SHOW:
|
|
- or go back to the newest paste.
| 1 | - | from bs4 import BeautifulSoup |
| 1 | + | from lxml import parse |
| 2 | ||
| 3 | - | import urllib2 #http://love-python.blogspot.nl/2008/02/get-html-source-of-url.html |
| 3 | + | doc = parse('http://services.runescape.com/m=itemdb_rs/top100.ws').getroot()
|
| 4 | ||
| 5 | - | url = 'http://services.runescape.com/m=itemdb_rs/top100.ws' |
| 5 | + | |
| 6 | cells = doc.cssselect('tbody tr[data-item-id] td:last-child')
| |
| 7 | - | usock = urllib2.urlopen(url) |
| 7 | + | for td in cells: |
| 8 | - | data = usock.read() |
| 8 | + | obj[td.get('data-item-id')] = td.text_content()
|
| 9 | - | usock.close() |
| 9 | + | |
| 10 | print obj | |
| 11 | - | soup = BeautifulSoup(data) |
| 11 | + | |
| 12 | #obj now contains all data in the format {"2":"107.6m",...} |
