Python实现爬取盘多多百度云资源链接的完整代码示例

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://www.panduoduo.net/s/name/'+search_text)


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