TopDownHockey-Scraper 6.0.7__py3-none-any.whl → 6.0.10__py3-none-any.whl

TopDownHockey_Scraper/TopDownHockey_NHL_Scraper.py

@@ -1036,7 +1036,7 @@ def scrape_html_shifts(season, game_id, live = True):
         
         # Additional logic to handle period 1 scrape when we don't have goalie shifts yet. 
             
-        if len(home_shifts[(home_shifts.name.isin(goalie_names))]) == 0 or len(away_shifts[(away_shifts.name.isin(goalie_names))]):
+        if len(home_shifts[(home_shifts.name.isin(goalie_names))]) == 0 or len(away_shifts[(away_shifts.name.isin(goalie_names))]) == 0:
         
             pbp_html_url = f'https://www.nhl.com/scores/htmlreports/{season}/GS0{game_id}.HTM'
             pbp_soup = BeautifulSoup(requests.get(pbp_html_url).content)
@@ -1047,26 +1047,27 @@ def scrape_html_shifts(season, game_id, live = True):
 
             away_teams = pd.read_html(str(goalie_table))[0][:2]
             away_team = away_teams[0].iloc[0]
-            
-            away_goalies = pd.read_html(str(goalie_table))[0][2:4]
+
+            away_goalies = pd.read_html(str(goalie_table))[0][2:4][
+                ~pd.isna(pd.read_html(str(goalie_table))[0][2:4])[0]
+            ]
             away_goalies = away_goalies[~pd.isna(away_goalies[6])]
-            
+
             away_goalies = away_goalies.assign(team = away_team).rename(columns = {0:'number', 2:'name', 6:'TOI'}).loc[:, ['number', 'name', 'TOI', 'team']]
 
-            home_teams = pd.read_html(str(goalie_table))[0][6:7]
+            away_goalies = away_goalies[away_goalies.TOI!='TOT']
+
+            home_teams = pd.read_html(str(goalie_table))[0][6:8][
+                ~pd.isna(pd.read_html(str(goalie_table))[0][6:8])[0]
+            ]
             home_team = home_teams[0].iloc[0]
-            
+
             home_goalies = pd.read_html(str(goalie_table))[0][8:10]
             home_goalies = home_goalies[~pd.isna(home_goalies[6])]
-            
-            home_goalies = home_goalies.assign(team = home_team).rename(columns = {0:'number', 2:'name', 6:'TOI'}).loc[:, ['number', 'name', 'TOI', 'team']]
 
-            # home_goalies = pd.read_html(str(goalie_table))[0][8:9]
+            home_goalies = home_goalies.assign(team = home_team).rename(columns = {0:'number', 2:'name', 6:'TOI'}).loc[:, ['number', 'name', 'TOI', 'team']]
 
-            # Temporary to test. Will fix later.
-            
-            # home_goalies = home_goalies.assign(TOI = '11:26')
-            # away_goalies = away_goalies.assign(TOI = '11:26')
+            home_goalies = home_goalies[home_goalies.TOI!='TOT']
 
         if len(home_shifts[(home_shifts.name.isin(goalie_names))]) == 0:
 
@@ -1410,8 +1411,9 @@ def scrape_html_events(season, game_id):
     #global stripped_html
     #global eventdf
     stripped_html = hs_strip_html(tds)
-    length = int(len(stripped_html)/8)
-    eventdf = pd.DataFrame(np.array(stripped_html).reshape(length, 8)).rename(
+    length = (len(stripped_html) // 8) * 8
+    stripped_html = stripped_html[:length]
+    eventdf = pd.DataFrame(np.array(stripped_html).reshape(int(length/8), 8)).rename(
     columns = {0:'index', 1:'period', 2:'strength', 3:'time', 4:'event', 5:'description', 6:'away_skaters', 7:'home_skaters'})
     split = eventdf.time.str.split(':')
     game_date = soup.find_all('td', {'align':'center', 'style':'font-size: 10px;font-weight:bold'})[2].get_text()
@@ -2693,11 +2695,13 @@ def full_scrape_1by1(game_id_list, live = False, shift_to_espn = True):
             
         except IndexError as e:
             print(str(game_id) + ' has an issue with the HTML Report. Here is the error: ' + str(e))
+            print(traceback.format_exc())
             i = i + 1
             continue
             
         except ValueError as e:
             print(str(game_id) + ' has an issue with the HTML Report. Here is the error: ' + str(e))
+            print(traceback.format_exc())
             i = i + 1
             continue
 

{topdownhockey_scraper-6.0.7.dist-info → topdownhockey_scraper-6.0.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: TopDownHockey_Scraper
-Version: 6.0.7
+Version: 6.0.10
 Summary: The TopDownHockey Scraper
 Home-page: https://github.com/TopDownHockey/TopDownHockey_Scraper
 Author: Patrick Bacon

topdownhockey_scraper-6.0.10.dist-info/RECORD

@@ -0,0 +1,7 @@
+TopDownHockey_Scraper/TopDownHockey_EliteProspects_Scraper.py,sha256=j-7gTk-cp_0LyZihNxm67xH9KdA3Fx4xrFKKu3-9-rU,42245
+TopDownHockey_Scraper/TopDownHockey_NHL_Scraper.py,sha256=m6osH-VY491_4HUo5-A-JU41NHLPP9F48KJmwbfmvvI,163999
+topdownhockey_scraper-6.0.10.dist-info/licenses/LICENSE,sha256=2bm9uFabQZ3Ykb_SaSU_uUbAj2-htc6WJQmS_65qD00,1073
+topdownhockey_scraper-6.0.10.dist-info/METADATA,sha256=X1NaTOIWuTiRPjzHMqLv0Lw2uGLTSNuBWZfFUwRcyv8,5671
+topdownhockey_scraper-6.0.10.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+topdownhockey_scraper-6.0.10.dist-info/top_level.txt,sha256=PBd96GLGFq97ZDLd7_4ZCx8_ZFr_wdWKs5SIpGl5xCs,22
+topdownhockey_scraper-6.0.10.dist-info/RECORD,,

topdownhockey_scraper-6.0.7.dist-info/RECORD

@@ -1,7 +0,0 @@
-TopDownHockey_Scraper/TopDownHockey_EliteProspects_Scraper.py,sha256=j-7gTk-cp_0LyZihNxm67xH9KdA3Fx4xrFKKu3-9-rU,42245
-TopDownHockey_Scraper/TopDownHockey_NHL_Scraper.py,sha256=0YWnDOGFexyaUSjux-4pVp1NLOlnqk7CfCsQNQT6isI,163865
-topdownhockey_scraper-6.0.7.dist-info/licenses/LICENSE,sha256=2bm9uFabQZ3Ykb_SaSU_uUbAj2-htc6WJQmS_65qD00,1073
-topdownhockey_scraper-6.0.7.dist-info/METADATA,sha256=nEp4X2tq_dylw6TAIzzmxL5L052rWQ7fTGj60AaQD7o,5670
-topdownhockey_scraper-6.0.7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-topdownhockey_scraper-6.0.7.dist-info/top_level.txt,sha256=PBd96GLGFq97ZDLd7_4ZCx8_ZFr_wdWKs5SIpGl5xCs,22
-topdownhockey_scraper-6.0.7.dist-info/RECORD,,