Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- from bs4 import BeautifulSoup
- import urllib2 #http://love-python.blogspot.nl/2008/02/get-html-source-of-url.html
- url = 'http://services.runescape.com/m=itemdb_rs/top100.ws'
- usock = urllib2.urlopen(url)
- data = usock.read()
- usock.close()
- soup = BeautifulSoup(BeautifulSoup(data).find_all('tbody')[0])
- tr = soup.find_all("tr")
- obj = {}
- for thistr in tr:
- bstr = BeautifulSoup(thistr)
- td = bstr.find_all('td')
- obj[bstr['data-item-id']] = BeautifulSoup(td[5]).string
- #obj now contains all data in the format {"2":"107.6m",...}
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement