TopDownHockey-Scraper 4.3__tar.gz → 5.0.0__tar.gz

{topdownhockey_scraper-4.3/src/TopDownHockey_Scraper.egg-info → topdownhockey_scraper-5.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: TopDownHockey_Scraper
-Version: 4.3
+Version: 5.0.0
 Summary: The TopDownHockey Scraper
 Home-page: https://github.com/TopDownHockey/TopDownHockey_Scraper
 Author: Patrick Bacon

{topdownhockey_scraper-4.3 → topdownhockey_scraper-5.0.0}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = TopDownHockey_Scraper
-version = 4.3
+version = 5.0.0
 author = Patrick Bacon
 author_email = patrick.s.bacon@gmail.com
 description = A package built for scraping hockey data from EliteProspects, the NHL's HTML/API reports, and ESPN's XML reports.

{topdownhockey_scraper-4.3 → topdownhockey_scraper-5.0.0}/setup.py

@@ -9,7 +9,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
 
 setup(
     name="TopDownHockey_Scraper", # Replace with your own username
-    version="4.3",
+    version="5.0.0",
     author="Patrick Bacon",
     author_email="patrick.s.bacon@gmail.com",
     description="The TopDownHockey Scraper",

{topdownhockey_scraper-4.3 → topdownhockey_scraper-5.0.0}/src/TopDownHockey_Scraper/TopDownHockey_NHL_Scraper.py

@@ -508,6 +508,8 @@ def scrape_html_roster(season, game_id):
 
     roster_df['Name'] = roster_df['Name'].str.normalize('NFKD').str.encode('ascii', errors='ignore').str.decode('utf-8').str.upper()
 
+    roster_df['Name'] = np.where(roster_df['Name']== "JURAJ SLAFKOVSKA" , "JURAJ SLAFKOVSKY", roster_df['Name']) # Need to do this after normalization, only then he becomes Slafkovska?
+
     return roster_df 
 
 def scrape_html_shifts(season, game_id):
@@ -1229,6 +1231,8 @@ def scrape_html_shifts(season, game_id):
     all_shifts['name']))))))))))))))))))))))))))))))))))
 
     all_shifts['name'] = all_shifts['name'].str.normalize('NFKD').str.encode('ascii', errors='ignore').str.decode('utf-8').str.upper()
+
+    all_shifts['name'] = np.where(all_shifts['name']== "JURAJ SLAFKOVSKA" , "JURAJ SLAFKOVSKY", all_shifts['name']) # Need to do this after normalization, only then he becomes Slafkovska?
     
     
     all_shifts = all_shifts.assign(end_time = np.where(pd.to_datetime(all_shifts.start_time).dt.time > pd.to_datetime(all_shifts.end_time).dt.time, '20:00', all_shifts.end_time),
@@ -1555,6 +1559,8 @@ def scrape_api_events(game_id, drop_description = True, shift_to_espn = False):
 
         api_events['ep1_name'] = api_events['ep1_name'].str.normalize('NFKD').str.encode('ascii', errors='ignore').str.decode('utf-8').str.upper()
 
+        api_events['ep1_name'] = np.where(api_events['ep1_name'] == "JURAJ SLAFKOVSKA" , "JURAJ SLAFKOVSKY", api_events['ep1_name']) # Need to do this after normalization, only then he becomes Slafkovska?
+
         api_events = api_events.assign(ep1_name = np.where(api_events.ep1_name=='ALEX BARRÉ-BOULET', 'ALEX BARRE_BOULET', api_events.ep1_name))
 
         if drop_description == True:
@@ -1967,6 +1973,8 @@ def scrape_espn_events(espn_game_id, drop_description = True):
     espn_events['event_player_1'] = espn_events['event_player_1'].str.strip()
     
     espn_events['event_player_1'] = espn_events['event_player_1'].str.normalize('NFKD').str.encode('ascii', errors='ignore').str.decode('utf-8').str.upper()
+
+    espn_events['event_player_1'] = np.where(espn_events['event_player_1'] == "JURAJ SLAFKOVSKA" , "JURAJ SLAFKOVSKY", espn_events['event_player_1']) 
     
     #espn_events = espn_events.assign(event_player_1 = np.where(
     #espn_events.event_player_1=='ALEX BURROWS', 'ALEXANDRE BURROWS', espn_events.event_player_1))
@@ -2003,15 +2011,17 @@ def scrape_espn_ids_single_game(game_date, home_team, away_team):
     soup_found = soup.find_all('a', {'class':['AnchorLink truncate', 
                              'AnchorLink Button Button--sm Button--anchorLink Button--alt mb4 w-100',
                             'AnchorLink Button Button--sm Button--anchorLink Button--alt mb4 w-100 mr2'], 'href':[re.compile("/nhl/team/_/name/"), re.compile("game/_")]})
+    game_sections = soup.find_all('section', class_ = 'Scoreboard bg-clr-white flex flex-auto justify-between')
+
     at = []
     ht = []
     gids = []
     fax = pd.DataFrame()
     #print(str(i))
-    for i in range (0, ((len(soup_found)))):
-        away = soup_found[i]['href'].rsplit('/')[-1].split('-')[0].upper()
-        home = soup_found[i]['href'].rsplit('/')[-1].split('-')[-1].upper()
-        espnid = soup_found[i]['href'].rsplit('/')[-2]
+    for i in range(0, len(game_sections)):
+        away = game_sections[i].find_all('div', class_='ScoreCell__TeamName ScoreCell__TeamName--shortDisplayName db')[0].contents[0].upper()
+        home = game_sections[i].find_all('div', class_='ScoreCell__TeamName ScoreCell__TeamName--shortDisplayName db')[1].contents[0].upper()
+        espnid = game_sections[0]['id']
         at.append(away)
         ht.append(home)
         gids.append(espnid)

{topdownhockey_scraper-4.3 → topdownhockey_scraper-5.0.0/src/TopDownHockey_Scraper.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: TopDownHockey_Scraper
-Version: 4.3
+Version: 5.0.0
 Summary: The TopDownHockey Scraper
 Home-page: https://github.com/TopDownHockey/TopDownHockey_Scraper
 Author: Patrick Bacon