TopDownHockey-Scraper 6.0.0__tar.gz → 6.0.2__tar.gz

{topdownhockey_scraper-6.0.0/src/TopDownHockey_Scraper.egg-info → topdownhockey_scraper-6.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: TopDownHockey_Scraper
-Version: 6.0.0
+Version: 6.0.2
 Summary: The TopDownHockey Scraper
 Home-page: https://github.com/TopDownHockey/TopDownHockey_Scraper
 Author: Patrick Bacon
@@ -17,8 +17,6 @@ Requires-Dist: numpy
 Requires-Dist: pandas
 Requires-Dist: bs4
 Requires-Dist: datetime
-Requires-Dist: seaborn
-Requires-Dist: matplotlib
 Requires-Dist: xmltodict
 Requires-Dist: lxml
 Requires-Dist: natsort

{topdownhockey_scraper-6.0.0 → topdownhockey_scraper-6.0.2}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = TopDownHockey_Scraper
-version = 5.0.2
+version = 6.0.2
 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.
@@ -25,8 +25,6 @@ install_requires =
 	pandas
 	datetime
 	requests
-	seasborn
-	matplotlib
 	xml
 	xmltodict
 	requests

{topdownhockey_scraper-6.0.0 → topdownhockey_scraper-6.0.2}/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="6.0.0",
+    version="6.0.2",
     author="Patrick Bacon",
     author_email="patrick.s.bacon@gmail.com",
     description="The TopDownHockey Scraper",
@@ -33,8 +33,6 @@ setup(
     'pandas',
     'bs4',
     'datetime',
-    'seaborn',
-    'matplotlib',
     'xmltodict',
     'lxml',
     'natsort'

{topdownhockey_scraper-6.0.0 → topdownhockey_scraper-6.0.2}/src/TopDownHockey_Scraper/TopDownHockey_NHL_Scraper.py

@@ -2255,6 +2255,7 @@ def scrape_espn_ids_single_game(game_date, home_team, away_team):
     this_date = (game_date)
     url = 'http://www.espn.com/nhl/scoreboard?date=' + this_date.replace("-", "")
     page = requests.get(url, headers={'User-Agent': 'Mozilla/5.0'}, timeout = 500)
+    print('Request to ESPN IDs successful.')
     soup = BeautifulSoup(page.content, parser = 'lxml')
     soup_found = soup.find_all('a', {'class':['AnchorLink truncate', 
                              'AnchorLink Button Button--sm Button--anchorLink Button--alt mb4 w-100',
@@ -2926,7 +2927,10 @@ def full_scrape_1by1(game_id_list, live = False, shift_to_espn = True):
                             espn_home_team = 'SJS'
                         if away_team == 'S.J':
                             espn_away_team = 'SJS'
+                        print('Scraping ESPN IDs')
                         espn_id = scrape_espn_ids_single_game(str(game_date.date()), espn_home_team, espn_away_team).espn_id.iloc[0]
+                        print('Scraping ESPN Events')
+                        print('Here is the ESPN ID': espn_id)
                         event_coords = scrape_espn_events(int(espn_id))
                         event_coords['coordinate_source'] = 'espn'
                         events = single.merge(event_coords, on = ['event_player_1', 'game_seconds', 'period', 'version', 'event'], how = 'left').drop(columns = ['espn_id'])
@@ -3196,35 +3200,39 @@ def full_scrape(game_id_list, live = True, shift = False):
     df = full_scrape_1by1(game_id_list, live, shift_to_espn = shift)
 
     # Fixing the Pettersson issue for event player. Just going downstream for this.
-    df = df.assign(
-        event_player_1 = np.where(
-            (df.event_player_1 == 'ELIAS PETTERSSON') & 
-            (df.event_description.str.contains('#', na=False)) &
-            (df.event_description.str.contains(' PETTERSSON', na=False)) &
-            (df.event_description.str.extract(r'#(\d+) PETTERSSON', expand=False) == '25'), 
-            'ELIAS PETTERSSON(D)', df.event_player_1),
-        event_player_2 = np.where(
-            (df.event_player_2 == 'ELIAS PETTERSSON') & 
-            (
-                # Goal and Petey got A1
-                ((df.event_type == 'GOAL') &
-                 (df.event_description.str.contains(': #', na=False)) &
-                 (df.event_description.str.contains(' PETTERSSON', na=False)) &
-                 (df.event_description.str.extract(r': #(\d+) PETTERSSON', expand=False) == '25')) |
-                # Not a goal, Petey was EP2
-                ((df.event_type != 'GOAL') & 
-                 (df.event_description.str.contains('VAN #', na=False)) &
-                 (df.event_description.str.contains(' PETTERSSON', na=False)) &
-                 (df.event_description.str.extract(r'VAN #(\d+) PETTERSSON', expand=False) == '25'))
-            ),
-            'ELIAS PETTERSSON(D)', df.event_player_2),
-        event_player_3 = np.where(
-            (df.event_player_3=='ELIAS PETTERSSON') & 
-            (df.event_description.str.contains('#', na=False)) &
-            (df.event_description.str.contains(' PETTERSSON', na=False)) &
-            (df.event_description.str.extract(r'#(\d+) PETTERSSON(?:\s|$)', expand=False) == '25'),
-            'ELIAS PETTERSSON(D)', df.event_player_3)
-    )
+    try:
+        df = df.assign(
+            event_player_1 = np.where(
+                (df.event_player_1 == 'ELIAS PETTERSSON') & 
+                (df.event_description.str.contains('#', na=False)) &
+                (df.event_description.str.contains(' PETTERSSON', na=False)) &
+                (df.event_description.str.extract(r'#(\d+) PETTERSSON', expand=False) == '25'), 
+                'ELIAS PETTERSSON(D)', df.event_player_1),
+            event_player_2 = np.where(
+                (df.event_player_2 == 'ELIAS PETTERSSON') & 
+                (
+                    # Goal and Petey got A1
+                    ((df.event_type == 'GOAL') &
+                    (df.event_description.str.contains(': #', na=False)) &
+                    (df.event_description.str.contains(' PETTERSSON', na=False)) &
+                    (df.event_description.str.extract(r': #(\d+) PETTERSSON', expand=False) == '25')) |
+                    # Not a goal, Petey was EP2
+                    ((df.event_type != 'GOAL') & 
+                    (df.event_description.str.contains('VAN #', na=False)) &
+                    (df.event_description.str.contains(' PETTERSSON', na=False)) &
+                    (df.event_description.str.extract(r'VAN #(\d+) PETTERSSON', expand=False) == '25'))
+                ),
+                'ELIAS PETTERSSON(D)', df.event_player_2),
+            event_player_3 = np.where(
+                (df.event_player_3=='ELIAS PETTERSSON') & 
+                (df.event_description.str.contains('#', na=False)) &
+                (df.event_description.str.contains(' PETTERSSON', na=False)) &
+                (df.event_description.str.extract(r'#(\d+) PETTERSSON(?:\s|$)', expand=False) == '25'),
+                'ELIAS PETTERSSON(D)', df.event_player_3)
+        )
+    except Exception as e:
+        print(e)
+        continue
 
     # Don't even need this, we've had this problem with Stutzle for years, just let it be. 
     # df.event_description = df.event_description.str.replace('FEHÃ\x89RVÃ\x81RY', 'FEHERVARY').str.replace('BLÜMEL', 'BLAMEL')

{topdownhockey_scraper-6.0.0 → topdownhockey_scraper-6.0.2/src/TopDownHockey_Scraper.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: TopDownHockey_Scraper
-Version: 6.0.0
+Version: 6.0.2
 Summary: The TopDownHockey Scraper
 Home-page: https://github.com/TopDownHockey/TopDownHockey_Scraper
 Author: Patrick Bacon
@@ -17,8 +17,6 @@ Requires-Dist: numpy
 Requires-Dist: pandas
 Requires-Dist: bs4
 Requires-Dist: datetime
-Requires-Dist: seaborn
-Requires-Dist: matplotlib
 Requires-Dist: xmltodict
 Requires-Dist: lxml
 Requires-Dist: natsort

{topdownhockey_scraper-6.0.0 → topdownhockey_scraper-6.0.2}/src/TopDownHockey_Scraper.egg-info/requires.txt

@@ -2,8 +2,6 @@ numpy
 pandas
 bs4
 datetime
-seaborn
-matplotlib
 xmltodict
 lxml
 natsort