Advertisement
Joeytje50

Untitled

Nov 30th, 2012
135
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).find_all('tbody')[0]
  12.  
  13. tr = soup.find_all('tr')
  14. itnames = {}
  15. itids = {}
  16. for thistr in tr:
  17.     td = thistr.find_all('td')
  18.     a = td[0].find_all('a')[0]
  19.     id = a['href'][a['href'].index('obj=')+4:]
  20.     val = td[5].string
  21.     itnames[a.string] = val
  22.     itids[id] = val
  23.  
  24. print obj
  25.  
  26. # itids now contains all data in the format {"2":"107.6m",...}
  27. # itnames now contains all data in the format {"cannonball":"107.6m",...}
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement