Python使用urllib2模块抓取HTML页面资源的实例分享

脚本专栏 2024/11/25 佚名

3 2 1

先把要抓取的网络地址列在单独的list文件中

https://www.jb51.net/article/83440.html
https://www.jb51.net/article/83437.html
https://www.jb51.net/article/83430.html
https://www.jb51.net/article/83449.html

然后我们来看程序操作，代码如下：

#!/usr/bin/python

import os
import sys
import urllib2
import re

def Cdown_data(fileurl, fpath, dpath):
 if not os.path.exists(dpath):
  os.makedirs(dpath)
 try:
  getfile = urllib2.urlopen(fileurl) 
  data = getfile.read()
  f = open(fpath, 'w')
  f.write(data)
  f.close()
 except:
 print 

with open('u1.list') as lines:
 for line in lines:
  URI = line.strip()
  if '?' and '%' in URI:
   continue
 elif URI.count('/') == 2:
   continue
  elif URI.count('/') > 2:
   #print URI,URI.count('/')
  try:
    dirpath = URI.rpartition('/')[0].split('//')[1]
    #filepath = URI.split('//')[1].split('/')[1]
    filepath = URI.split('//')[1]
   if filepath:
     print URI,filepath,dirpath
     Cdown_data(URI, filepath, dirpath)
   except:
    print URI,'error'

Python,urllib2,HTML