def dfFromGameLogURL(url):
"""
Takes a url of a player's game log for a given year, returns a DataFrame
"""
glsoup = getSoupFromURL(url)
reg_season_table = glsoup.findAll('table', attrs={'id': 'pgl_basic'}) # id for reg season table
playoff_table = glsoup.findAll('table', attrs={'id': 'pgl_basic_playoffs'}) # id for playoff table
# parse the table header. we'll use this for the creation of the DataFrame
header = []
for th in reg_season_table[0].findAll('th'):
if not th.getText() in header:
header.append(th.getText())
# add in headers for home/away and w/l columns. a must to get the DataFrame to parse correctly
header[5] = u'HomeAway'
header.insert(7, u'WinLoss')
reg = soupTableToDF(reg_season_table, header)
playoff = soupTableToDF(playoff_table, header)
if reg is None:
return playoff
elif playoff is None:
return reg
else:
return pd.concat([reg, playoff])
def dfFromGameLogURL(url):
"""
Takes a url of a player's game log for a given year, returns a DataFrame
"""
glsoup = getSoupFromURL(url)
reg_season_table = glsoup.findAll('table',
attrs={'id': 'pgl_basic'
}) # id for reg season table
playoff_table = glsoup.findAll('table', attrs={'id': 'pgl_basic_playoffs'
}) # id for playoff table
# parse the table header. we'll use this for the creation of the DataFrame
header = []
for th in reg_season_table[0].findAll('th'):
if not th.getText() in header:
header.append(th.getText())
# add in headers for home/away and w/l columns. a must to get the DataFrame to parse correctly
header[5] = u'HomeAway'
header.insert(7, u'WinLoss')
reg = soupTableToDF(reg_season_table, header)
playoff = soupTableToDF(playoff_table, header)
if reg is None:
return playoff
elif playoff is None:
return reg
else:
return pd.concat([reg, playoff])
def getAllPlayers(suppressOutput=True, min_year_active=2004):
players = dict()
for letter in string.ascii_lowercase:
letter_page = getSoupFromURL('https://www.basketball-reference.com/players/{}/'.format(letter), suppressOutput)
if letter_page is None:
continue
all_rows = letter_page.find("table", id="players").find("tbody").find_all("tr")
for row in all_rows:
player = row.find("th", attrs={"data-stat": "player", "scope": "row"})
if player is None:
continue
player = player.find("a")
name = player.get_text()
last_year_active_soup = row.find("td", attrs={"data-stat": "year_max"})
last_year_active = int(last_year_active_soup.get_text())
try:
if last_year_active >= min_year_active:
players[name] = Player(name, 'https://www.basketball-reference.com' + player.attrs['href'])
except Exception as e:
print("ERROR:", e)
sleep(1) # sleeping to be kind for requests
return players
def playoff_dfFromGameLogURL(url):
glsoup = getSoupFromURL(url)
playoff_table = find_playoff_table(glsoup)
header = []
if len(playoff_table) > 0 and playoff_table[0] is not None:
table_header = playoff_table[0].find("thead")
else:
print("Not found playoff season dataframes")
return None
for th in table_header.find_all('th'):
# if not th.getText() in header:
header.append(th.getText())
header.insert(5, 'HomeAway')
header.insert(8, 'WinLoss')
header.pop(0)
header.remove(u'\xa0')
header.remove(u'\xa0')
playoff = soupTableToDF(playoff_table, header)
if playoff is None:
print("Not found playoff season dataframes")
return None
else:
try:
return playoff
except Exception as e:
print("ERROR - Couldn't merge dataframes:", e)
print(playoff)
return None
def pbp_dfFromGameLogURL(url):
glsoup = getSoupFromURL(url)
pbp_table = find_pbp_table(glsoup)
header = []
x = 0
if len(pbp_table) > 0 and pbp_table[0] is not None:
table_header = pbp_table[0].find("thead")
else:
print("Not found playoff season dataframes")
return None
for th in table_header.find_all('th'):
if x > 7:
header.append(th.getText())
x += 1
# the above for loop is aiming to delete overhead of pbp table
# print(header)
pbp = soupTableToDF(pbp_table, header)
if pbp is None:
print("Not found pbp dataframes")
return None
else:
try:
return pbp
except Exception as e:
print("ERROR - Couldn't merge dataframes:", e)
print(pbp)
return None
def getCurrentTeams(suppressOutput=True):
teams = dict()
glsoup = getSoupFromURL('https://www.basketball-reference.com/teams/',
suppressOutput)
active_teams_table = glsoup.find(
'table', id='teams_active') # id for reg season table
all_rows = active_teams_table.find_all("th",
attrs={"data-stat": "franch_name"})
active_teams = list()
for row in all_rows:
team = row.find("a")
if team is None:
continue
active_teams.append(team)
for team in active_teams:
name = team.get_text()
try:
teams[name] = Team(
name,
'https://www.basketball-reference.com' + team.attrs['href'])
except Exception as e:
print("ERROR:", e)
sleep(1) # sleeping to be kind for requests
return teams
def getAllPlayerNamesAndURLS(suppressOutput=True):
names = []
for letter in string.ascii_lowercase:
letter_page = getSoupFromURL(
'https://www.basketball-reference.com/players/{}/'.format(letter),
suppressOutput)
if letter_page is None:
continue
all_rows = letter_page.find("table",
id="players").find("tbody").find_all("tr")
for row in all_rows:
player = row.find("th",
attrs={
"data-stat": "player",
"scope": "row"
})
if player is None:
continue
player = player.find("a")
name = player.get_text()
try:
names.append((name, 'https://www.basketball-reference.com' +
player.attrs['href']))
except Exception as e:
print("ERROR:", e)
sleep(1) # sleeping to be kind for requests
return dict(names)
def getoverView(url_tup):
print("in get overViews")
glsoup = getSoupFromURL(url_tup[1])
id_lst = [
"all_per_game", "all_totals", "all_per_minute", "all_per_poss",
"all_advanced", "all_shooting", "all_pbp", "all_playoffs_per_game",
"all_playoffs_totals", "all_playoffs_per_minute",
"all_playoffs_per_poss", "all_playoffs_advanced",
"all_playoffs_shooting", "all_playoffs_pbp", "all_all_salaries"
]
final_dict = {}
for curr_id in id_lst:
curr_div = glsoup.find("div", {"id": curr_id})
if curr_div != None:
div = curr_div.find("div", {"class": "overthrow table_container"})
table_header_lst = div.find("thead")
th_lst = table_header_lst.find_all("tr")
final_th_header = th_lst[-1]
header_lst = []
th_stuff = final_th_header.find_all("th")
for th_thing in th_stuff:
curr_val = th_thing.get_text()
header_lst.append(curr_val)
curr_table = getovHelper(div)
final_table = curr_table
final_table.insert(0, header_lst)
final_dict[curr_id] = final_table
sleep(2)
return (url_tip[0], final_dict)
def getCurrentPlayerNamesAndURLS(suppressOutput=True):
names = []
for letter in string.ascii_lowercase:
letter_page = getSoupFromURL('http://www.basketball-reference.com/players/%s/' % (letter), suppressOutput)
# we know that all the currently active players have <strong> tags, so we'll limit our names to those
current_names = letter_page.findAll('strong')
for n in current_names:
name_data = n.children.next()
names.append((name_data.contents[0], 'http://www.basketball-reference.com' + name_data.attrs['href']))
time.sleep(1) # sleeping to be kind for requests
return dict(names)
def dfFromGameLogURL(url):
"""
Takes a url of a player's game log for a given year, returns a DataFrame
"""
sleep(1)
glsoup = getSoupFromURL(url)
reg_season_table = glsoup.find_all(
'table', id="pgl_basic") # id for reg season table
playoff_table = find_playoff_table(glsoup)
# parse the table header. we'll use this for the creation of the DataFrame
header = []
if len(reg_season_table) > 0 and reg_season_table[0] is not None:
table_header = reg_season_table[0].find("thead")
else:
print("Error retrieving game log from:")
print(url)
exit(1)
for th in table_header.find_all('th'):
# if not th.getText() in header:
header.append(th.getText())
# add in headers for home/away and w/l columns. a must to get the DataFrame to parse correctly
header.insert(5, 'HomeAway')
header.insert(8, 'WinLoss')
header.pop(0)
header.remove('\xa0')
header.remove('\xa0')
reg = soupTableToDF(reg_season_table, header)
playoff = soupTableToDF(playoff_table, header)
if reg is None:
return playoff
elif playoff is None:
return reg
else:
try:
return pd.concat([reg, playoff])
except Exception as e:
print("ERROR - Couldn't merge dataframes:", e)
print(reg)
print(playoff)
return None
def dfFromGameLogURL(url):
"""
Takes a url of a player's game log for a given year, returns a DataFrame
"""
glsoup = getSoupFromURL(url)
reg_season_table = glsoup.findAll('table',
attrs={'id': 'pgl_basic'
}) # id for reg season table
playoff_table = glsoup.find_all(
string=lambda text: isinstance(text, Comment))
try:
playoff_table = BeautifulSoup(
filter(lambda x: 'pgl_basic_playoffs' in x, playoff_table)[0])
playoff_table = playoff_table.findAll(
'table', attrs={'id':
'pgl_basic_playoffs'}) # id for playoff table
except:
playoff_table = []
# parse the table header. we'll use this for the creation of the DataFrame
header = []
for th in reg_season_table[0].findAll('th'):
if not th.getText() in header:
try:
int(th.getText())
except:
header.append(th.getText())
# add in headers for home/away and w/l columns. a must to get the DataFrame to parse correctly
header[5] = u'HomeAway'
header.insert(7, u'WinLoss')
reg = soupTableToDF(reg_season_table, header)
playoff = soupTableToDF(playoff_table, header)
if reg is None:
return playoff
elif playoff is None:
return reg
else:
return pd.concat([reg, playoff])
def getAllCoaches(suppressOutput=True, min_year_active=2004):
coaches = dict()
glsoup = getSoupFromURL('https://www.basketball-reference.com/coaches/', suppressOutput)
all_rows = glsoup.find("table", id="coaches").find("tbody").find_all("tr")
for row in all_rows:
coach = row.find("th", attrs={"data-stat": "coach", "scope": "row"})
if coach is None:
continue
coach = coach.find("a")
name = coach.get_text()
last_year_active_soup = row.find("td", attrs={"data-stat": "year_max"})
last_year_active = int(last_year_active_soup.get_text())
try:
if last_year_active >= min_year_active:
coaches[name] = Coach(name, 'https://www.basketball-reference.com' + coach.attrs['href'])
except Exception as e:
print("ERROR:", e)
sleep(1) # sleeping to be kind for requests
return coaches
def getCurrentPlayerNamesAndURLS(suppressOutput=True):
names = []
for letter in string.ascii_lowercase:
letter_page = getSoupFromURL('https://www.basketball-reference.com/players/%s/' % (letter), suppressOutput)
if letter_page is None:
continue
# we know that all the currently active players have <strong> tags, so we'll limit our names to those
current_names = letter_page.findAll('strong')
for n in current_names:
name_data = n.children.next()
try:
names.append((name_data.contents[0], 'https://www.basketball-reference.com' + name_data.attrs['href']))
except Exception as e:
pass
sleep(1) # sleeping to be kind for requests
return dict(names)
