Python爬取智联招聘的GIS开发信息（初级版本）

一、闲着无聊，每天都是那么无聊，感觉我算是废了，真坑想出去实习那么坑

二、直接放源代码(写的烂不要喷我)

import re#正则 
import time
import requests
import random
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import urllib
header={
'Accept': 'application/json, text/javascript, */*; q=0.01',
'Accept-Encoding': 'gzip, deflate',
'Accept-Language': 'zh-CN,zh;q=0.9',
'Cache-Control': 'no-cache',
'Connection': 'keep-alive',
'Content-Length': '1599',
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
'Host': 'hotel.elong.com',
'Origin': 'http://hotel.elong.com',
'Pragma': 'no-cache',
'Referer': 'http://hotel.elong.com/beijing/',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.79 Safari/537.36',
'X-Requested-With': 'XMLHttpRequest'}
for n in range(1,6):
    dat={'jl': '北京+上海+广州+深圳+西安',
          'kw': 'GIS开发',
          'p':n,
          'sm': '0',
          'sg': 'a20b0e245eac4aa1b4844dca099fc75a'}
    url='https://sou.zhaopin.com/jobs/searchresult.ashx?'
    print(n)
    html= requests.get(url,params=dat).text
        # 正则表达式进行解析
    pattern1 = re.findall('href="http://jobs.zhaopin.com/.*?.htm" target="_blank">(.*?)</a>',html )
    #pattern=[]
    #for x in pattern1:
    #    if ('<b>'in x)or('</b>'in x):
    #        strt=str(x)
    #        ss=strt.replace('</b>','')
    #        pattern.append(ss)
    #    else:
    #        pattern.append(x)
 
    pattern2 = re.findall('class="gsmc"><a href="http://company.zhaopin.com/.*?.htm" target="_blank">(.*?)</a>',html)
    pattern3 = re.findall( 'class="zwyx">(.*?)</td>',html)
    pattern4 = re.findall('class="newlist_deatil_two"><span>(.*?)</span>',html)
    print(pattern1)
    print('***********************')
    #print(ss)
    print(len(pattern1))
    data=list(map(lambda x:(pattern1[x],pattern2[x],pattern3[x],pattern4[x]),range(20)))
    data2=pd.DataFrame(data)
    data2.to_csv('C:\\Users\\你若成风618\\Desktop\\aa\\2.csv',header=False,index=False,mode='a+')

三、感觉很烂，后面准备优化一下，整点图表，数据分析下

四、忘了配个图