def scrape_date_range(from_date, to_date, if_scrape_shifts, data_format='csv', preseason=False, rescrape=False,
docs_dir=False):
"""
Scrape games in given date range
:param from_date: date you want to scrape from
:param to_date: date you want to scrape to
:param if_scrape_shifts: Boolean indicating whether to also scrape shifts
:param data_format: format you want data in - csv or pandas (csv is default)
:param preseason: Boolean indicating whether to include preseason games (default if False)
This is may or may not work!!! I don't give a shit.
:param rescrape: If you want to rescrape pages already scraped. Only applies if you supply a docs dir. (def. = None)
:param docs_dir: Directory that either contains previously scraped docs or one that you want them to be deposited
in after scraping. When True it'll refer to (or if needed create) such a repository in the home
directory. When provided a string it'll try to use that. Here it must be a valid directory otheriwse
it won't work (I won't make it for you). When False the files won't be saved.
:return: Dictionary with DataFrames and errors or None
"""
# First check if the inputs are good
shared.check_data_format(data_format)
shared.check_valid_dates(from_date, to_date)
# Check on the docs_dir and re_scrape
shared.add_dir(docs_dir)
shared.if_rescrape(rescrape)
games = json_schedule.scrape_schedule(from_date, to_date, preseason)
pbp_df, shifts_df = scrape_list_of_games(games, if_scrape_shifts)
if data_format.lower() == 'csv':
shared.to_csv(from_date + '--' + to_date, pbp_df, "nhl", "pbp")
shared.to_csv(from_date + '--' + to_date, shifts_df, "nhl", "shifts")
else:
return {"pbp": pbp_df, "shifts": shifts_df} if if_scrape_shifts else {"pbp": pbp_df}
def scrape_schedule(from_date, to_date, data_format='pandas', rescrape=False, docs_dir=False):
"""
Scrape the games schedule in a given range.
:param from_date: date you want to scrape from
:param to_date: date you want to scrape to
:param data_format: format you want data in - csv or pandas (pandas is default)
:param rescrape: If you want to rescrape pages already scraped. Only applies if you supply a docs dir. (def. = None)
:param docs_dir: Directory that either contains previously scraped docs or one that you want them to be deposited
in after scraping. When True it'll refer to (or if needed create) such a repository in the home
directory. When provided a string it'll try to use that. Here it must be a valid directory otheriwse
it won't work (I won't make it for you). When False the files won't be saved.
:return: DataFrame of None
"""
cols = ["game_id", "date", "venue", "home_team", "away_team", "start_time", "home_score", "away_score", "status"]
# First check if the inputs are good
shared.check_data_format(data_format)
shared.check_valid_dates(from_date, to_date)
# Check on the docs_dir and re_scrape
shared.add_dir(docs_dir)
shared.if_rescrape(rescrape)
print("Scraping the schedule between {} and {}".format(from_date, to_date))
# live = True allows us to scrape games that aren't final
sched = json_schedule.scrape_schedule(from_date, to_date, preseason=True, not_over=True)
sched_df = pd.DataFrame(sched, columns=cols)
if data_format.lower() == 'csv':
shared.to_csv(from_date + '--' + to_date, sched_df, "nhl", "schedule")
else:
return sched_df
def scrape_date_range(from_date,
to_date,
data_format='csv',
rescrape=False,
docs_dir=None):
"""
Scrape games in given date range
:param from_date: date you want to scrape from
:param to_date: date you want to scrape to
:param data_format: format you want data in - csv or pandas (csv is default)
:param rescrape: If you want to rescrape pages already scraped. Only applies if you supply a docs dir. (def. = None)
:param docs_dir: Directory that either contains previously scraped docs or one that you want them to be deposited
in after scraping. (default is None)
:return: Dictionary with DataFrames and errors or None
"""
# First check if the inputs are good
shared.check_data_format(data_format)
shared.check_valid_dates(from_date, to_date)
# Check on the docs_dir and re_scrape
shared.add_dir(docs_dir)
shared.if_rescrape(rescrape)
# Get dates and convert to just a list of game ids
games = html_schedule.scrape_dates(from_date, to_date)
game_ids = [game['game_id'] for game in games]
# Scrape all PBP
pbp_df = scrape_list_of_games(game_ids)
# Merge in subtype
pbp_df = pd.merge(pbp_df,
pd.DataFrame(games, columns=['game_id', 'sub_type']),
on="game_id",
how="left")
print_errors()
if data_format.lower() == 'csv':
shared.to_csv(from_date + '--' + to_date, pbp_df, None, "nwhl")
else:
return pbp_df
def test_check_valid_dates():
""" Test if given valid date range"""
shared.check_valid_dates("2017-10-01", "2018-01-05")
with pytest.raises(ValueError):
shared.check_valid_dates("2017-12-01", "2017-11-30")
