def get_player_info_from_url(playerid):
"""
Gets ID, Name, Hand, Pos, DOB, Height, Weight, and Nationality from the NHL API.
:param playerid: int, the player id
:return: dict with player ID, name, handedness, position, etc
"""
page = helpers.try_url_n_times(get_player_url(playerid))
data = json.loads(page)
info = {}
vars_to_get = {'ID': ['people', 0, 'id'],
'Name': ['people', 0, 'fullName'],
'Hand': ['people', 0, 'shootsCatches'],
'Pos': ['people', 0, 'primaryPosition', 'code'],
'DOB': ['people', 0, 'birthDate'],
'Height': ['people', 0, 'height'],
'Weight': ['people', 0, 'weight'],
'Nationality': ['people', 0, 'nationality']}
for key, val in vars_to_get.items():
info[key] = helpers.try_to_access_dict(data, *val)
# Remove the space in the middle of height
if info['Height'] is not None:
info['Height'] = info['Height'].replace(' ', '')
return info
def get_game_from_url(season, game):
"""
Gets the page containing information for specified game from NHL API.
:param season: int, the season
:param game: int, the game
:return: str, the page at the url
"""
return helpers.try_url_n_times(get_game_url(season, game))
def get_team_info_from_url(teamid):
"""
Pulls ID, abbreviation, and name from the NHL API.
:param teamid: int, the team ID
:return: (id, abbrev, name)
"""
teamid = int(teamid)
page = helpers.try_url_n_times(get_team_info_url(teamid))
if page is None:
return None, None, None
teaminfo = json.loads(page)
tid = teaminfo['teams'][0]['id']
tabbrev = teaminfo['teams'][0]['abbreviation']
tname = teaminfo['teams'][0]['name']
return tid, tabbrev, tname
def scrape_game_toi(season, game, force_overwrite=False):
"""
This method scrapes the toi for the given game.
:param season: int, the season
:param game: int, the game
:param force_overwrite: bool. If file exists already, won't scrape again
:return: nothing
"""
filename = get_game_raw_toi_filename(season, game)
if not force_overwrite and os.path.exists(filename):
return False
page = helpers.try_url_n_times(get_shift_url(season, game))
save_raw_toi(page, season, game)
# ed.print_and_log('Scraped toi for {0:d} {1:d}'.format(season, game))
sleep(1) # Don't want to overload NHL servers
# It's most efficient to parse with page in memory, but for sake of simplicity will do it later
# toi = read_toi_from_page(page)
return True
def generate_season_schedule_file(season, force_overwrite=True):
"""
Reads season schedule from NHL API and writes to file.
The output contains the following columns:
- Season: int, the season
- Date: str, the dates
- Game: int, the game id
- Type: str, the game type (for preseason vs regular season, etc)
- Status: str, e.g. Final
- Road: int, the road team ID
- RoadScore: int, number of road team goals
- RoadCoach str, 'N/A' when this function is run (edited later with road coach name)
- Home: int, the home team ID
- HomeScore: int, number of home team goals
- HomeCoach: str, 'N/A' when this function is run (edited later with home coach name)
- Venue: str, the name of the arena
- Result: str, 'N/A' when this function is run (edited accordingly later from PoV of home team: W, OTW, SOL, etc)
- PBPStatus: str, 'Not scraped' when this function is run (edited accordingly later)
- TOIStatus: str, 'Not scraped' when this function is run (edited accordingly later)
:param season: int, the season
:param force_overwrite: bool. If True, generates entire file from scratch.
If False, only redoes when not Final previously.
:return: Nothing
"""
page = helpers.try_url_n_times(get_season_schedule_url(season))
page2 = json.loads(page)
df = _create_schedule_dataframe_from_json(page2)
df.loc[:, 'Season'] = season
# Last step: we fill in some info from the pbp. If current schedule already exists, fill in that info.
df = _fill_in_schedule_from_pbp(df, season)
write_season_schedule(df, season, force_overwrite)
def scrape_game_toi_from_html(season, game, force_overwrite=True):
"""
This method scrapes the toi html logs for the given game.
:param season: int, the season
:param game: int, the game
:param force_overwrite: bool. If file exists already, won't scrape again
:return: nothing
"""
filenames = (get_home_shiftlog_filename(season, game),
get_road_shiftlog_filename(season, game))
urls = (get_home_shiftlog_url(season,
game), get_road_shiftlog_url(season, game))
filetypes = ('H', 'R')
for i in range(2):
filename = filenames[i]
if not force_overwrite and os.path.exists(filename):
pass
page = helpers.try_url_n_times(urls[i])
save_raw_toi_from_html(page, season, game, filetypes[i])
sleep(1) # Don't want to overload NHL servers
print('Scraped html toi for {0:d} {1:d}'.format(season, game))
