TopDownHockey-Scraper 4.1.2__py3-none-any.whl → 4.1.4__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of TopDownHockey-Scraper might be problematic. Click here for more details.
- TopDownHockey_Scraper/TopDownHockey_NHL_Scraper.py +77 -6
- {TopDownHockey_Scraper-4.1.2.dist-info → topdownhockey_scraper-4.1.4.dist-info}/METADATA +1 -1
- topdownhockey_scraper-4.1.4.dist-info/RECORD +7 -0
- {TopDownHockey_Scraper-4.1.2.dist-info → topdownhockey_scraper-4.1.4.dist-info}/WHEEL +1 -1
- TopDownHockey_Scraper-4.1.2.dist-info/RECORD +0 -7
- {TopDownHockey_Scraper-4.1.2.dist-info → topdownhockey_scraper-4.1.4.dist-info}/LICENSE +0 -0
- {TopDownHockey_Scraper-4.1.2.dist-info → topdownhockey_scraper-4.1.4.dist-info}/top_level.txt +0 -0
|
@@ -477,7 +477,7 @@ def scrape_html_roster(season, game_id):
|
|
|
477
477
|
)))))))))))))))))))))))))))))))))))
|
|
478
478
|
|
|
479
479
|
roster_df['Name'] = np.where((roster_df['Name']=="SEBASTIAN AHO") & (roster_df['Pos']=='D'), 'SEBASTIAN AHO SWE', roster_df['Name'])
|
|
480
|
-
roster_df['Name'] = np.where((roster_df['Name']=="ELIAS PETTERSSON") & (roster_df['Pos']=='D'), 'ELIAS PETTERSSON
|
|
480
|
+
roster_df['Name'] = np.where((roster_df['Name']=="ELIAS PETTERSSON") & (roster_df['Pos']=='D'), 'ELIAS PETTERSSON(D)', roster_df['Name'])
|
|
481
481
|
roster_df['Name'] = np.where((roster_df['Name']=="COLIN WHITE") & (roster_df['Pos']=='D'), 'COLIN WHITE CAN', roster_df['Name'])
|
|
482
482
|
roster_df['Name'] = np.where((roster_df['Name']=="SEAN COLLINS") & (roster_df['Pos']=='D'), 'SEAN COLLINS CAN', roster_df['Name'])
|
|
483
483
|
roster_df['Name'] = np.where((roster_df['Name']=="ALEX PICARD") & (roster_df['Pos']!='D'), 'ALEX PICARD F', roster_df['Name'])
|
|
@@ -490,7 +490,19 @@ def scrape_html_roster(season, game_id):
|
|
|
490
490
|
(np.where(roster_df['Name']== "NICHOLAS PAUL" , "NICK PAUL",
|
|
491
491
|
(np.where(roster_df['Name']== "JACOB MIDDLETON" , "JAKE MIDDLETON",
|
|
492
492
|
(np.where(roster_df['Name']== "TOMMY NOVAK" , "THOMAS NOVAK",
|
|
493
|
-
|
|
493
|
+
# New guys from 24-25
|
|
494
|
+
(np.where(roster_df['Name']== "JOSHUA NORRIS" , "JOSH NORRIS",
|
|
495
|
+
(np.where(roster_df['Name']== "P.O JOSEPH" , "'PIERRE-OLIVIER JOSEPH",
|
|
496
|
+
(np.where(roster_df['Name']== "MIKEY EYSSIMONT" , "MICHAEL EYSSIMONT",
|
|
497
|
+
(np.where(roster_df['Name']== "MATAJ BLAMEL" , "MATAJ BLAMEL",
|
|
498
|
+
(np.where(roster_df['Name']== "VITTORIO MANCINI" , "VICTOR MANCINI",
|
|
499
|
+
(np.where(roster_df['Name']== "JOSHUA MAHURA" , "JOSH MAHURA",
|
|
500
|
+
(np.where(roster_df['Name']== "JOSEPH VELENO" , "JOE VELENO",
|
|
501
|
+
(np.where(roster_df['Name']== "ZACK BOLDUC" , "ZACHARY BOLDUC",
|
|
502
|
+
(np.where(roster_df['Name']== "JOSHUA BROWN" , "JOSH BROWN",
|
|
503
|
+
(np.where(roster_df['Name']== "JAKE LUCCHINI" , "JACOB LUCCHINI",
|
|
504
|
+
(np.where(roster_df['Name']== "EMIL LILLEBERG" , "EMIL MARTINSEN LILLEBERG",
|
|
505
|
+
roster_df['Name']))))))))))))))))))))))))))))))
|
|
494
506
|
|
|
495
507
|
roster_df['Name'] = roster_df['Name'].str.normalize('NFKD').str.encode('ascii', errors='ignore').str.decode('utf-8').str.upper()
|
|
496
508
|
|
|
@@ -937,6 +949,8 @@ def scrape_html_shifts(season, game_id):
|
|
|
937
949
|
|
|
938
950
|
for i in range(len(found)):
|
|
939
951
|
line = found[i].get_text()
|
|
952
|
+
if line == '25 PETTERSSON, ELIAS':
|
|
953
|
+
line = '25 PETTERSSON(D), ELIAS'
|
|
940
954
|
if ', ' in line:
|
|
941
955
|
name = line.split(',')
|
|
942
956
|
number = name[0].split(' ')[0].strip()
|
|
@@ -974,6 +988,8 @@ def scrape_html_shifts(season, game_id):
|
|
|
974
988
|
|
|
975
989
|
for i in range(len(found)):
|
|
976
990
|
line = found[i].get_text()
|
|
991
|
+
if line == '25 PETTERSSON, ELIAS':
|
|
992
|
+
line = '25 PETTERSSON(D), ELIAS'
|
|
977
993
|
if ', ' in line:
|
|
978
994
|
name = line.split(',')
|
|
979
995
|
number = name[0].split(' ')[0].strip()
|
|
@@ -1186,6 +1202,24 @@ def scrape_html_shifts(season, game_id):
|
|
|
1186
1202
|
(np.where(all_shifts['name']== "JOSH DUNNE" , "JOSHUA DUNNE",all_shifts['name'])))))))))))))))))))))))))))))))))))))))))))
|
|
1187
1203
|
)))))))))))))))))))))))))))))))))))))
|
|
1188
1204
|
|
|
1205
|
+
all_shifts['name'] = (np.where(all_shifts['name']== "JANIS MOSER" , "J.J. MOSER",
|
|
1206
|
+
(np.where(all_shifts['name']== "NICHOLAS PAUL" , "NICK PAUL",
|
|
1207
|
+
(np.where(all_shifts['name']== "JACOB MIDDLETON" , "JAKE MIDDLETON",
|
|
1208
|
+
(np.where(all_shifts['name']== "TOMMY NOVAK" , "THOMAS NOVAK",
|
|
1209
|
+
# New guys from 24-25
|
|
1210
|
+
(np.where(all_shifts['name']== "JOSHUA NORRIS" , "JOSH NORRIS",
|
|
1211
|
+
(np.where(all_shifts['name']== "P.O JOSEPH" , "'PIERRE-OLIVIER JOSEPH",
|
|
1212
|
+
(np.where(all_shifts['name']== "MIKEY EYSSIMONT" , "MICHAEL EYSSIMONT",
|
|
1213
|
+
(np.where(all_shifts['name']== "MATAJ BLAMEL" , "MATAJ BLAMEL",
|
|
1214
|
+
(np.where(all_shifts['name']== "VITTORIO MANCINI" , "VICTOR MANCINI",
|
|
1215
|
+
(np.where(all_shifts['name']== "JOSHUA MAHURA" , "JOSH MAHURA",
|
|
1216
|
+
(np.where(all_shifts['name']== "JOSEPH VELENO" , "JOE VELENO",
|
|
1217
|
+
(np.where(all_shifts['name']== "ZACK BOLDUC" , "ZACHARY BOLDUC",
|
|
1218
|
+
(np.where(all_shifts['name']== "JOSHUA BROWN" , "JOSH BROWN",
|
|
1219
|
+
(np.where(all_shifts['name']== "JAKE LUCCHINI" , "JACOB LUCCHINI",
|
|
1220
|
+
(np.where(all_shifts['name']== "EMIL LILLEBERG" , "EMIL MARTINSEN LILLEBERG",
|
|
1221
|
+
all_shifts['name']))))))))))))))))))))))))))))))
|
|
1222
|
+
|
|
1189
1223
|
all_shifts['name'] = all_shifts['name'].str.normalize('NFKD').str.encode('ascii', errors='ignore').str.decode('utf-8').str.upper()
|
|
1190
1224
|
|
|
1191
1225
|
|
|
@@ -1488,6 +1522,25 @@ def scrape_api_events(game_id, drop_description = True, shift_to_espn = False):
|
|
|
1488
1522
|
))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))
|
|
1489
1523
|
)))))))))))))))))))))))))))))))))))))))))))))))
|
|
1490
1524
|
|
|
1525
|
+
api_events['ep1_name'] = (np.where(api_events['ep1_name']== "JANIS MOSER" , "J.J. MOSER",
|
|
1526
|
+
(np.where(api_events['ep1_name']== "NICHOLAS PAUL" , "NICK PAUL",
|
|
1527
|
+
(np.where(api_events['ep1_name']== "JACOB MIDDLETON" , "JAKE MIDDLETON",
|
|
1528
|
+
(np.where(api_events['ep1_name']== "TOMMY NOVAK" , "THOMAS NOVAK",
|
|
1529
|
+
# New guys from 24-25
|
|
1530
|
+
(np.where(api_events['ep1_name']== "JOSHUA NORRIS" , "JOSH NORRIS",
|
|
1531
|
+
(np.where(api_events['ep1_name']== "P.O JOSEPH" , "'PIERRE-OLIVIER JOSEPH",
|
|
1532
|
+
(np.where(api_events['ep1_name']== "MIKEY EYSSIMONT" , "MICHAEL EYSSIMONT",
|
|
1533
|
+
(np.where(api_events['ep1_name']== "MATAJ BLAMEL" , "MATAJ BLAMEL",
|
|
1534
|
+
(np.where(api_events['ep1_name']== "VITTORIO MANCINI" , "VICTOR MANCINI",
|
|
1535
|
+
(np.where(api_events['ep1_name']== "JOSHUA MAHURA" , "JOSH MAHURA",
|
|
1536
|
+
(np.where(api_events['ep1_name']== "JOSEPH VELENO" , "JOE VELENO",
|
|
1537
|
+
(np.where(api_events['ep1_name']== "ZACK BOLDUC" , "ZACHARY BOLDUC",
|
|
1538
|
+
(np.where(api_events['ep1_name']== "JOSHUA BROWN" , "JOSH BROWN",
|
|
1539
|
+
(np.where(api_events['ep1_name']== "JAKE LUCCHINI" , "JACOB LUCCHINI",
|
|
1540
|
+
(np.where(api_events['ep1_name']== "EMIL LILLEBERG" , "EMIL MARTINSEN LILLEBERG",
|
|
1541
|
+
api_events['ep1_name']))))))))))))))))))))))))))))))
|
|
1542
|
+
|
|
1543
|
+
|
|
1491
1544
|
# 21-22 CHANGES
|
|
1492
1545
|
|
|
1493
1546
|
api_events['ep1_name'] = api_events['ep1_name'].str.normalize('NFKD').str.encode('ascii', errors='ignore').str.decode('utf-8').str.upper()
|
|
@@ -1848,11 +1901,29 @@ def scrape_espn_events(espn_game_id, drop_description = True):
|
|
|
1848
1901
|
(np.where(espn_events['event_player_1']== "TOMMY NOVAK" , "THOMAS NOVAK",
|
|
1849
1902
|
espn_events['event_player_1']))))))))
|
|
1850
1903
|
|
|
1851
|
-
espn_events['event_player_1'] = (np.where(espn_events['event_player_1']== "
|
|
1852
|
-
(np.where(espn_events['event_player_1']== "JOHHNY BEECHER" , "JOHN BEECHER",
|
|
1904
|
+
espn_events['event_player_1'] = (np.where(espn_events['event_player_1']== "JOHHNY BEECHER" , "JOHN BEECHER",
|
|
1853
1905
|
(np.where(espn_events['event_player_1']== "ALEXANDER BARKOV" , "ALEKSANDER BARKOV",
|
|
1854
1906
|
(np.where(espn_events['event_player_1']== "TOMMY NOVAK" , "THOMAS NOVAK",
|
|
1855
|
-
espn_events['event_player_1']))))))
|
|
1907
|
+
espn_events['event_player_1']))))))
|
|
1908
|
+
|
|
1909
|
+
espn_events['event_player_1'] = (np.where(espn_events['event_player_1']== "JANIS MOSER" , "J.J. MOSER",
|
|
1910
|
+
(np.where(espn_events['event_player_1']== "NICHOLAS PAUL" , "NICK PAUL",
|
|
1911
|
+
(np.where(espn_events['event_player_1']== "JACOB MIDDLETON" , "JAKE MIDDLETON",
|
|
1912
|
+
(np.where(espn_events['event_player_1']== "TOMMY NOVAK" , "THOMAS NOVAK",
|
|
1913
|
+
# New guys from 24-25
|
|
1914
|
+
(np.where(espn_events['event_player_1']== "JOSHUA NORRIS" , "JOSH NORRIS",
|
|
1915
|
+
(np.where(espn_events['event_player_1']== "P.O JOSEPH" , "'PIERRE-OLIVIER JOSEPH",
|
|
1916
|
+
(np.where(espn_events['event_player_1']== "MIKEY EYSSIMONT" , "MICHAEL EYSSIMONT",
|
|
1917
|
+
(np.where(espn_events['event_player_1']== "MATAJ BLAMEL" , "MATAJ BLAMEL",
|
|
1918
|
+
(np.where(espn_events['event_player_1']== "VITTORIO MANCINI" , "VICTOR MANCINI",
|
|
1919
|
+
(np.where(espn_events['event_player_1']== "JOSHUA MAHURA" , "JOSH MAHURA",
|
|
1920
|
+
(np.where(espn_events['event_player_1']== "JOSEPH VELENO" , "JOE VELENO",
|
|
1921
|
+
(np.where(espn_events['event_player_1']== "ZACK BOLDUC" , "ZACHARY BOLDUC",
|
|
1922
|
+
(np.where(espn_events['event_player_1']== "JOSHUA BROWN" , "JOSH BROWN",
|
|
1923
|
+
(np.where(espn_events['event_player_1']== "JAKE LUCCHINI" , "JACOB LUCCHINI",
|
|
1924
|
+
(np.where(espn_events['event_player_1']== "EMIL LILLEBERG" , "EMIL MARTINSEN LILLEBERG",
|
|
1925
|
+
espn_events['event_player_1']))))))))))))))))))))))))))))))
|
|
1926
|
+
|
|
1856
1927
|
|
|
1857
1928
|
espn_events = espn_events.assign(version =
|
|
1858
1929
|
(np.where(
|
|
@@ -2153,7 +2224,7 @@ def merge_and_prepare(events, shifts):
|
|
|
2153
2224
|
Name = roster.Name.str.split('(').str[0].str.strip())
|
|
2154
2225
|
|
|
2155
2226
|
roster = roster.assign(Name = np.where((roster.Name=='SEBASTIAN AHO') &( roster.team_name == 'NEW YORK ISLANDERS'), 'SEBASTIAN AHO (SWE)', roster.Name))
|
|
2156
|
-
roster = roster.assign(Name = np.where((roster.Name=='ELIAS PETTERSSON') &( roster.Pos == 'D'), 'ELIAS PETTERSSON
|
|
2227
|
+
roster = roster.assign(Name = np.where((roster.Name=='ELIAS PETTERSSON') &( roster.Pos == 'D'), 'ELIAS PETTERSSON(D)', roster.Name))
|
|
2157
2228
|
|
|
2158
2229
|
goalies = roster[(roster.Pos=='G') & (roster.status!='scratch')]
|
|
2159
2230
|
|
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
TopDownHockey_Scraper/TopDownHockey_EliteProspects_Scraper.py,sha256=j-7gTk-cp_0LyZihNxm67xH9KdA3Fx4xrFKKu3-9-rU,42245
|
|
2
|
+
TopDownHockey_Scraper/TopDownHockey_NHL_Scraper.py,sha256=LEzCPzH0qQj5TZz0pYjqTMtS4Qg4OqEIqz3ys5x0yTU,159298
|
|
3
|
+
topdownhockey_scraper-4.1.4.dist-info/LICENSE,sha256=2bm9uFabQZ3Ykb_SaSU_uUbAj2-htc6WJQmS_65qD00,1073
|
|
4
|
+
topdownhockey_scraper-4.1.4.dist-info/METADATA,sha256=5JFQux2AtN5ipoUa--xERKIFSdVsysZOtpiBsNO7z5I,5697
|
|
5
|
+
topdownhockey_scraper-4.1.4.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
|
|
6
|
+
topdownhockey_scraper-4.1.4.dist-info/top_level.txt,sha256=PBd96GLGFq97ZDLd7_4ZCx8_ZFr_wdWKs5SIpGl5xCs,22
|
|
7
|
+
topdownhockey_scraper-4.1.4.dist-info/RECORD,,
|
|
@@ -1,7 +0,0 @@
|
|
|
1
|
-
TopDownHockey_Scraper/TopDownHockey_EliteProspects_Scraper.py,sha256=j-7gTk-cp_0LyZihNxm67xH9KdA3Fx4xrFKKu3-9-rU,42245
|
|
2
|
-
TopDownHockey_Scraper/TopDownHockey_NHL_Scraper.py,sha256=W4DNU1fZdrQ9FlUczmGGq1dn7vAxeDK_HIn4bhZjo6w,154535
|
|
3
|
-
TopDownHockey_Scraper-4.1.2.dist-info/LICENSE,sha256=2bm9uFabQZ3Ykb_SaSU_uUbAj2-htc6WJQmS_65qD00,1073
|
|
4
|
-
TopDownHockey_Scraper-4.1.2.dist-info/METADATA,sha256=wV51DiDI7CXwA6TlYXTdd3TEGalJPeeNq2zhwMjoV4Q,5697
|
|
5
|
-
TopDownHockey_Scraper-4.1.2.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
|
|
6
|
-
TopDownHockey_Scraper-4.1.2.dist-info/top_level.txt,sha256=PBd96GLGFq97ZDLd7_4ZCx8_ZFr_wdWKs5SIpGl5xCs,22
|
|
7
|
-
TopDownHockey_Scraper-4.1.2.dist-info/RECORD,,
|
|
File without changes
|
{TopDownHockey_Scraper-4.1.2.dist-info → topdownhockey_scraper-4.1.4.dist-info}/top_level.txt
RENAMED
|
File without changes
|