scrape the BBC sport website.

sportScrape.py

#!/usr/bin/env python
# encoding: utf-8
# author: Ernest
# created: 03/02/2016
# http://goo.gl/pXfFe1

"""
Description
Return the scores and table for a given league using BS4. Change the url to get the given league.

premier-league
championship
spanish-la-liga
"""

from bs4 import BeautifulSoup
from urllib.request import urlopen
import csv

url = 'http://www.bbc.com/sport/football/premier-league/results'
page = urlopen(url).read()
soup = BeautifulSoup(page, "html.parser")

def has_class_but_no_id(tag):
    return tag.has_attr('score')

writer = csv.writer(open("webScraper.csv", "w"))


for match in soup.find_all('td', class_='match-details'):
    home_tag = match.find('span', class_='team-home')
    home = home_tag and ''.join(home_tag.stripped_strings)
    score_tag = match.find('span', class_='score')
    score = score_tag and ''.join(score_tag.stripped_strings)
    away_tag = match.find('span', class_='team-away')
    away = away_tag and ''.join(away_tag.stripped_strings)
    if home and score and away:
        print(home, score, away)

url2 = "http://www.bbc.com/sport/football/spanish-la-liga/table"
soup = BeautifulSoup(urlopen(url2).read(), "html.parser")
for row in soup("table", {"class": "table-stats"})[0].tbody("tr"):
    tds = row("td")
    print(tds[1].contents[2].string, tds[2].string)