import axios from "axios"; import fs from "fs"; import path from "path"; import { timestampToDate, loopCall, keywordsInclude } from "./utils.js"; import config from "./config.js"; import { SQLiteMessageQueue } from "./sqlite.js"; // import cheerio from "cheerio"; class LeapMotor { constructor() { this.url = "https://lpsrm.leapmotor.com/cloud-srm/api-inq/inq-anon/reqhead/listPage"; this.info = []; console.log("零跑 爬虫启动..."); this.queue = new SQLiteMessageQueue(); this.start(); } async start() { try { await this.init(); } catch (err) { console.error("启动失败:", err); } } async init() { let announcements = this.queue.getAnnouncementsBySpider("零跑"); if (announcements.length > 0) { // console.log(announcements); await this.increment(); } else { await this.fullFetch(); } } // 全量爬取 async fullFetch() { console.log("开始全量爬取..."); try { await loopCall(this.getInfo.bind(this), { time: config.fullFetchTime, pagenumber: 1, stopWhen: (pagenumber, result) => { return ( pagenumber >= result.pages || pagenumber >= config.pageNumberLimit ); }, readyForNext: (pagenumber, result) => { this.info.push(...result.info); return pagenumber + 1; }, complete: (result) => { this.info.push(...result.info); console.log(`爬取完成,共获取 ${this.info.length} 条有效数据`); try { this.queue.saveAnnouncements("零跑", this.info); this.queue.addMessage("零跑", this.info); } catch (error) { console.error("数据库操作失败:", error); } }, }); } catch (error) { console.error("全量爬取失败:", error); } console.log("开始增量爬取..."); this.increment(); } // 增量爬取 async increment() { console.log("开始增量爬取模式,每5分钟检查一次新数据..."); try { await loopCall(this.getInfo.bind(this), { time: config.incrementFetchTime, // 5分钟间隔 pagenumber: 1, readyForNext: (pagenumber, result) => { // 判断数据是否存在 try { let newInfo = this.queue.filterNewAnnouncements( "零跑", result.info ); // 有新数据 if (newInfo.length > 0) { console.log(`发现 ${newInfo.length} 条新数据`); this.queue.saveAnnouncements("零跑", newInfo); this.queue.addMessage("零跑", newInfo); // 全是新数据,继续下一页 if (newInfo.length === result.info.length) { return pagenumber + 1; } else { // 有部分重复数据,重新从第一页开始 return 1; } } else { console.log("没有发现新数据,继续监控..."); return 1; // 重新从第一页开始 } } catch (error) { console.error("数据库操作失败:", error); } }, }); } catch (error) { console.error("增量爬取失败:", error); } } // 传入页码获取数据 async getInfo(pagenumber = 1) { let info = []; console.log(`正在获取第 ${pagenumber} 页数据...`); let result = await this.getList(pagenumber); if (result[0]) { // 出错, 记录错误日志 console.error("获取页面数据失败:", result[0]); return { pages: 0, info: [] }; } else { // let total = result[1].data.total; let pages = result[1].data.pages; let arr = result[1].data.list; for (let i = 0; i < arr.length; i++) { let item = arr[i]; // 命中关键词 if (keywordsInclude(item.souReqTitile)) { console.log("处理项目:", item.reqHeadId, item.souReqTitile); let noticeRes = await this.getNoticeUrl(item.reqHeadId); if (noticeRes[0]) { // 获取招标公告内容报错 console.error("获取公告链接失败:", noticeRes[0]); } else { info.push({ id: item.reqHeadId, name: item.souReqTitile, publishTime: item.publishTime, endTime: item.expirationTime, urls: noticeRes[1], }); } } } return { pages, info }; } } getList(pagenumber) { return axios({ url: this.url, data: { pageNum: pagenumber, pageSize: 8, }, method: "post", }) .then((res) => { let result = res.data; if (result.code === "0") { return [null, result]; } else { return ["err", null]; } }) .catch((err) => { return [err, null]; }); } getNoticeUrl(id) { return axios({ url: `https://lpsrm.leapmotor.com/cloud-srm/api-inq/inq-anon/pj/reqhead/get?id=${id}`, method: "get", }) .then((res) => { let result = res.data; if (result.code === "0") { return [null, result.data.extNoticeLink]; } else { return ["err", null]; } }) .catch((err) => { console.log("err:", err); return [err, null]; }); } // writeFile(info) { // fs.writeFileSync(this.filepath, JSON.stringify(info), "utf-8"); // } } new LeapMotor();