import axios from "axios"; import fs from "fs"; import path from "path"; import { timestampToDate, loopCall, keywordsInclude, // addToMessageQueue, } from "./utils.js"; import config from "./config.js"; import { SQLiteMessageQueue } from "./sqlite.js"; // import { messageQueue } from "./msgManager.js"; // import cheerio from "cheerio"; class ChangAn { constructor() { // this.filepath = path.resolve("changan.json"); this.info = []; console.log("长安 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("长安"); if (announcements.length > 0) { await this.increment(); } else { await this.fullFetch(); } // if (fs.existsSync(this.filepath)) { // let data = fs.readFileSync(this.filepath, "utf-8"); // this.info = data ? JSON.parse(data) : []; // if (this.info.length > 0) { // await this.increment(); // } else { // await this.fullFetch(); // } // } else { // console.log("历史文件不存在,开始全量爬取"); // 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("长安", this.info); // this.writeFile(this.info); this.queue.addMessage("长安", 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) => { try { let newInfo = this.queue.filterNewAnnouncements( "长安", result.info ); // 存在新数据 if (newInfo.length > 0) { console.log(`发现 ${newInfo.length} 条新数据`); // this.info.push(...newInfo); this.queue.saveAnnouncements("长安", newInfo); // this.writeFile(this.info); this.queue.addMessage("长安", 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); } } async getInfo(pagenumber = 1) { let info = []; console.log(`正在获取第 ${pagenumber} 页数据...`); let result = await this.getList(pagenumber); if (result[0]) { // 出错, 记录错误日志 console.error("获取页面数据失败:", result[0]); return { pages: 0, info: [] }; } else { // let total = result[1].result.total; let pages = result[1].result.pages; let arr = result[1].result.records; for (let i = 0; i < arr.length; i++) { let item = arr[i]; // 命中关键词 if (keywordsInclude(item.projectName)) { console.log("处理项目:", item.id, item.projectName); info.push({ id: item.id, name: item.projectName, publishTime: item.startTime, endTime: item.endTime, urls: `https://portal.changan.com.cn/noProdNoticeInfo?_t=${Date.now()}&id=${ item.id }`, }); } } return { pages, info }; } } // 分页获取数据 getList(pagenumber) { return axios({ url: "https://portal.changan.com.cn/backend_8086/changan_platform/api/nonPdcSourceNoticeCt/listSourceNoticePageBySupplier", params: { _t: Date.now(), pageNo: pagenumber, pageSize: 20, }, method: "get", }) .then((res) => { let result = res.data; if (result.success) { return [null, result]; } else { return ["err", null]; } }) .catch((err) => { return [err, null]; }); } // writeFile(info) { // fs.writeFileSync(this.filepath, JSON.stringify(info), "utf-8"); // } } new ChangAn();