python实现工作职位爬虫

代码

import requests
import bs4

ll=[]
list__=["职位","公司","规模","经验","学历","工资"]
ll.append(list__)
for i in range(1,68):
    print(i)
    print(ll)
    list_01=[]
    list_02=[]
    list_021=[]
    list_022=[]
    list_03=[]
    list_04=[]
    url=f"需要爬的URLn={i}"
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.113 Safari/537.36'}
    re = requests.get(url, headers=headers)
    # print(re.text)
    re.encoding = 'utf-8'
    bs = bs4.BeautifulSoup(re.text, 'html.parser')
    list_title=bs.find_all('a',class_='job-name')
    list_name=bs.find_all('div',class_='job-desc')
    list_dizhi=bs.find_all('a',class_='job-company-name')
    list_gui=bs.find_all('span',class_='job-desc')
    # print(list_name)
    aa=''
    for i in list_title:
        list_name01=bs.find('span')
        bb=(str(i.text)).replace('\n','')
        list_01.append(bb)
    for i in list_name:
        list_name01=bs.find('span',class_="job-pay-text")
        aa=i.text.split("|")
        bb=str(aa[0]).replace('\n','')
        cc=str(aa[1]).replace('\n','')
        dd=str(aa[2]).replace('\n','')
        list_02.append(bb)
        list_021.append(cc)
        list_022.append(dd)

    for i in list_dizhi:
        list_03.append(i.text)
    for i in list_gui:
        aa=i.text.split('|')
        bb=str(aa[1]).split("\n")
        list_04.append(str(bb[0]))
    for i, j, k, n ,a ,b  in zip(list_01,list_03,list_04,list_02,list_021,list_022):
        ll1=[]
        ll1.append(i)
        ll1.append(j)
        ll1.append(k)
        ll1.append(n)
        ll1.append(a)
        ll1.append(b)
        ll.append(ll1)
    # print(list_01[10])
    # print(list_02[10])
    # print(list_03[10])
    # print(list_04)
import openpyxl
wb=openpyxl.Workbook()
sheet=wb.active
sheet.title='广州'
for i in ll:
    sheet.append(i)

wb.save("F://爬虫资料/工作职位.xlsx")
wb.close()

爬取的部分资料