Python与网页相关的操作集锦

1、从网址中获取网页内容

 

import urllib
import re
import sys
import string

sock = urllib.urlopen("http://www.hao123.com/")
strhtml = sock.read()
strhtml = unicode(strhtml, 'gb2312','ignore').encode('utf-8','ignore')
print(strhtml)

转载自：http://hi.baidu.com/kopla/blog/item/591335afde167ce8fbed505a.html

这个博客有不少python从网页获取内容的东东，很好

 

2、POST请求

 

以前在实现论坛自动发贴的时候写的代码，其中data部分就是你要提交的数据。
其实最好的方式就是你自己在提交一次注册信息的时候，抓包看一下post了什么东西，然后把data部分改成你要提交的东西，注意报文格式，就可以了。
#!/usr/bin/python

import cookielib, urllib2, urllib, sys, time
import httplib


http = httplib.HTTP('你要连接的host')

# write header
http.putrequest("POST", '/phpwind/post.php?')
http.putheader("User-Agent", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 1.1.4322; InfoPath.2; MAXTHON 2.0)")
http.putheader("Referer", 'http://10.16.62.100/phpwind/post.php?fid=2')
http.putheader("Host", '10.16.62.100')
http.putheader("Cookie", cookie)
http.putheader("Content-Type", 'multipart/form-data; boundary=---------------------------7d91d42da0af0')
http.putheader("Content-Length", str(len(data)))
http.endheaders()

# write body
http.send(data)

# get response
errcode, errmsg, headers = http.getreply()

if errcode != 200:
  raise Error(errcode, errmsg, headers)
file = http.getfile()
print file.read()

 

转载自：http://topic.csdn.net/u/20101012/14/51a74db4-fad7-4d05-ba64-69f6b0149a44.html

 

http://pleac.sourceforge.net/pleac_python/webautomation.html

 

示例：

使用python在win下通过IE组件获得Ajax执行后网页源代码

 

在论坛发帖都没人回，最后还是自己解决了，现在把测试的代码写下。距离色色的目标又进一步了，欧耶！

view plaincopy to clipboardprint?

   1. #!/usr/bin/env python 
   2. #coding=utf-8 
   3. import wx.lib.iewin 
   4. import wx,time 
   5. class MyFrame(wx.Frame): 
   6.     def __init__(self): 
   7.         wx.Frame.__init__(self,parent = None,id = -1,pos = wx.DefaultPosition,title = u'iewin窗口') 
   8.         panel = wx.Panel(self) 
   9.         self.html = wx.lib.iewin.IEHtmlWindow(panel,-1,pos = wx.DefaultPosition,style = 0,name = 'OK') 
  10.         self.html.LoadUrl('http://www.cnbeta.com/articles/105719.htm') 
  11.          
  12.         sizer = wx.BoxSizer(wx.HORIZONTAL) 
  13.         sizer.Add(self.html,1, wx.ALL|wx.EXPAND,0) 
  14.         panel.SetSizer(sizer) 
  15.         sizer.Fit(self) 
  16.         self.html.AddEventSink(self) 
  17.          
  18.     def DocumentComplete(self,pDisp,URL): 
  19.          
  20.         print isinstance(self.html.GetText(),unicode) 
  21.         s = self.html.GetText().encode('utf8') 
  22.         fi = open('1.txt','w') 
  23.         t = s.replace('乔布斯','片子') 
  24.         fi.write(t) 
  25.         fi.close() 
  26.          
  27.          
  28. if __name__=='__main__': 
  29.     app= wx.PySimpleApp() 
  30.     frame = MyFrame() 
  31.     frame.Show() 
  32.     app.MainLoop() 

#!/usr/bin/env python #coding=utf-8 import wx.lib.iewin import wx,time class MyFrame(wx.Frame): def __init__(self): wx.Frame.__init__(self,parent = None,id = -1,pos = wx.DefaultPosition,title = u'iewin窗口') panel = wx.Panel(self) self.html = wx.lib.iewin.IEHtmlWindow(panel,-1,pos = wx.DefaultPosition,style = 0,name = 'OK') self.html.LoadUrl('http://www.cnbeta.com/articles/105719.htm') sizer = wx.BoxSizer(wx.HORIZONTAL) sizer.Add(self.html,1, wx.ALL|wx.EXPAND,0) panel.SetSizer(sizer) sizer.Fit(self) self.html.AddEventSink(self) def DocumentComplete(self,pDisp,URL): print isinstance(self.html.GetText(),unicode) s = self.html.GetText().encode('utf8') fi = open('1.txt','w') t = s.replace('乔布斯','片子') fi.write(t) fi.close() if __name__=='__main__': app= wx.PySimpleApp() frame = MyFrame() frame.Show() app.MainLoop()