黑板课Python爬虫第二关 

 1 #coding=utf-8
 2 import requests
 3 from lxml import etree
 4 
 5 url = 'http://www.heibanke.com/lesson/crawler_ex01/'
 6 password = 0
 7 #要提交的表单
 8 payload = {
 9     'password':password,
10     'username':123
11 }
12 
13 while password<=30:
14     #获取response
15     payload['password'] = password
16     r = requests.post(url,data = payload)
17     #获取二进制文本，并且从utf-8解码
18     html = r.content.decode('utf-8')
19     #用etree获取页面
20     page = etree.HTML(html)
21     #提取信息
22     info = page.xpath('/html/body/div/div/div/h3/text()')
23     #print info[0]
24     if u'您输入的密码错误, 请重新输入' in info[0]:
25         password = password+1
26     else:
27         break
28 
29 print password

 

posted on 2016-01-20 13:19  freetime  阅读(193)  评论(0)    收藏  举报

导航