Last active
January 5, 2016 19:04
-
-
Save IngoKl/3ebd968ef3c6da406638 to your computer and use it in GitHub Desktop.
A python script that automatically downloads all comments from a theguardian.com article
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment