python如何爬取百度云连接方法指导

本篇文章主要介绍了python urllib爬取百度云连接的实例代码，具有一定的参考价值，感兴趣的小伙伴们可以参考一下

from bs4 import BeautifulSoup
import urllib
import requests
import re

adr =[]

''''对搜素资源名字进行url编码'''
search_text =raw_input('请输入搜索资源名：')
search_text = search_text.decode('gbk')
search_text = search_text.encode('utf-8')
search_text = urllib.quote(search_text)


''''获取文件地址'''
home = urllib.urlopen('http://HdhCmsTestpanduoduo.net/s/name/'+search_text)


'''获取百度云地址'''
def getbaidu(adr):
  for i in adr:
    url = urllib.urlopen('http://HdhCmsTestpanduoduo.net'+i)
    bs = BeautifulSoup(url)
    bs1 = bs.select('.dbutton2')
    href = re测试数据pile('http\%(\%|\d|\w|\/\/|\/|\.)*')
    b = href.search(str(bs1))
    name = str(bs.select('.center')).decode('utf-8')
    text1 = re测试数据pile('\<h1\sclass\=\"center"\>[\d|\w|\D|\W]*\</h1\>')
    text2 = text1.search(name)
    rag1 = re测试数据pile('\>[\d|\w|\D|\W]*\<')
    if text2:
      text3 = rag1.search(text2.group())
      if text3:
        print text3.group()
    if b:
      text = urllib.unquote(str(b.group())).decode('utf-8')
      print text

'''初始化'''
def init(adr):
  soup = BeautifulSoup(home)
  soup = soup.select('.row')
  pattern = re测试数据pile('\/r\/\d+')
  for i in soup:
    i = str(i)
    adress = pattern.search(i)
    adress = adress.group()
    adr.append(adress)


print 'running---------'    
init(adr)
getbaidu(adr) 

以上就是python如何爬取百度云连接方法指导的详细内容，更多请关注Gxl网其它相关文章！

查看更多关于python如何爬取百度云连接方法指导的详细内容...