hi...
the following sample is an attempt to fetch two subsequent pages from a
sameple site. (it's public) the script attempts to implement a request,
using the POST method, as well as as cookies. Testing using
LiveHttpHeaders/Firefox indicates that the app uses post/cookies, and it
doesn't work if cookies are disabled on the browser.
the query for the post, was obtained via the LiveHttpHeaders app.
I can get the 1st page, but not the 2nd. I'm assuming that I'm somehow
screwing up the use/implementation of the cookies.. Searching the net isn't
shedding any light for now..
After showing the 1sr page, the 2nd page is viewed from the browser, by
selecting a 'next' link, which invokes a jscript submit for the DOM. The
post data is captured via LiveHttpHeaders.. It's this data that forms the
data for the 2nd Post attempt in the test..
Any thoughts/comments/pointers would be helpful... (and yeah the test is
ugly..!)
thanks
-tom
#!/usr/bin/python
#test python script
import re
import urllib
import urllib2
import sys, string, os
from mechanize
import Browser
import mechanize
import cookielib
########################
#
# Parsing App Information
########################
# datafile
cj = "p"
COOKIEFILE = 'cookies.lwp'
#cookielib = 1
urlopen = urllib2.urlopen
#cj = urllib2.cookielib.LWPCookieJar()
cj = cookielib.LWPCookieJar()
#cj = ClientCookie.LWPCookieJar()
Request = urllib2.Request
br = Browser()
if cj != None:
print "sss"
#install the CookieJar for the default CookieProcessor
if os.path.isfile(COOKIEFILE):
cj.load(COOKIEFILE)
print "foo\n"
if cookielib:
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
urllib2.install_opener(opener)
print "foo2\n"
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
values1 = {'name' : 'Michael Foord',
'location' : 'Northampton',
'language' : 'Python' }
headers = { 'User-Agent' : user_agent }
if __name__ == "__main__":
# main app
baseurl="https://pisa.ucsc.edu/class_search/index.php";
print "b = ",baseurl
print "b = ",headers
query="action=results&binds%5B%3Aterm%5D=2100&binds%5B%3Areg_status%5D=O&bin
ds%5B%3Asubject%5D=&binds%5B%3Acatalog_nbr_op%5D=%3D&binds%5B%3Acatalog_nbr%
5D=&binds%5B%3Atitle%5D=&binds%5B%3Ainstr_name_op%5D=%3D&binds%5B%3Ainstruct
or%5D=&binds%5B%3Age%5D=&binds%5B%3Acrse_units_op%5D=%3D&binds%5B%3Acrse_uni
ts_from%5D=&binds%5B%3Acrse_units_to%5D=&binds%5B%3Acrse_units_exact%5D=&bin
ds%5B%3Adays%5D=&binds%5B%3Atimes%5D=&binds%5B%3Aacad_career%5D="
request = urllib2.Request(baseurl, query, headers)
response = urllib2.urlopen(request)
print "gggg \n"
#print req
print "\n gggg 555555\n"
print "res = ",response
x1 = response.read()
#x1 = res.read()
print x1
#sys.exit()
cj.save(COOKIEFILE)
# resave cookies
if cj is None:
print "We don't have a cookie library available - sorry."
print "I can't show you any cookies."
else:
print 'These are the cookies we have received so far :'
for index, cookie in enumerate (cj):
print index, ' : ', cookie
cj.save(COOKIEFILE)
print "ffgg \n"
for index, cookie in enumerate (cj):
print index, ' : ', cookie
#baseurl ="http://students.yale.edu/oci/resultList.jsp";
baseurl="https://pisa.ucsc.edu/class_search/index.php";
query="action=next&Rec_Dur=100&sel_col%5Bclass_nbr%5D=1&sel_col%5Bclass_id%5
D=1&sel_col%5Bclass_title%5D=1&sel_col%5Btype%5D=1&sel_col%5Bdays%5D=1&sel_c
ol%5Btimes%5D=1&sel_col%5Binstr_name%5D=1&sel_col%5Bstatus%5D=1&sel_col%5Ben
rl_cap%5D=1&sel_col%5Benrl_tot%5D=1&sel_col%5Bseats_avail%5D=1&sel_col%5Bloc
ation%5D=1"
request = urllib2.Request(baseurl, query, headers)
response = urllib2.urlopen(request)
print "gggg \n"
#print req
print "\n gggg 555555\n"
print "res = ",response
x1 = response.read()
#x1 = res.read()
print x1
sys.exit()
req = Request(baseurl, query, headers)
print "gggg \n"
#print req
print "\n gggg 555555\n"
#br.open(req)
res = urlopen(req)
print "gggg 000000000000\n"
x1 = res.read()
print x1
sys.exit()
--
http://mail.python.org/mailman/listinfo/python-list
