



2、2020年工行高管及重要人员变动

二、建行

1、建行高管团队及其他重要人员



2、2020年建行高管及重要人员变动

三、农行

1、农行高管团队及其他重要人员


2、2020年农行高管及重要人员变动

四、中行

1、中行高管团队及其他重要人员


2、2020年中行高管及重要人员人变动

五、交行

1、交行高管团队及其他重要人员


2、2020年交行高管及重要人员变动


六、邮储银行

邮储银行高管团队及其他重要人员：一正六副



【轻金融好文】

1、谁是银行业金融科技之王？

2、2019银行业十佳文章【轻金融】

3、300万银行人迎来一位“新同事”

4、2020银行金融科技最新布局！

5、30万亿工行金融科技革命！

6、某城商行消费贷规模，比农行、招行还大

7、银行云大爆发！三类玩家角逐千亿市场

8、各大银行零售业务含金量比拼

9、工行、建行的“较量” | 轻金融

10、互联网银行：ROE最高的民营银行“物种”

11、中小银行正遭遇一场金融科技生死战

12、中小银行信用卡业务报告！（史上最全）

\n
\n\n \n\n\n
\n\n\n\n
\n\n
\n\n\n\n\n
\n
预览时标签不可点
\n\n\n\n\n\n
    \n\n\n\n\n
    \n
    \n
    收录于话题 #
    \n 个\n
    \n
    \n \n \n 上一篇\n \n \n \n \n \n 下一篇\n \n \n \n
    \n
    \n\n\n\n\n\n\n
    \n
    \n
    \n\n\n\n\n
    \n 阅读\n \n
    \n
    \n
    \n
    \n
    \n\n \n \n \n\n\n \n \n \n
    \n\n\n \n \n \n\n\n \n\n \n \n
    \n
    \n\n
    \n
    \n
    \n
    \n
    \n 已同步到看一看写下你的想法\n
    \n
    \n

    \n \n 前往“发现”-“看一看”浏览“朋友在看”\n

    \n

    \n \n

    \n \n
    \n
    \n
    \n
    \n
    \n
    \n
    \n
    看一看入口已关闭
    \n
    \n 在“设置”-“通用”-“发现页管理”打开“看一看”入口
    \n
    \n 我知道了\n
    \n
    \n
    \n\n
    \n
    \n
    \n \n

    已发送

    \n
    \n
    \n\n
    \n
    \n
    \n
    \n
    \n \n
    \n

    发送到看一看

    \n
    \n \n
    \n
    \n
    \n
    \n 两家大行行长空缺\n
    \n
    \n \n
    \n
    \n 最多200字，当前共字\n
    \n
    \n
    \n
    \n\n
    \n
    \n
    \n \n

    发送中

    \n
    \n
    \n\n\n\n
    \n
    \n\n
    \n\n\n\n
    \n
    \n\n \n\n\n\n
    \n\n
    \n\n
    \n\n\n\n
    \n\n\n\n
    \n\n
    \n
    \n
    \n
    \n
    \n\n\n
    \n
    \n
    \n \n

    微信扫一扫
    关注该公众号

    \n
    \n
    \n
    \n
    \n
    \n\n\n\n
    \n
    \n
    \n \n 微信扫一扫
    使用小程序
    \n
    \n
    \n
    \n
    \n
    \n
    \n \n
    \n
    \n\n
    \n 取消\n 允许\n
    \n
    \n
    \n\n\n\n
    \n
    \n
    \n
    \n 微信版本过低\n
    \n
    当前微信版本不支持该功能，请升级至最新版本。
    \n\n
    \n 我知道了\n 前往更新\n
    \n
    \n
    \n\n
    \n
    \n
    \n
    确定删除回复吗？
    \n
    \n 取消\n 删除\n
    \n
    \n
    \n\n\n
    \n
    \n
      \n
    \n
    \n
    \n\n\n
    \n
    \n
    \n
    \n
    \n 知道了\n
    \n
    \n
    \n\n
    \n
    \n
    \n
    长按识别前往小程序
    \n
    \n \n
    \n
    \n
    \n\n\n\n \n \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n \n\n\n\n\n \n\n \n\n" }, { "path": "test/mp-links.js", "content": "const extract = require('..').extract\nconst assert = require('assert')\nconst fs = require('fs')\nconst path = require('path')\n\nconst url = 'https://mp.weixin.qq.com/s?__biz=MzIwNjU2ODk1MQ==&mid=2247497639&idx=1&sn=bba35c164cbae04da8d78808151d35aa&chksm=971d1b3fa06a922971367bca63cce1f8a754b582c4ce7c2d07dfb28e5dd2b38d7695ff72b56b&scene=132#wechat_redirect'\n\nconst content = fs.readFileSync(path.join(__dirname, './mp-link.html'), 'utf-8')\n;(async () => {\n\tconst res = await extract(content, {\n\t\tshouldReturnContent: false,\n\t\tshouldExtractMpLinks: true\n\t})\n\tconsole.log(JSON.stringify(res, null, 2))\n})()\n" }, { "path": "test.js", "content": "const extract = require('.').extract\nconst assert = require('assert')\nconst fs = require('fs')\n\n;(async function () {\n // const url = fs.readFileSync('./links/post.html', 'utf-8')\n // const postRs = await extract(url, {\n // shouldReturnContent: false\n // })\n //\n // console.log(postRs)\n //\n // const expected = {\n // account_name: '微信派',\n // account_alias: 'wx-pai',\n // account_id: 'gh_bc5ec2ee663f',\n // account_biz: 'MjM5NjM4MDAxMg==',\n // account_biz_number: 2396380012,\n // account_qr_code: 'https://open.weixin.qq.com/qr/code?username=gh_bc5ec2ee663f',\n // msg_has_copyright: false,\n // msg_content: null,\n // msg_author: null,\n // msg_sn: '9a0a54f2e7c8ac4019812aa78bd4b3e0',\n // msg_idx: 1,\n // msg_mid: 2655078412,\n // msg_title: '重磅 | 微信订阅号全新改版上线！',\n // msg_desc: '今后，头图也很重要',\n // msg_link: 'http://mp.weixin.qq.com/s?__biz=MjM5NjM4MDAxMg==&mid=2655078412&idx=1&sn=9a0a54f2e7c8ac4019812aa78bd4b3e0&chksm=bd5fc40f8a284d19360e956074ffced37d8e2d78cb01a4ecdfaae40247823e7056b9d31ae3ef#rd',\n // msg_source_url: null,\n // msg_cover: 'http://mmbiz.qpic.cn/mmbiz_jpg/OiaFLUqewuIDldpxsV3ZYJzzyH9HTFsSwOEPX82WEvBZozGiam3LbRSzpIIKGzj72nxjhLjnscWsibDPFmnpFZykg/0?wx_fmt=jpeg',\n // msg_article_type: null,\n // msg_publish_time_str: '2018/06/20 18:52:35',\n // msg_type: 'post'\n // }\n // for (let i in expected) {\n // assert(postRs.data[i] === expected[i])\n // }\n //\n // const link001 = fs.readFileSync('./links/quota_limit.html', 'utf-8')\n // const res001 = await extract(link001)\n // console.log(res001)\n // assert(res001.code === 2010)\n //\n // const imageUrl = fs.readFileSync('./links/image.html', 'utf-8')\n // const imageRs = await extract(imageUrl)\n //\n // console.log(imageRs)\n //\n // const videoUrl = fs.readFileSync('./links/video.html', 'utf-8')\n // const videoRs = await extract(videoUrl)\n //\n // console.log(videoRs)\n //\n // const documentWriteUrl = fs.readFileSync('./links/document.write.html', 'utf-8')\n // const documentWriteRs = await extract(documentWriteUrl)\n //\n // console.log(documentWriteRs)\n //\n // const _20181021WriteUrl = fs.readFileSync('./links/20181021.issue.html', 'utf-8')\n // const _20181021WriteRs = await extract(_20181021WriteUrl)\n //\n // console.log(_20181021WriteRs)\n\n // const issue3WriteUrl = fs.readFileSync('./links/issue3.html', 'utf-8')\n // const issue3WriteRs = await extract(issue3WriteUrl)\n\n // console.log(issue3WriteRs)\n\n // const sogou = await extract('https://mp.weixin.qq.com/s?src=3×tamp=1559431337&ver=1&signature=K*8sgrrv9y5KoQr22U2gh3Tut0DIldkcZ67t4Oc3BzcyNEQMtX3l459-K2JvxxeLvWbdhtjtuzSWorY-zsW-Nm2Rloy30WAJi82JmQGYI2GlWpIcFuXNh53g1jY*Dh8XRczrRrjewQgRj*N1Kg8FK0j5W-3wb*NdM3JzzhO4jWc=')\n\n // console.log(sogou)\n\n const url = fs.readFileSync('./links/20240107.html', 'utf-8')\n const postRs = await extract(url, {\n shouldReturnContent: true\n })\n\n console.log(postRs)\n\n})()\n" }, { "path": "util.js", "content": "const qs = require('qs')\n\nfunction getParameterByName(name, url = window.location.href) {\n name = name.replace(/[\\[\\]]/g, '\\\\$&');\n var regex = new RegExp('[?&]' + name + '(=([^&#]*)|&|#|$)'),\n results = regex.exec(url);\n if (!results) return null;\n if (!results[2]) return '';\n return decodeURIComponent(results[2].replace(/\\+/g, ' '));\n}\n\nfunction normalizeUrl (url = '') {\n const parts = url.replace(/&/g, '&').split('?')\n const rs = qs.parse(parts[1])\n const querys = qs.stringify(rs)\n if (querys) {\n return parts[0] + '?' + querys\n } else {\n return parts[0]\n }\n}\n\nmodule.exports = {\n getParameterByName,\n normalizeUrl\n}" }, { "path": "video.js", "content": "const dayjs = require('dayjs')\n\nmodule.exports = function({\n\tpost,\n\tbasic,\n\tscript,\n\tgetError,\n\thtml,\n\t$,\n\tshouldReturnRawMeta\n}) {\n\tconst lines = script.split('\\n')\n\tconst lines2 = lines.filter(line => !!line.trim())\n\tlet code = lines2.filter((line, index) => {\n\t\treturn /d\\./.test(line) || (lines2[index - 1] && lines2[index - 1].includes('d.') && !line.includes('}'))\n\t})\n\tcode = `var d = {};\n \\nfunction getXmlValue (path) {\n return false\n }\\n` + code.join('\\n').replace('var d = _g.cgiData;', 'var d = {}') + '\\n return d;'\n\tlet data = {}\n\tcode = `var _g = {};` + code\n\tconst fn = new Function(code)\n\tdata = fn()\n\tbasic.accountName = data.nick_name\n\tbasic.accountAvatar = data.hd_head_img\n\tbasic.accountId = data.user_name\n\n\t// biz\n\tif (!basic.accountBiz && data.biz) {\n\t\tbasic.accountBiz = data.biz\n\t\tbasic.accountBizNumber = Buffer.from(basic.accountBiz, 'base64').toString() * 1\n\t}\n\n\t// 标题\n\tpost.msg_title = data.title\n\tpost.msg_desc = null\n\tpost.msg_cover = null\n\tpost.msg_link = data.msg_link || null\n\tpost.msg_article_type = null\n\n\t// sn, idx, mid\n\tpost.msg_sn = data.sn || null\n\tpost.msg_idx = data.idx ? data.idx * 1 : null\n\tpost.msg_mid = data.mid ? data.mid * 1 : null\n\n\t// 视频链接赋值于 source_url\n\tconst vidMatch = html.match(/vid\\s*:\\s*'(.*?)'/)\n\tif (vidMatch && vidMatch[1]) {\n\t\tdata.vid = vidMatch[1]\n\t\t// 旧版 vid 已经不适用\n\t\t// post.msg_source_url = 'http://v.qq.com/x/page/' + vid + '.html'\n\t}\n\tif (!post.msg_cover) {\n\t\t// 旧版废弃\n\t\t// post.msg_cover = `https://vpic.video.qq.com/60643382/${vid}.png`\n\t\tpost.msg_cover = $(\"meta[property='og:image']\").attr(\"content\")\n\t}\n\n\t// 视频只有标题 + 内容，内容直接从 meta 里取\n\tconst description = $(\"meta[name='description']\").attr(\"content\")\n\tpost.msg_content = description\n\n\t// 发布时间\n\tif (data.create_time) {\n\t\tpost.msg_publish_time = new Date(data.create_time * 1000)\n\t\tpost.msg_publish_time_str = dayjs(post.msg_publish_time).format('YYYY/MM/DD HH:mm:ss')\n\t}\n\n\t// 如果没有，使用 ct_str\n\tif (!data.create_time && data.ct_str) {\n\t\tpost.msg_publish_time = new Date(data.ct_str)\n\t\tpost.msg_publish_time_str = dayjs(post.msg_publish_time).format('YYYY/MM/DD HH:mm:ss')\n\t}\n\n\tif (shouldReturnRawMeta) {\n\t\tpost.raw_data = data\n\t}\n\n}" } ]