利用Python获取赶集网招聘信息前篇

 import re import urllib import urllib.request #获取赶集网数据 def begin(url): #要伪装成的浏览器(我这个是用的chrome) headers = ('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.86 Safari/537.36') opener = urllib.request.build_opener() #将要伪装成的浏览器添加到对应的http头部 opener.addheaders=[headers] #读取相应的url data = opener.open(url).read() #将获得的html解码为utf-8 data=data.decode('utf-8') return data #处理数据，返回字典城市对应城市的url def get_cityinfo(data): city_info1=re.findall(r'dl>(.*?)',data,re.S) city_info2=re.findall(r'()',city_info1[0],re.S) city_dict={} for each in city_info2: key=re.findall('>(.*?))',data[0],re.S) a_dict={} for each in a_info: key=re.findall('>(.*?)',cdzp_info,re.S) a_dict={} class_info=re.findall('
(.*?)
',allzp_info[0],re.S) for each in class_info: a_info=re.findall(r'()',each,re.S) for each1 in a_info: key=re.findall('>(.*?)