scrapy爬取前程无忧招聘信息代码
# -*- coding: utf-8 -*-
import scrapy
class JobSpider(scrapy.Spider):
name = 'job' #爬虫名
allowed_domains = ['51job.com'] #域名,此爬虫只会在该网站下采集数据
start_urls = [f'https://search.51job.com/list/000000,000000,0000,00,9,99,%2B,2,{page}.html?lang=c&postchannel=0000&workyear=99&cotype=99°reefrom=99&jobterm=99&companysize=99&ord_field=0&dibiaoid=0&line=&welfare='for page in range(1