def test_md56b4698269dd34a823cf6b233c6165614(self, finalcols):
# generate empty df with cols of length that the site would return in this instance
empty = pd.DataFrame(columns=[x for x in range(0, 17)])
assert all(x in list(
Rechash.RecHash().md56b4698269dd34a823cf6b233c6165614(empty))
for x in finalcols)
def test_md57f97f3885d50fcf9b92797810856a89f(self, finalcols):
# generate empty df with cols of length that the site would return in this instance
empty = pd.DataFrame(columns=[x for x in range(0, 21)])
assert all(x in list(
Rechash.RecHash().md57f97f3885d50fcf9b92797810856a89f(empty))
for x in finalcols)
def test_md5bfbf86ae0485a0a70692ae04124449b9(self, finalcols):
# generate empty df with cols of length that the site would return in this instance
empty = pd.DataFrame(columns=[x for x in range(0, 18)])
assert all(x in list(
Rechash.RecHash().md5bfbf86ae0485a0a70692ae04124449b9(empty))
for x in finalcols)
def finalcols():
return Rechash.RecHash().base[1:] + Rechash.RecHash().receiving + Rechash.RecHash().rushing + \
Rechash.RecHash().kick_rt + Rechash.RecHash().punt_rt + Rechash.RecHash().scoring2p + \
Rechash.RecHash().scoring
def test_md5111e8480632f73642d7e20acbdbe6b16(self, finalcols):
# generate empty df with cols of length that the site would return in this instance
empty = pd.DataFrame(columns=[x for x in range(0, 25)])
assert all(x in list(
Rechash.RecHash().md5111e8480632f73642d7e20acbdbe6b16(empty))
for x in finalcols)
def test_md5adc05c5af0f88775d3605d02c831c0ed(self, finalcols):
# generate empty df with cols of length that the site would return in this instance
empty = pd.DataFrame(columns=[x for x in range(0, 20)])
assert all(x in list(
Rechash.RecHash().md5adc05c5af0f88775d3605d02c831c0ed(empty))
for x in finalcols)
def test_md550fcceaa170b1a1e501e3f40548e403d(self, finalcols):
# generate empty df with cols of length that the site would return in this instance
empty = pd.DataFrame(columns=[x for x in range(0, 29)])
assert all(x in list(
Rechash.RecHash().md550fcceaa170b1a1e501e3f40548e403d(empty))
for x in finalcols)
def test_md552589e869a13d76c6d0dbf066cab536f(self, finalcols):
# generate empty df with cols of length that the site would return in this instance
empty = pd.DataFrame(columns=[x for x in range(0, 18)])
assert all(x in list(
Rechash.RecHash().md552589e869a13d76c6d0dbf066cab536f(empty))
for x in finalcols)
def test_md54c82a489ec5b2c943e78c9018dcbbca1(self, finalcols):
# generate empty df with cols of length that the site would return in this instance
empty = pd.DataFrame(columns=[x for x in range(0, 36)])
assert all(x in list(
Rechash.RecHash().md54c82a489ec5b2c943e78c9018dcbbca1(empty))
for x in finalcols)
def test_md5e8ffc7202223bb253e92da83b76e9944(self, finalcols):
# generate empty df with cols of length that the site would return in this instance
empty = pd.DataFrame(columns=[x for x in range(0, 39)])
assert all(x in list(
Rechash.RecHash().md5e8ffc7202223bb253e92da83b76e9944(empty))
for x in finalcols)
def test_md54560c290b45e942c16cc6d7811345fce(self, finalcols):
# generate empty df with cols of length that the site would return in this instance
empty = pd.DataFrame(columns=[x for x in range(0, 37)])
assert all(x in list(
Rechash.RecHash().md54560c290b45e942c16cc6d7811345fce(empty))
for x in finalcols)
def test_md5bcb96297b50fb2120f475e8e05fbabcd(self, finalcols):
# generate empty df with cols of length that the site would return in this instance
empty = pd.DataFrame(columns=[x for x in range(0, 41)])
assert all(x in list(
Rechash.RecHash().md5bcb96297b50fb2120f475e8e05fbabcd(empty))
for x in finalcols)
def test_md5b3c4237d9a10de8cfaad61852cb552c4(self, finalcols):
# generate empty df with cols of length that the site would return in this instance
empty = pd.DataFrame(columns=[x for x in range(0, 32)])
assert all(x in list(
Rechash.RecHash().md5b3c4237d9a10de8cfaad61852cb552c4(empty))
for x in finalcols)
def test_md5aa321161d6f3f5230259dbc4ae67299a(self, finalcols):
# generate empty df with cols of length that the site would return in this instance
empty = pd.DataFrame(columns=[x for x in range(0, 24)])
assert all(x in list(
Rechash.RecHash().md5aa321161d6f3f5230259dbc4ae67299a(empty))
for x in finalcols)
def test_md5e160e714b29305ecfecf513cbf84b80f(self, finalcols):
# generate empty df with cols of length that the site would return in this instance
empty = pd.DataFrame(columns=[x for x in range(0, 25)])
assert all(x in list(
Rechash.RecHash().md5e160e714b29305ecfecf513cbf84b80f(empty))
for x in finalcols)
def receiving(self, player_link, year, **kwargs):
# Set up the gamelog suffix
gamelog_suffix = '/gamelog/%s/' % year
# Modify the player url to point to the gamelog
log_url = player_link[:-4] + gamelog_suffix
# Get html
html = Loader.Loader().load_page(log_url).content.decode()
# ************** generate general stats, these need to be combined later ******************
gen = PlayerParser.PlayerParser().parse_general_info(html)
# parse tables w pandas
df = pd.read_html(html)[0]
# hash the columns to determine which fields are being used
which_cols = hashlib.md5(json.dumps(list(df.columns.levels[0])).encode()).hexdigest()
# Here we make a dict of hashes and their corresponding column parser, this is faster than if/else
options = { "b3c4237d9a10de8cfaad61852cb552c4": Rechash.RecHash().md5b3c4237d9a10de8cfaad61852cb552c4,
"bcb96297b50fb2120f475e8e05fbabcd": Rechash.RecHash().md5bcb96297b50fb2120f475e8e05fbabcd,
"4560c290b45e942c16cc6d7811345fce": Rechash.RecHash().md54560c290b45e942c16cc6d7811345fce,
"4c82a489ec5b2c943e78c9018dcbbca1": Rechash.RecHash().md54c82a489ec5b2c943e78c9018dcbbca1,
"e8ffc7202223bb253e92da83b76e9944": Rechash.RecHash().md5e8ffc7202223bb253e92da83b76e9944,
"50fcceaa170b1a1e501e3f40548e403d": Rechash.RecHash().md550fcceaa170b1a1e501e3f40548e403d,
"e160e714b29305ecfecf513cbf84b80f": Rechash.RecHash().md5e160e714b29305ecfecf513cbf84b80f,
"111e8480632f73642d7e20acbdbe6b16": Rechash.RecHash().md5111e8480632f73642d7e20acbdbe6b16,
"adc05c5af0f88775d3605d02c831c0ed": Rechash.RecHash().md5adc05c5af0f88775d3605d02c831c0ed,
"bfbf86ae0485a0a70692ae04124449b9": Rechash.RecHash().md5bfbf86ae0485a0a70692ae04124449b9,
"6b4698269dd34a823cf6b233c6165614": Rechash.RecHash().md56b4698269dd34a823cf6b233c6165614,
"7f97f3885d50fcf9b92797810856a89f": Rechash.RecHash().md57f97f3885d50fcf9b92797810856a89f,
"aa321161d6f3f5230259dbc4ae67299a": Rechash.RecHash().md5aa321161d6f3f5230259dbc4ae67299a,
"1193d47266d4acdcf1b6fca165121100": Rechash.RecHash().md51193d47266d4acdcf1b6fca165121100,
"52589e869a13d76c6d0dbf066cab536f": Rechash.RecHash().md552589e869a13d76c6d0dbf066cab536f,
"d522b9357244c20714a3b21f8f404918": Rechash.RecHash().md5d522b9357244c20714a3b21f8f404918}
df = options[which_cols](df)
# send df to the common parser
df = self.common(df, year)
# Add the name
df.loc[:, 'Name'] = gen['name']
# Add the players position
df.loc[:, 'Pos'] = gen['position']
df['Throws'] = gen['throws']
df['Height'] = gen['height']
df['Weight'] = gen['weight']
df['DOB_mo'] = gen['bday_mo']
df['DOB_day'] = gen['bday_day']
df['DOB_yr'] = gen['bday_yr']
df['College'] = gen['college']
df = df[['Name', 'Pos', 'Height', 'Weight', 'DOB_mo', 'DOB_day', 'DOB_yr', 'College'] +
Rechash.RecHash().base[1:] + ['PF', 'PA'] + Rechash.RecHash().receiving + Rechash.RecHash().rushing +
Rechash.RecHash().kick_rt + Rechash.RecHash().punt_rt + Rechash.RecHash().scoring2p +
Rechash.RecHash().scoring]
return df
def test_md51193d47266d4acdcf1b6fca165121100(self, finalcols):
# generate empty df with cols of length that the site would return in this instance
empty = pd.DataFrame(columns=[x for x in range(0, 43)])
assert all(x in list(
Rechash.RecHash().md51193d47266d4acdcf1b6fca165121100(empty))
for x in finalcols)