python2 urllib2抓取51job网的招聘数据

 1 #coding=utf-8
 2 __author__ = "carry"
 3 
 4 
 5 import sys
 6 reload(sys)
 7 sys.setdefaultencoding('utf-8')
 8 
 9 import urllib
10 import urllib2
11 import re
12 
13 
14 #获取源码
15 def get_content(page):
16     headers = {#'Host':'search.51job.com',
17                'User-Agent':'Mozilla/5.0 (Windows NT 6.2; rv:16.0) Gecko/20100101 Firefox/16.0',
18                #'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
19                #'Connection':'keep-alive'
20                }
21     url ='http://search.51job.com/list/000000,000000,0000,00,9,99,python,2,'+ str(page)+'.html'
22     req = urllib2.Request(url,headers=headers)
23     r = urllib2.urlopen(req)
24     response = r.read() #读取源代码并转为unicode
25     html = response.decode('gbk').encode('utf-8')
26     return html
27 
28 def get(html):
29     reg = re.compile(r'class="t1 ">.*? <a target="_blank" title="(.*?)".*? <span class="t2"><a target="_blank" title="(.*?)".*?<span class="t3">(.*?)</span>.*?<span class="t4">(.*?)</span>.*? <span class="t5">(.*?)</span>',re.S)#匹配换行符
30     items=re.findall(reg,html)
31     return items
32 
33 #多页处理，下载到文件
34 for  j in range(1,11):
35     print(u"正在爬取第"+str(j)+"页数据...")
36     html = get_content(j) #调用获取网页原码
37     for i in get(html):
38         #print(i[0],i[1],i[2],i[3],i[4])
39         with open ('51job.txt','a') as f:
40             f.write(i[0]+'	'+i[1]+'	'+i[2]+'	'+i[3]+'	'+i[4]+'
')
41             f.write("-----------------------------------------------------")
42             f.close()