on************* @gmail.com wrote:
Greetings gents. I'm a Railser working on a django app that needs to do
some scraping to gather its data.
I need to programatically access a site that requires a username and
password. Once I post to the login.php page, there seems to be a
redirect and it seems that the site is using a session (perhaps a
cookie) to determine whether the user is logged in. So I need to log in
and then have cookies and or sessions maintained as I access the page
that contains the content that I am actually interested in.
What is the simplest way to post data to a form, accept a cookie to
maintain the session (and support redirects) and then (now logged into
the site) retrieve the content of a page on the site?
Is their a library or technique that makes this simple?
Thanks!
I submit to you, in its entirety a, a script I wrote to do this. I think
its simple enough to figure out the important parts. I left some
debugging code in. Sorry for no explanation, etc., but I'm still playing
with the new 2.5 distro! This program worked for me, but there may be
comment on whether its good code from others. Names have been changed to
protect the innocent.
James
#! /usr/bin/env python
import sys
import os.path
import time
import random
import urllib
import urllib2
import cookielib
class DummyError(Exce ption): pass
############### ############### ############### ############### ###########
# some constants
############### ############### ############### ############### ###########
COOKIEFILE = 'cookies.lwp'
pda = "http://www.somemapcomp any.com/"
signin_params = urllib.urlencod e({'email_addre ss':'y***@email .address',
'password':'you rpasshere',
'action':'log_i n',
'Submit':'Sign In'})
signout_params = urllib.urlencod e({'action':'si gn_out'})
download_dict = {'screen':'map_ details', 'action':'downl oad'}
info_dict = {'screen':'map_ details',
'back':'find_ma ps',
'view':'state'}
############### ############### ############### ############### ###########
# setup for cookies
############### ############### ############### ############### ###########
cj = cookielib.LWPCo okieJar()
if os.path.isfile( COOKIEFILE):
cj.load(COOKIEF ILE)
opener = urllib2.build_o pener(urllib2.H TTPCookieProces sor(cj))
urllib2.install _opener(opener)
############### ############### ############### ############### ###########
# make the signin request
############### ############### ############### ############### ###########
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
txheaders = {'User-agent' : user_agent}
req = urllib2.Request (pda, signin_params, txheaders)
############### ############### ############### ############### ###########
# download_map
############### ############### ############### ############### ###########
def download_map(ma p_id, urlopen=urllib2 .urlopen):
############### ############### ############### ############### #########
# download the map
############### ############### ############### ############### #########
download_dict['map_id'] = map_id
download_params = urllib.urlencod e(download_dict )
mapin = urlopen(pda + ("?%s" % download_params ))
mapout = open('map-%s' % map_id, "wb")
mapout.write(ma pin.read())
mapout.close()
############### ############### ############### ############### #########
# download the map info
############### ############### ############### ############### #########
info_dict['map_id'] = map_id
info_params = urllib.urlencod e(info_dict)
infoin = urlopen(pda + ("?%s" % info_params))
infoout = open('info-%s' % map_id, "wb")
infoout.write(i nfoin.read())
infoout.close()
############### ############### ############### ############### ###########
# signin and print info
############### ############### ############### ############### ###########
try:
signin = urllib2.urlopen (req)
except IOError, e:
print 'We failed to open "%s".' % pda
if hasattr(e, 'code'):
print 'We failed with error code - %s.' % e.code
else:
print
print 'Here are the headers of the page :'
print signin.info()
afile = open("signin.ht ml", "w")
afile.write(sig nin.read())
afile.close()
############### ############### ############### ############### ###########
# report and save cookies
############### ############### ############### ############### ###########
print
for index, cookie in enumerate(cj):
print index, ' : ', cookie
cj.save(COOKIEF ILE, True, True)
print
print "cookies=== >"
os.system('cat %s' % COOKIEFILE)
print "<===cookie s"
for map_id in xrange(1001, 1507):
try:
download_map(ma p_id)
wait = 7.5 + random.randint( 0,5)
print "=====waiti ng %s seconds..." % wait
time.sleep(wait )
except urllib2.HTTPErr or, e:
# except DummyError, e:
print "%s: failed to download" % map_id
print " HTTP ERROR:", e
else:
print "# Downloaded map %s successfully." % map_id
signout = urllib.urlopen( pda + ("?%s" % signout_params) )
afile = open("signout.h tml", "w")
afile.write(sig nout.read())
afile.close()
--
James Stroud
UCLA-DOE Institute for Genomics and Proteomics
Box 951570
Los Angeles, CA 90095
http://www.jamesstroud.com/ 
