Advertisement
Joeytje50

Untitled

Nov 29th, 2012
107
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
  1. from bs4 import BeautifulSoup
  2.  
  3. import urllib2 #http://love-python.blogspot.nl/2008/02/get-html-source-of-url.html
  4.  
  5. url = 'http://services.runescape.com/m=itemdb_rs/top100.ws'
  6.  
  7. usock = urllib2.urlopen(url)
  8. data = usock.read()
  9. usock.close()
  10.  
  11. soup = BeautifulSoup(data)
  12.  
  13. tr = soup.find_all("tr")
  14. obj = {}
  15. for thistr in tr:
  16.     if 'data-item-id' in thistr:
  17.         td = thistr.find_all('td')
  18.         obj[thistr['data-item-id']] = td[5].string
  19.  
  20. print obj
  21.  
  22. #obj now contains all data in the format {"2":"107.6m",...}
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement