I am trying to write a function to post form data and save returned cookie info in a file so that the next time the page is visited, the cookie information is sent to the server (i.e. normal browser behavior).
I wrote this relatively easily in C++ using curlib, but have spent almost an entire day trying to write this in Python, using urllib2 - and still no success.
This is what I have so far:
import urllib, urllib2
import logging
# the path and filename to save your cookies in
COOKIEFILE = 'cookies.lwp'
cj = None
ClientCookie = None
cookielib = None
logger = logging.getLogger(__name__)
# Let's see if cookielib is available
try:
import cookielib
except ImportError:
logger.debug('importing cookielib failed. Trying ClientCookie')
try:
import ClientCookie
except ImportError:
logger.debug('ClientCookie isn\'t available either')
urlopen = urllib2.urlopen
Request = urllib2.Request
else:
logger.debug('imported ClientCookie succesfully')
urlopen = ClientCookie.urlopen
Request = ClientCookie.Request
cj = ClientCookie.LWPCookieJar()
else:
logger.debug('Successfully imported cookielib')
urlopen = urllib2.urlopen
Request = urllib2.Request
# This is a subclass of FileCookieJar
# that has useful load and save methods
cj = cookielib.LWPCookieJar()
login_params = {'name': 'anon', 'password': 'pass' }
def login(theurl, login_params):
init_cookies();
data = urllib.urlencode(login_params)
txheaders = {'User-agent' : 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'}
try:
# create a request object
req = Request(theurl, data, txheaders)
# and open it to return a handle on the url
handle = urlopen(req)
except IOError, e:
log.debug('Failed to open "%s".' % theurl)
if hasattr(e, 'code'):
log.debug('Failed with error code - %s.' % e.code)
elif hasattr(e, 'reason'):
log.debug("The error object has the following 'reason' attribute :"+e.reason)
sys.exit()
else:
if cj is None:
log.debug('We don\'t have a cookie library available - sorry.')
else:
print 'These are the cookies we have received so far :'
for index, cookie in enumerate(cj):
print index, ' : ', cookie
# save the cookies again
cj.save(COOKIEFILE)
#return the data
return handle.read()
# FIXME: I need to fix this so that it takes into account any cookie data we may have stored
def get_page(*args, **query):
if len(args) != 1:
raise ValueError(
"post_page() takes exactly 1 argument (%d given)" % len(args)
)
url = args[0]
query = urllib.urlencode(list(query.iteritems()))
if not url.endswith('/') and query:
url += '/'
if query:
url += "?" + query
resource = urllib.urlopen(url)
logger.debug('GET url "%s" => "%s", code %d' % (url,
resource.url,
resource.code))
return resource.read()
When I attempt to log in, I pass the correct username and pwd,. yet the login fails, and no cookie data is saved.
My two questions are:
can anyone see whats wrong with the login() function, and how may I fix it?
how may I modify the get_page() function to make use of any cookie info I have saved ?
