使用Python3編寫抓取網頁和只抓網頁圖片的指令碼

最基本的抓取網頁內容的代碼實現：

#!/usr/bin/env python  from urllib import urlretrieve  def firstNonBlank(lines):   for eachLine in lines:     if not eachLine.strip():       continue     else:       return eachLine  def firstLast(webpage):   f = open(webpage)   lines = f.readlines()   f.close()   print firstNonBlank(lines),   lines.reverse()   print firstNonBlank(lines),  def download(url='http://www',process=firstLast):   try:     retval = urlretrieve(url)[0]   except IOError:     retval = None   if retval:     process(retval)  if __name__ == '__main__':   download() 

利用urllib模組，來實現一個網頁中針對圖片的抓取功能：

import urllib.request import socket import re import sys import os targetDir = r"C:\Users\elqstux\Desktop\pic" def destFile(path):   if not os.path.isdir(targetDir):     os.mkdir(targetDir)   pos = path.rindex('/')   t = os.path.join(targetDir, path[pos+1:])   return t  if __name__ == "__main__":   hostname = "http://www.douban.com"   req = urllib.request.Request(hostname)   webpage = urllib.request.urlopen(req)   contentBytes = webpage.read()   for link, t in set(re.findall(r'(http:[^\s]*?(jpg|png|gif))', str(contentBytes))):     print(link)     urllib.request.urlretrieve(link, destFile(link)) 

import urllib.request import socket import re import sys import os targetDir = r"H:\pic" def destFile(path):   if not os.path.isdir(targetDir):     os.mkdir(targetDir)   pos = path.rindex('/')   t = os.path.join(targetDir, path[pos+1:]) #會以/作為分隔   return t  if __name__ == "__main__":   hostname = "http://www.douban.com/"   req = urllib.request.Request(hostname)   webpage = urllib.request.urlopen(req)   contentBytes = webpage.read()   match = re.findall(r'(http:[^\s]*?(jpg|png|gif))', str(contentBytes) )#r'(http:[^\s]*?(jpg|png|gif))'中包含兩層圓括弧，故有兩個分組，                              #上面會返回列表，括弧中匹配的內容才會出現在列表中   for picname, picType in match:     print(picname)     print(picType)      ''''' 輸出： http://img3.douban.com/pics/blank.gif gif http://img3.douban.com/icon/g111328-1.jpg jpg http://img3.douban.com/pics/blank.gif gif http://img3.douban.com/icon/g197523-19.jpg jpg http://img3.douban.com/pics/blank.gif gif ... ''' 

