python之爬取绍兴e网招聘信息

from bs4 import BeautifulSoup as bs
import urllib
import re
class Spider(object):
    def __init__(self):
        print('init')
        self.begin_page=1
        self.end_page=4
        self.base_url='https://job.e0575.com/list.php?cIx=5&page='
    def load_page(self):
        print("load")
        headers={"User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:69.0) Gecko/20100101 Firefox/69.0"}
        for page in range(self.begin_page,self.end_page):
            print(page)
            url=self.base_url+str(page)
            request=urllib.request.Request(url,headers=headers)
            response=urllib.request.urlopen(request)
            html=response.read().decode('utf-8')
            self.parse_page(html)
    def parse_page(self,html):
        print("parse")
        html=bs(html,'lxml')
        result1=html.select('li[class="bg1"]')
        result2=html.select('li[class="bg3"]')
        result1+=result2
        items=[]
        for site in result1:
            item={}
            name=site.find('span').text
            detailLink=site.find('a').attrs['href']
            wage=site.select('.dd1')[0].text[7:-5]
            publishTime=site.select('.dd2')[0].text[7:-5]
            companyname=site.find('a',{'class':None}).text[7:-6]
            workrequest=site.find('a').attrs['title'].replace('\u3000','  ')
            item['职位名称']=name
            item['详情链接']=detailLink
            item['工作薪酬']=wage
            item['发布时间']=publishTime
            item['发布公司']=companyname
            item['工作要求']=workrequest
            items.append(item)
        self.save_file(items)
    def save_file(self,items):
        print('save')
        file=open('job.json','ab')
        file.write(str(items).encode())
        file.close()
if __name__=='__main__':
    spider=Spider()
    spider.load_page()

import os
os.remove('job.json')