def test_second_request_is_from_cache(self):
url = "https://afltables.com/afl/stats/playersA_idx.html"
resp1 = requests.get(url)
assert hasattr(resp1, "from_cache")
assert not resp1.from_cache
resp2 = requests.get(url)
assert hasattr(resp2, "from_cache")
assert resp2.from_cache
def test_all_requests_with_force_live_are_not_from_cache(self):
url = "https://afltables.com/afl/stats/playersA_idx.html"
resp1 = requests.get(url, force_live=True)
assert not hasattr(resp1, "from_cache")
resp2 = requests.get(url, force_live=True)
assert not hasattr(resp2, "from_cache")
resp3 = requests.get(url, force_live=True)
assert not hasattr(resp3, "from_cache")
def get_player_stats(self):
"""
Returns player stats as per the player stats page defined in `self._get_player_url()`
Returns
----------
stats : obj
player stats Python object
"""
resp = requests.get(self.url)
self._stat_html = resp.text
soup = BeautifulSoup(self._stat_html, "html.parser")
all_dfs = pd.read_html(self._stat_html)
season_dfs = pd.read_html(self._stat_html,
match=r"[A-Za-z]* - [0-9]{4}")
season_stats_total = all_dfs[0] # The first table on the page
season_stats_average = all_dfs[1] # The second table on the page
ret = PlayerStats(
season_stats_total=season_stats_total,
season_stats_average=season_stats_average,
season_results=season_dfs,
)
return ret
def _get_player_url(self):
last_initial = self.name.split(" ")[1][0]
player_list_url = (config.AFLTABLES_STATS_BASE_URL +
f"stats/players{last_initial}_idx.html")
resp = requests.get(player_list_url)
soup = BeautifulSoup(resp.text, "html.parser")
url_list = soup.findAll(
"a",
href=re.compile(
f"players/{self.name[0]}/{self.name.replace(' ', '_')}"),
)
# If no matches found, raise LookupError
if len(url_list) == 0:
raise LookupError(
f"Found no players with name {self.name}. Browse https://afltables.com/afl/stats/playersA_idx.html for a list of all players. Name must be in format '[first] [last]'."
)
# If more than one name is matched, print warning message and return first.
if len(url_list) > 1:
print(
f"Warning: {len(url_list)} players have been found for name: {self.name}. Returning only the first"
)
return url_list[0].attrs.get("href")
def _get_games(self):
"""
Returns a Pandas dataframe listing every match contained in `self.all_time_games_url`
Returns
----------
games : Pandas dataframe
dataframe listing all games played by the team. Contains results and match metadata.
"""
resp = requests.get(self.all_time_games_url)
soup = BeautifulSoup(resp.text, "html.parser")
seasons = soup.findAll("table")
dfs = []
for season_html in seasons:
df = pd.read_html(str(season_html))[0]
df.columns = df.columns.droplevel(1)
df = df.iloc[0:-2, :]
dfs.append(df)
games = pd.concat(dfs)
games.index = pd.to_datetime(games.Date)
games = games.sort_index()
games = games.rename(columns={
"A": "Against",
"F": "For",
"R": "Result",
"M": "Margin"
})
return games
def season_stats(self, year: int):
"""
Returns a Pandas dataframe detailing the season stats for the specified year.
E.g. for Adelaide the table found at https://afltables.com/afl/stats/2020.html#1
Parameters
----------
year : int (required)
year as a four-digit integer (e.g. 2019)
Returns
----------
season_stats : Pandas dataframe
dataframe summarising individual player (and team total) stats for the specified year.
"""
season_player_stats_url = f"https://afltables.com/afl/stats/{year}.html"
resp = requests.get(season_player_stats_url)
if resp.status_code == 404:
raise Exception(f"Could not find season stats for year: {year}")
soup = BeautifulSoup(resp.text, "html.parser")
team_tables = soup.findAll("table")
for table in team_tables:
if table.find("th"):
if self.name in table.find("th").text:
df = pd.read_html(str(table))
if df is None:
raise LookupError(
f"Could not find season stats table for team {self.name} in year {year} at URL https://afltables.com/afl/stats/{year}.html"
)
season_stats = df[0]
season_stats.columns = season_stats.columns.droplevel()
return season_stats
def _get_players(self):
"""
Returns a list of pyAFL.Player objects for all players contained in `self.all_time_players_url`
Returns
----------
players : list
list of pyAFL.Player objects
"""
resp = requests.get(self.all_time_players_url)
soup = BeautifulSoup(resp.text, "html.parser")
player_table = soup.find("table")
player_table_body = player_table.find("tbody")
player_anchor_tags = player_table_body.findAll("a")
players = [
Player(player.text, url=player.attrs.get("href"))
for player in player_anchor_tags
]
return players
def test_invalid_url_throws_exception(self):
with pytest.raises(AttributeError):
resp = requests.get("https://abcdefgh")
def test_missing_url_schema_throws_exception(self):
with pytest.raises(AttributeError):
resp = requests.get("abcdefgh")
def test_none_url_throws_exception(self):
with pytest.raises(TypeError):
resp = requests.get()