scrapper2.py

#!/usr/bin/env python
__author__ = 'Ernest'

# scrape http://www.bbc.co.uk/sport/football/fixtures for up and coming matches.

from bs4 import BeautifulSoup
from urllib2 import urlopen

BASE_URL = "http://www.bbc.co.uk/sport/football/fixtures"

def get_category_links(section_url):
    html = urlopen(section_url).read()
    soup = BeautifulSoup(html, "lxml")
    fixtures = soup.find("div", "fixtures-table full-table-medium")
    category_links = [BASE_URL + dd.a["href"] for dd in fixtures.findAll("dd")]
    return category_links