Python 爬虫学习 urllib

1. 网页抓取

   # -*-coding: utf-8 -*-
   
   import urllib
   
   url = "http://www.cndzz.com/"
   
   html = urllib.urlopen(url)
   
   print html.read()
   

   　　对于网页编码为gb2312等格式的网页，使用如下方法

   # -*-coding: utf-8 -*-
   
   import urllib
   
   url = "http://www.sina.com.cn/"
   
   html = urllib.urlopen(url)
   
   print html.read().decode("gbk").encode("utf-8")
   

   　　如果有多种编码，可以使用如下方法

   # -*-coding: utf-8 -*-
   # Author:Evilxr
   
   import urllib
    
   url = "http://www.sina.com.cn/"
    
   html = urllib.urlopen(url)
    
   print html.read().decode("gbk", "ignore").encode("utf-8")
   

   　　

2. 获取Web服务器头部信息

   # -*-coding: utf-8 -*-
   # Author:Evilxr
   
   import urllib
   
   url = "http://www.sina.com.cn/"
   
   html = urllib.urlopen(url)
   
   print html.info()
   

   　　返回信息：

   Server: nginx
   Date: Otc, 10 Nov 2014 12:54:50 GMT
   Content-Type: text/html
   Last-Modified: Otc, 10 Nov 2014 12:54:11 GMT
   Vary: Accept-Encoding
   Expires: Otc, 10 Nov 2014 12:55:50 GMT
   Cache-Control: max-age=60
   X-Powered-By: schi_v1.03
   Age: 27
   Content-Length: 563513
   X-Cache: HIT from cd31-151.sina.com.cn
   Connection: close
   
   
   [Finished in 0.2s]
   

   　　

3. 获取网页状态码

   # -*-coding: utf-8 -*-
   # Author:Evilxr
   
   import urllib
   
   url = "http://www.sina.com.cn/"
   
   html = urllib.urlopen(url)
   
   # 200正常访问	301重定向	403 禁止访问 404页面不存在	500 服务器忙或者服务器无响应
   print html.getcode()
   
   # 获取用户传入的url
   print html.geturl()
   
   # 关闭文件
   html.close
   

   　　

4. 保存网页内容

   # -*-coding: utf-8 -*-
   # Author:Evilxr
   
   import urllib
   
   url = "http://www.cdnzz.com/"
   
   urllib.urlretrieve(url, "d:\\evilxr.html")
   

   　　

5. 获取网站编码类型

   # coding:utf8
   # Author:Evilxr
   
   import urllib
   
   url = "http://www.163.com"
   
   html = urllib.urlopen(url)
   
   print html.info().getparam('charset')
   html.close()
   

   　　返回：

   GBK
   [Finished in 0.6s]
   

   　　

   # coding:utf8
   # Author:Evilxr
   
   import urllib
   
   url = "http://www.cnblogs.com/Evilxr"
   
   html = urllib.urlopen(url)
   
   print html.info().getparam('charset')
   html.close()
   

   　　返回：

   utf-8
   [Finished in 0.3s]
   

   　　

6. 自动获取网站编码 chardet[字符集检测]

   #先安装chardet
   #pip install chardet

   # coding:utf8
   
   import urllib 
   import chardet
   
   def automatic_detect(url):
   	"""" doc """
   	content = urllib.urlopen(url).read()
   	result= chardet.detect(content)
   	encoding = result['encoding']
   	return encoding
   
   url_list = ["http://www.sina.com.cn/", 
   			 "http://www.cnblogs.com/evilxr",
   			  "http://bbs.hackav.com/",
   			  "http://www.baidu.com/",
   			  "http://fuli.ba/"]
   for url in url_list:
   	print url, automatic_detect(url)

   http://www.sina.com.cn/ GB2312
   http://www.cnblogs.com/evilxr utf-8
   http://bbs.hackav.com/ GB2312
   http://www.baidu.com/ utf-8
   http://fuli.ba/ utf-8
   [Finished in 17.1s]