Python 爬虫学习 网页图片下载

1. 使用正则表达式匹配

   # coding:utf-8
    
   import  re
   import urllib
    
   def get_content(url):
       """ Evilxr, """
       html = urllib.urlopen(url)
       content = html.read()
       html.close()
       return content
    
   def get_images(info):
       """" Download Baidu pictures.
       <img class="BDE_Image" src="http:*****">
       """
       regex = r' class="BDE_Image" src="(.+?\.jpg)" '
       pat = re.compile(regex)
       images_code = re.findall(pat, info)
    
       i = 0
       for image_url in images_code:
           print image_url
           urllib.urlretrieve(image_url, '%s.jpg' % i)
           i = i +1
       print len(images_code)
    
   info = get_content("http://tieba.baidu.com/p/2299704181")
   print get_images(info)

   　　

2. 使用第三方库BeautifulSoup匹配

   # 安装 sudo pip install beautifulsoup4

   　　

   # coding:utf-8
    
   import urllib
   from bs4 import BeautifulSoup
    
   def get_content(url):
       """ Evilxr, """
       html = urllib.urlopen(url)
       content = html.read()
       html.close()
       return content
    
   def get_images(info):
       """
        使用BeautifulSoup在网页源码中匹配图片地址
       """
       soup = BeautifulSoup(info)
       all_img = soup.find_all('img', class_="BDE_Image" )
    
       i = 1
    
       for img in all_img:
           print img['src']
           urllib.urlretrieve(img['src'], '%s.jpg' % i)
           i = i +1
       print "一共下载了 ", len(all_img), "张图片"
    
   info = get_content("http://tieba.baidu.com/p/3368845086")
    
   print get_images(info)