python采集博客中上传的QQ截图文件

import urllib2
from bs4 import BeautifulSoup
import re
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
 
baseurl = "http://www.gxlcms.com/dont-worry.html"
#说明下，起始地址是第一篇文章的地址，通过该文章的页面就
#可以使用BeautifulSoup模块来获取上一篇文章的地址
 
file = open(r"E:\123.txt","a")
 
def pageloop(url):
  page = urllib2.urlopen(url)
  soup = BeautifulSoup(page)
  img = soup.findAll(['img'])
  if img == []:
    print "当前页面没有图片"
    return
  else:
    for myimg in img:
      link = myimg.get('src')
      print link
      
      pattern = re.compile(r'QQ\S*[0-9]*png')
      badimg = pattern.findall(str(link))
      if badimg:
        print url
        file.write(link + "\n")
        file.write(url+"\n")
      
 
 
def getthenextpage(url):
  pageloop(url)
  page = urllib2.urlopen(url)
  soup = BeautifulSoup(page)
  for spanclass in soup.findAll(attrs={"class" : "article-nav-prev"}):
    #print spanclass
    if spanclass.find('article-nav-prev') != -1:
      pattern = re.compile(r'http://www.gxlcms.com/\S*html')
      pageurl = pattern.findall(str(spanclass))
      for i in pageurl:
        #print i
        getthenextpage(i)
       
      
 
getthenextpage(baseurl)
 
 
 
print "the end!"
file.close()

最后，对和我以前刚开始做网站的同学说下，图片命名的话最好是用数字形式或者是英文、拼音的形式，要不然到最后想修改的话就麻烦了，所以最好就是从刚开始就养成好的习惯，用正确的命名规范来问文章、图片来命名，这样就会好很多。