Created
April 4, 2012 00:34
-
-
Save JDougherty/2296700 to your computer and use it in GitHub Desktop.
FreeCCNAWorkbook Scraper
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
# This is a quick and dirty script to grab the practice questions from | |
# the Free CCNA Workbook (http://www.freeccnaworkbook.com/) to place | |
# each question in its own file and be able to view one question at a time | |
from BeautifulSoup import BeautifulSoup | |
import urllib2 | |
page = urllib2.urlopen("http://www.freeccnaworkbook.com/labs/free-ccna-workbook-ccna-practice-exam/") | |
soup = BeautifulSoup(page) | |
divs=soup.findAll('div',attrs={"class" : "quizzin-question"}) | |
i=1 | |
for d in divs: | |
f = open('./'+str(i)+'.html', 'w') | |
q=d.find('div',attrs={"class" : "question-content"}) | |
a=d.findAll('label') | |
f.write(q) | |
f.write('</br>') | |
for l in a: | |
f.write(l.text.encode("utf8").strip('\n')) | |
f.write('</br>') | |
f.write('<a href="'+str(i+1)+'">Next</a>') | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment