def get_team_ids(cls, html):
rows = html.findAll('tr')
row1 = rows[1]
row2 = rows[2]
link1 = row1.find('a')
team1_id, team2_id = None, None
if link1:
url = link1['href']
team1_id = nscr.url_to_teamid(url)
link2 = row2.find('a')
if link2:
url = link2['href']
team2_id = nscr.url_to_teamid(url)
return team1_id, team2_id
def get_team_ids(cls, html):
rows = html.findAll('tr')
row1 = rows[1]
row2 = rows[2]
link1 = row1.find('a')
team1_id, team2_id = None, None
if link1:
url = link1['href']
team1_id = nscr.url_to_teamid(url)
link2 = row2.find('a')
if link2:
url = link2['href']
team2_id = nscr.url_to_teamid(url)
return team1_id, team2_id
def _process_schedule_row(row, team_id):
"""Extract useful information about a game from its row representation"""
tds = row.findAll('td')
if len(tds) != 3:
return None
date_string = tds[0].get_text()
game_date = datetime.strptime(date_string, '%m/%d/%Y').date()
opp_link = tds[1].find('a')
opp_text = tds[1].get_text()
if opp_link is not None:
opp_id = nscr.url_to_teamid(opp_link['href'])
else:
opp_id = None
opp, neutral_site, loc = nscr.parse_opp_string(opp_text)
if loc == 'A':
hteam_id = opp_id
ateam_id = team_id
else:
hteam_id = team_id
ateam_id = opp_id
neutral = True if neutral_site else False
outcome_string = tds[2].get_text()
game_link = tds[2].find('a')
if game_link is not None:
game_url = game_link['href']
game_id = nscr.game_link_to_gameid(game_url)
else:
game_id = None
outcome, score, opp_score, num_ot = nscr.parse_outcome(outcome_string)
home_score, away_score, home_outcome = \
ScheduleScraper._process_score(score, opp_score, loc)
return [game_id, game_date, hteam_id, ateam_id, opp, neutral,
neutral_site, home_outcome, num_ot, home_score, away_score]
def get_team_schedule(soup, url):
"""
INPUT: BeautifulSoup, string
OUTPUT: 2D-Array
Get a 2D array representation of the team's scheduled games including various
information about each game.
"""
team_id = nscr.url_to_teamid(url)
tables = soup.findAll('table', {'class': 'mytable'})
if len(tables) > 0:
schedule_table = tables[0]
else:
return []
table_rows = schedule_table.findAll('tr')
games = []
for idx, row in enumerate(table_rows):
# skip the title row and header row
if idx < 2:
continue
game_info = ScheduleScraper._process_schedule_row(row, team_id)
if game_info is not None:
games.append(game_info)
return games
def get_team_schedule(soup, url):
"""
INPUT: BeautifulSoup, string
OUTPUT: 2D-Array
Get a 2D array representation of the team's scheduled games including various
information about each game.
"""
team_id = nscr.url_to_teamid(url)
tables = soup.findAll('table', {'class': 'mytable'})
if len(tables) > 0:
schedule_table = tables[0]
else:
return []
table_rows = schedule_table.findAll('tr')
games = []
for idx, row in enumerate(table_rows):
# skip the title row and header row
if idx < 2:
continue
game_info = ScheduleScraper._process_schedule_row(row, team_id)
if game_info is not None:
games.append(game_info)
return games
def extract_teams(cls, soup):
atags = soup.findAll('a')
atags = filter(lambda a: 'team/index' in a['href'], atags)
ncaaids = [nscr.url_to_teamid(a['href']) for a in atags]
ncaa_names = [a.get_text().strip() for a in atags]
assert len(ncaaids) == len(ncaa_names)
return ncaaids, ncaa_names
def extract_teams(cls, soup):
atags = soup.findAll('a')
atags = filter(lambda a: 'team/index' in a['href'], atags)
ncaaids = [nscr.url_to_teamid(a['href']) for a in atags]
ncaa_names = [a.get_text().strip() for a in atags]
assert len(ncaaids) == len(ncaa_names)
return ncaaids, ncaa_names
def get_team_ids_from_header(cls, htable):
header_rows = htable.findAll('tr')
assert len(header_rows) == 3, "bad header"
team_ids = []
for row in header_rows[1:]:
tds = row.findAll('td')
if len(tds) > 1:
team_cell = tds[0]
a = team_cell.find('a')
if a is not None:
url = a['href']
team_id = nscr.url_to_teamid(url)
else:
team_id = None
else:
team_id = None
team_ids.append(team_id)
return team_ids
def get_team_ids_from_header(cls, htable):
header_rows = htable.findAll('tr')
assert len(header_rows) == 3, "bad header"
team_ids = []
for row in header_rows[1:]:
tds = row.findAll('td')
if len(tds) > 1:
team_cell = tds[0]
a = team_cell.find('a')
if a is not None:
url = a['href']
team_id = nscr.url_to_teamid(url)
else:
team_id = None
else:
team_id = None
team_ids.append(team_id)
return team_ids
def _process_schedule_row(row, team_id):
"""Extract useful information about a game from its row representation"""
tds = row.findAll('td')
if len(tds) != 3:
return None
date_string = tds[0].get_text()
game_date = datetime.strptime(date_string, '%m/%d/%Y').date()
opp_link = tds[1].find('a')
opp_text = tds[1].get_text()
if opp_link is not None:
opp_id = nscr.url_to_teamid(opp_link['href'])
else:
opp_id = None
opp, neutral_site, loc = nscr.parse_opp_string(opp_text)
if loc == 'A':
hteam_id = opp_id
ateam_id = team_id
else:
hteam_id = team_id
ateam_id = opp_id
neutral = True if neutral_site else False
outcome_string = tds[2].get_text()
game_link = tds[2].find('a')
if game_link is not None:
game_url = game_link['href']
game_id = nscr.game_link_to_gameid(game_url)
else:
game_id = None
outcome, score, opp_score, num_ot = nscr.parse_outcome(outcome_string)
home_score, away_score, home_outcome = \
ScheduleScraper._process_score(score, opp_score, loc)
return [
game_id, game_date, hteam_id, ateam_id, opp, neutral, neutral_site,
home_outcome, num_ot, home_score, away_score
]