Pythonic Prose: urllib2

Monday, September 21, 2009

Python - alter user agent string in web request

# Sometimes websites deny access to bots or unsupported browsers
# python allows you to change the user agent string so you can 
# impersonate any browser you desire

import urllib
import urllib2

# unaltered header.

print "sending a request using the default python user agent string..."
url = 'http://www.example.com'
req = urllib2.Request(url)

response = urllib2.urlopen(req)
the_page = response.read()


# alter the header to look like a real browser
print "sending a request with an altered user agent string..."
url = 'http://www.example.com'
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'

headers = { 'User-Agent' : user_agent }
req = urllib2.Request(url, data=None, headers=headers) #, data) #, headers)

response = urllib2.urlopen(req)
the_page = response.read()



#Apache logs on the server indicate:
#   make a request without altering the user_agent
#       "POST / HTTP/1.1" 200 2022 "-" "Python-urllib/2.6"
#
#   a request made with the altered user_agent
#       "POST / HTTP/1.1" 200 2022 "-" "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)"

Python - browse the web with python

# retrieve the html from a web site 
import urllib2 
import urllib 
 
# query string 
# in this example these GET parameters don't 
#   do anything.  They are just here to show 
#   off the urlencode() function 
qs = {} 
qs['q'] = "items to search for" 
qs['i'] = 22 
qs_values = urllib.urlencode(qs) 
 
# append everything together 
url = "http://www.example.com" 
full_url = url + '?' + qs_values 
print "my full url: %s" %(full_url) 
 
# get the data from the web 
data = urllib2.urlopen(full_url) 
 
# data now has all the html/css/javascsript in it 
for item in data: 
    print item 
 
 
## output:     
##my full url: http://www.example.com?q=items+to+search+for&i=22 
##<HTML> 
## 
##<HEAD> 
## 
##  <TITLE>Example Web Page</TITLE> 
## 
##</HEAD>  
## 
##<body>   
## 
##<p>You have reached this web page by typing &quot;example.com&quot;, 
## 
##&quot;example.net&quot;, 
## 
##  or &quot;example.org&quot; into your web browser.</p> 
## 
##<p>These domain names are reserved for use in documentation and are not available  
## 
##  for registration. See <a href="http://www.rfc-editor.org/rfc/rfc2606.txt">RFC  
## 
##  2606</a>, Section 3.</p> 
## 
##</BODY> 
## 
##</HTML>