A python script that automatically downloads all comments from a theguardian.com article

GuardianCommentDownloader.py

import urllib2
import re
import time
import sys

# This script will download all comments from a Guardian (theguardian.com) article into a single .html file
# Use 'File ID' to easily identify your file later (this could also be something like a Citavi identifier)
# Ingo Kleiber <ikleiber@googlemail.com>

print """\
   _____                     _ _             _____  _      
  / ____|                   | (_)           |  __ \| |     
 | |  __ _   _  __ _ _ __ __| |_  __ _ _ __ | |  | | |     
 | | |_ | | | |/ _` | '__/ _` | |/ _` | '_ \| |  | | |     
 | |__| | |_| | (_| | | | (_| | | (_| | | | | |__| | |____ 
  \_____|\__,_|\__,_|_|  \__,_|_|\__,_|_| |_|_____/|______|

"""                                                         

print 'Guardian Comment Downloader v.1.1 - Ingo Kleiber (05.01.2015)\n'
guardianLink = raw_input ('> Guadian Link: ')
fileId = raw_input('> File ID: ')

#Figuring out the PageId
pageResponse = urllib2.urlopen(guardianLink)
commentsMatch = re.search(r'/p/(.*?)"', pageResponse.read(), re.M|re.I)
if commentsMatch:
	pageId = commentsMatch.group(1)
	print '[+] pageId has been retrieved ('+pageId+')'
else:
	sys.exit('[-] Could not retrieve pageId!')

#Retrieving comments
downloadCount = 1
downloadError = 0

startTime = time.time()
fileName = 'GuardianDownload_' + pageId + '_' + str(startTime) + '_' + fileId + '.html'
f = open(fileName, 'a')

print '[~] Start downloading pages ...'
while downloadError == 0:
	try:
		response = urllib2.urlopen('http://www.theguardian.com/discussion/p/' + pageId + '?page=' + str(downloadCount))
		html = response.read()
		f.write(html)
		print '[+] Page: ' + str(downloadCount) + ' has been downloaded!'
		downloadCount = downloadCount + 1
	except:
		downloadError = 1

stopTime = time.time()
runningTime = (stopTime - startTime)/60;
print '[=] ' + str(downloadCount-1) + ' pages have been downloaded in ' + str(round(runningTime,2)) + ' minutes' 		
f.close()