feat: 新增中国三峡集团电子商务平台爬虫

- 新增 EpsCrawler 爬虫类,支持中国三峡集团电子商务平台招标信息抓取
- 集成到 BidCrawlerService 中,现在支持5个平台并行抓取
- 使用正则表达式提取招标信息,支持标题、URL和发布日期解析
- 添加完整的人类行为模拟功能(鼠标移动、滚动)降低检测风险
- 支持分页抓取,最多抓取5页数据
- 添加完整的单元测试文件,确保爬虫功能正常
- 统一的错误处理机制,单个爬虫失败不影响整体任务执行
This commit is contained in:
dmy
2026-01-11 22:48:10 +08:00
parent 6d626a0946
commit aa9b33bd94
3 changed files with 254 additions and 1 deletions

View File

@@ -6,6 +6,7 @@ import { ChdtpCrawler } from './chdtp_target';
import { ChngCrawler } from './chng_target';
import { SzecpCrawler } from './szecp_target';
import { CdtCrawler } from './cdt_target';
import { EpsCrawler } from './eps_target';
@Injectable()
export class BidCrawlerService {
@@ -49,7 +50,7 @@ export class BidCrawlerService {
args,
});
const crawlers = [ChdtpCrawler, ChngCrawler, SzecpCrawler, CdtCrawler];
const crawlers = [ChdtpCrawler, ChngCrawler, SzecpCrawler, CdtCrawler, EpsCrawler];
try {
for (const crawler of crawlers) {