def __init__(self):
self.schedule = GetSchedule()
self.url = "http://www.womensprosoccer.com/Home/schedule/2011-wps-schedule"
class WomensProSoccer(object):
"""Download schedule from official WPS website and process information."""
def __init__(self):
self.schedule = GetSchedule()
self.url = "http://www.womensprosoccer.com/Home/schedule/2011-wps-schedule"
def crawl(self):
"""Crawl the page with BeautifulSoup for applicable information."""
schedule = []
soup = self.schedule.load_page(self.url)
print 'Locating scheduling section'
tbody = soup.find("tbody").findAll('tr')
del tbody[0] # Remove table header
for row in tbody:
stat = row.findAll("div", {"align": "center"})
stat = [self.cleaner(info, 1) for info in stat] # Remove <div>
# If the row consists of one column it contains the date. This is
#quicker than searching for <th> with BeatifulSoup
if len(stat) == 1:
date = self.date(stat[0])
else:
match = {} # Dictionary to hold match information
match['date'] = date # Assign the date of the last header row
match['team1'] = stat[0][0]
match['team2'] = stat[1][0]
match['venue'] = stat[2][0]
match.update(self.score(stat[3]))
# Fourth element is a link to match report
print stat[5]
match['attendance'] = self.attendance(stat[5])
print match
# Add match dictionary to schedule list
schedule.append(match)
return schedule
def cleaner(self, html, repeat):
"""Recursively remove tags for a certain count, returning a list."""
count = 0
html = unicode(html)
soup = BeautifulSoup(html)
for element in soup.findAll(True):
if count == repeat:
break
else:
content = element.contents
count += 1
return content
def date(self, html):
"""Find the date in a table row. If playoff match create element."""
row = self.cleaner(html, 1) # Remove <strong>
if len(row) == 1:
date = row[0]
else: # Process ugly formatting of playoff games
row = [element for element in row if isinstance(element, NavigableString)]
date = row[-1] #TODO(pamolloy): Store game title
return date
def score(self, section):
"""Process the score into number of (penalty) goals for each team"""
match = {}
if section[0] == 'Postponed':
pass
elif section[0] == '\n': # Penalty goals
section = section[1]
goals = re.findall('\d', unicode(section))
match['goals1'] = int(goals[0])
match['goals2'] = int(goals[1])
match['pens1'] = int(goals[2])
match['pens2'] = int(goals[3])
else:
section = section[0]
match['goals1'] = int(section[0])
match['goals2'] = int(section[4])
return match
def attendance(self, html):
"""Find the attendance within list"""
print html
if len(html) == 1:
attendance = html[0]
elif len(html) == 2:
print html
attendance = [element for element in html if isinstance(element, NavigableString)]
print attendance
attendance = attendance[0]
elif len(html) == 0: # Postponed game
attendance = int()
return attendance
def __init__(self):
self.schedule = GetSchedule()
self.url = "http://www.ussoccer.com/Schedule-Tickets/Schedule.aspx"
self.att = {"class": "genericTable"}
class USSoccer(object):
"""Download schedule from official USSF website and process information."""
def __init__(self):
self.schedule = GetSchedule()
self.url = "http://www.ussoccer.com/Schedule-Tickets/Schedule.aspx"
self.att = {"class": "genericTable"}
def crawl(self):
"""Crawl the page with BeautifulSoup for applicable information."""
schedule = []
soup = self.schedule.load_page(self.url)
print 'Locating scheduling section: {}'.format(self.att.values()[0])
table = soup.find("table", self.att).findAll('tr')
del table[0] # Remove table header
for row in table:
#stat = row.findAll("div", {"align": "center"})
stats = row.contents
stats = [element for element in stats if element != '\n']
stats = [element.contents for element in stats] # Remove <td>
match = {} # Dictionary to hold match information
match['date'] = self.cleaner(stats[0], 1)[0]
match['time'] = self.cleaner(stats[2], 1)[0]
stadium = self.cleaner(stats[3][0], 1)[0]
city = stats[3][2]
match['venue'] = '{}, {}'.format(stadium, city)
teams = stats[1][0]
teams = teams.split(' vs. ')
match['team1'] = teams[0]
match['team2'] = teams[1]
channels = stats[4][0]
channels = channels.strip()
if channels == ' ':
pass
else:
channels = channels.split(', ')
count = 0
for station in channels:
match['tv{}'.format(count)] = station
count += 1
# Fifth element is "Info Center"
print match
# Add match dictionary to schedule list
schedule.append(match)
return schedule
def cleaner(self, html, repeat):
"""Recursively remove tags for a certain count, returning a list."""
count = 0
html = unicode(html)
soup = BeautifulSoup(html)
for element in soup.findAll(True):
if count == repeat:
break
else:
content = element.contents
count += 1
return content
def __init__(self):
self.schedule = GetSchedule()
self.url = "http://www.mlssoccer.com/schedule?month=all&year=2011"
self.att = "schedule-page"
class MLSSoccer(object):
"""Download schedule from official MLS website and process information."""
def __init__(self):
self.schedule = GetSchedule()
self.url = "http://www.mlssoccer.com/schedule?month=all&year=2011"
self.att = "schedule-page"
def crawl(self):
"""Crawl the page with BeautifulSoup for applicable information."""
schedule = []
soup = self.schedule.load_page(self.url)
print 'Locating scheduling section: {}'.format(att)
section = soup.find("div", {"class": self.att})
for table in section.findAll("table"):
table_body = table.find('tbody')
date = self.date(table)
table_rows = table_body.findAll('tr')
for row in table_rows:
match = {}
# NOT easily processed information
match['date'] = date
details = self.details(row)
match.update(details)
goals = self.score(row)
match.update(goals)
# Easily processed information
match['venue'] = self.generic(row, "views-field venue")
match['team1'] = self.generic(row, "views-field home-team")
match['team2'] = self.generic(row, "views-field away-team")
# Add match dictionary to schedule list
schedule.append(match)
return schedule
def date(self, section):
"""Find the date of each match based on the last preceding <h3> tag"""
date = section.findPreviousSibling("h3")
date = BeautifulSoup(unicode(date))
date = date.h3.contents[0] # Remove tags
return date
def details(self, section):
"""Process the venue and channels from the details section"""
match = {}
html = section.find("td", {"class": "views-field start-time"})
details = html.contents
# If the game has passed, ignore "Final"
if details[0] == u'Final':
return match
else:
match['hour'] = details[0]
count = 0
channels = html.findAll('strong')
for station in channels:
station = BeautifulSoup('{}'.format(station))
match['tv{}'.format(count)] = station.strong.contents[0]
count += 1
return match
def score(self, section):
"""Process the score into number of (penalty) goals for each team"""
match = {}
score = section.find("td", {"class": "views-field score"}).contents
# Ignore score for upcoming games, which return empty list
if score == []:
return match
else:
score = score[0] # Select first string from list
# Store penalties
if re.search('(\(|\))', score):
match['goals1'] = int(score[0])
match['goals2'] = int(score[8])
match['pens1'] = int(score[3])
match['pens2'] = int(score[11])
elif re.search('[0-9]', score):
match['goals1'] = int(score[0])
match['goals2'] = int(score[4])
else: pass
return match
def generic(self, section, attribute):
"""Find and return the match venue."""
info = section.find("td", {"class": attribute}).contents[0]
return info
