数据挖掘岗位的分析

    import requests
    from bs4 import BeautifulSoup
    import numpy as np
    import pandas as pd
    import matplotlib.pyplot as plt
    from selenium import webdriver
    import builtwith
    import re
    

    #检查网站采取了那些技术
    html = requests.get('https://search.51job.com').content
    builtwith.parse('https://search.51job.com',html=html.decode('gbk'))#因为51job是GBK格式，所以需要设置HTML的解码格式，模块默认是utf-8
    

    #数据爬取过程，51job
    occupation_infos = []
    for page in range(1,262):
    url = 'https://search.51job.com/list/000000,000000,0000,00,9,99,%25E6%2595%25B0%25E6%258D%25A