今天爬了51job的数据分析岗嘻嘻

其实就是改了一下上一篇的URL和正则表达式。

import urllib.request
import re
import urllib.parse

#获取原码
def get_content(page):
    url ='https://search.51job.com/list/010000,000000,0000,00,9,99,%25E6%2595%25B0%25E6%258D%25AE%25E5%2588%2586%25E6%259E%2590,2,'+str(page)+'.html?lang=c&postchannel=0000&workyear=99&cotype=99&degreefrom=99&jobterm=99&companysize=99&ord_field=0&dibiaoid=0&line=&welfare='
    a = urllib.request.urlopen(url)
    html = a.read().decode('gbk')
    return html

def get(html):
    reg = re.compile(r'class="t1 ">.*? <a target="_blank" title="(.*?)" href="(.*?)".*? <span class="t2"><a target="_blank" title="(.*?)".*?<span class="t3">(.*?)</span>.*?<span class="t4">(.*?)</span>.*? <span class="t5">(.*?)</span>',re.S)
    items = re.findall(reg,html)
    items_length = len(items) 
    return items,items_length

#爬取信息
items_all=[]
items_length_all=0
#30是页数
for i in range(0,30):
    items,items_length = get(get_content(i))
    items_all+=items
    items_length_all=items_length+items_length_all
    print(i)
import pandas as pd
items_all=pd.DataFrame(items_all).drop_duplicates()
items_all.columns=["职位","URL","公司","地址","money","time"]

#写入
items_all.to_excel("D:/DA.xls")

今天给看官老爷们附上结果图嘻嘻。

滚去看小闲书惹，喵~