from bs4 import BeautifulSoup
from pprint import pprint
soup = BeautifulSoup(html)
h2s = soup.select("h2") #get all h2 elements
tables = soup.select("table") #get all tables
first = True
title =""
players = []
for i,table in enumerate(tables):
if first:
#every h2 element has 2 tables. table size = 8, h2 size = 4
#so for every 2 tables 1 h2
title = h2s[int(i/2)].text
for tr in table.select("tr"):
player = (title,) #create a player
for td in tr.select("td"):
player = player + (td.text,) #add td info in the player
if len(player) > 1:
#If the tr contains a player and its not only ("Goalkeaper") add it
players.append(player)
first = not first
pprint(players)
：
[('Goalkeepers', 'Cech', 'Chelsea', '30', '£6.4'),
('Goalkeepers', 'Hart', 'Man City', '28', '£6.4'),
('Goalkeepers', 'Krul', 'Newcastle', '21', '£5.0'),
('Goalkeepers', 'Ruddy', 'Norwich', '25', '£5.0'),
('Goalkeepers', 'Vorm', 'Swansea', '19', '£5.0'),
('Goalkeepers', 'Stekelenburg', 'Fulham', '6', '£4.9'),
('Goalkeepers', 'Pantilimon', 'Man City', '0', '£4.9'),
('Goalkeepers', 'Lindegaard', 'Man Utd', '0', '£4.9'),
('Goalkeepers', 'Butland', 'Stoke City', '0', '£4.9'),
('Goalkeepers', 'Foster', 'West Brom', '13', '£4.9'),
('Goalkeepers', 'Viviano', 'Arsenal', '0', '£4.8'),
('Goalkeepers', 'Schwarzer', 'Chelsea', '0', '£4.7'),
('Goalkeepers', 'Boruc', 'Southampton', '42', '£4.7'),
('Goalkeepers', 'Myhill', 'West Brom', '15', '£4.5'),
('Goalkeepers', 'Fabianski', 'Arsenal', '0', '£4.4'),
('Goalkeepers', 'Gomes', 'Tottenham', '0', '£4.4'),
('Goalkeepers', 'Friedel', 'Tottenham', '0', '£4.4'),
('Goalkeepers', 'Henderson', 'West Ham', '0', '£4.0'),
('Defenders', 'Baines', 'Everton', '43', '£7.7'),
('Defenders', 'Vertonghen', 'Tottenham', '34', '£7.0'),
('Defenders', 'Taylor', 'Cardiff City', '14', '£4.5'),
('Defenders', 'Zverotic', 'Fulham', '0', '£4.5'),
('Defenders', 'Davies', 'Hull City', '28', '£4.5'),
('Defenders', 'Flanagan', 'Liverpool', '0', '£4.5'),
('Defenders', 'Dawson', 'West Brom', '0', '£3.9'),
('Defenders', 'Potts', 'West Ham', '0', '£3.9'),
('Defenders', 'Spence', 'West Ham', '0', '£3.9'),
('Midfielders', 'Özil', 'Arsenal', '24', '£10.6'),
('Midfielders', 'Redmond', 'Norwich', '20', '£5.0'),
('Midfielders', 'Mavrias', 'Sunderland', '5', '£5.0'),
('Midfielders', 'Gera', 'West Brom', '0', '£5.0'),
('Midfielders', 'Essien', 'Chelsea', '0', '£4.9'),
('Midfielders', 'Brown', 'West Brom', '0', '£4.3'),
('Forwards', 'van Persie', 'Man Utd', '24', '£13.9'),
('Forwards', 'Cornelius', 'Cardiff City', '1', '£5.4'),
('Forwards', 'Elmander', 'Norwich', '7', '£5.4'),
('Forwards', 'Murray', 'Crystal Palace', '0', '£5.3'),
('Forwards', 'Vydra', 'West Brom', '2', '£5.3'),
('Forwards', 'Proschwitz', 'Hull City', '0', '£4.3')]
602392714
清零编程群