python爬取招聘信息

import requests
from bs4 import BeautifulSoup
import time
import random

# 设置header
header = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:58.0) Gecko/20100101 Firefox/58.0',
        'Connection': 'keep - alive'
        }
movie_list = []

def get_pages_link():
    # https://movie.douban.com/top250?start=25
    for item in range(1,25,1):
        url = "https://www.liepin.com/zhaopin/?init=-1&headckid=8b8a11cc05e34e78&fromSearchBtn=2&ckid=8b8a11cc05e34e78&degradeFlag=0&key=python&siTag=I-7rQ0e90mv8a37po7dV3Q~fA9rXquZc5IkJpXC-Ycixw&d_sfrom=search_industry&d_ckId=ac6bf5fc984fbad69fd09f0270ca7f1f&d_curPage=0&d_pageSize=40&d_headId=ac6bf5fc984fbad69fd09f0270ca7f1f&curPage={}".format(item)
        web_data = requests.get(url,headers=header)
        time.sleep(1 + random.random())
        soup = BeautifulSoup(web_data.text,'lxml')
        for item in soup.select('.sojob-list li'):
            job = item.select('.job-info h3 a')[0].get_text().strip()
            condition = item.select('.condition')[0].get_text()
            (salary,addr,edu,experence) = condition.split()
            print(job)
            print(salary)
            print(addr)
            print(edu)
            print(experence)
            date = item.select('time')[0].attrs['title']
            print(date)
            company = item.select('.company-name')[0].get_text().strip()
            print(company)
            field = item.select('.field-financing')[0].get_text().strip()
            print(field)
            node = item.select('.temptation')
            if node:
                temptation = item.select('.temptation')[0].get_text().strip()
                print(temptation)
            print('-' * 20)
        print('\n'+' - '*50+'\n')

if __name__ =='__main__':
    get_pages_link()