TopDownHockey-Scraper 6.0.4__tar.gz → 6.0.7__tar.gz

{topdownhockey_scraper-6.0.4/src/TopDownHockey_Scraper.egg-info → topdownhockey_scraper-6.0.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: TopDownHockey_Scraper
-Version: 6.0.4
+Version: 6.0.7
 Summary: The TopDownHockey Scraper
 Home-page: https://github.com/TopDownHockey/TopDownHockey_Scraper
 Author: Patrick Bacon

{topdownhockey_scraper-6.0.4 → topdownhockey_scraper-6.0.7}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = TopDownHockey_Scraper
-version = 6.0.4
+version = 6.0.7
 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-6.0.4 → topdownhockey_scraper-6.0.7}/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="6.0.4",
+    version="6.0.7",
     author="Patrick Bacon",
     author_email="patrick.s.bacon@gmail.com",
     description="The TopDownHockey Scraper",

{topdownhockey_scraper-6.0.4 → topdownhockey_scraper-6.0.7}/src/TopDownHockey_Scraper/TopDownHockey_NHL_Scraper.py

@@ -18,6 +18,7 @@ import xml.etree.ElementTree as ET
 import xmltodict
 from xml.parsers.expat import ExpatError
 from requests.exceptions import ChunkedEncodingError
+import traceback
 
 print('Successfully did local install plus update')
 
@@ -834,8 +835,6 @@ def scrape_html_shifts(season, game_id, live = True):
         
     home_shifts = alldf
 
-    home_shifts.to_csv('/Users/patrickbacon/compact_topdownhockey/home_shifts.csv', index = False)
-
     if live == True:
 
         home_shifts = home_shifts.assign(shift_number = home_shifts.shift_number.astype(int))
@@ -956,8 +955,6 @@ def scrape_html_shifts(season, game_id, live = True):
         
     away_shifts = alldf
 
-    away_shifts.to_csv('/Users/patrickbacon/compact_topdownhockey/away_shifts.csv', index = False)
-
     if live == True:
 
         away_shifts = away_shifts.assign(shift_number = away_shifts.shift_number.astype(int))
@@ -1064,7 +1061,7 @@ def scrape_html_shifts(season, game_id, live = True):
             
             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 = pd.read_html(str(goalie_table))[0][8:9]
 
             # Temporary to test. Will fix later.
             
@@ -1108,8 +1105,6 @@ def scrape_html_shifts(season, game_id, live = True):
     global all_shifts
     
     all_shifts = pd.concat([home_shifts, away_shifts])
-
-    #all_shifts.to_csv('/Users/patrickbacon/compact_topdownhockey/all_shifts.csv', index = False)
     
     all_shifts = all_shifts.assign(start_time = all_shifts.shift_start.str.split('/').str[0])
     
@@ -1359,7 +1354,6 @@ def scrape_html_shifts(season, game_id, live = True):
     global changes_on
     global changes_off
     myshifts = all_shifts
-    #myshifts.to_csv('/Users/patrickbacon/compact_topdownhockey/tmp.csv', index = False)
     #print('Printing my shifts')
 
     #print(myshifts)
@@ -2080,8 +2074,6 @@ def merge_and_prepare(events, shifts):
                                           np.where(merged.event.isin(['PGSTR', 'PGEND', 'PSTR', 'PEND', 'ANTHEM']), -1, 1))).sort_values(
         by = ['game_seconds', 'period', 'event_index'])
 
-    merged.to_csv('/Users/patrickbacon/compact_topdownhockey/first_merged.csv', index = False)
-
     merged = merged.assign(change_before_event = np.where(
         (
             (merged.away_on_ice!='') & (merged.event.shift()=='CHANGE') & (merged.away_on_ice!=merged.away_on_ice.shift()) | 
@@ -2465,13 +2457,15 @@ def full_scrape_1by1(game_id_list, live = False, shift_to_espn = True):
             # If all goes well with the HTML scrape:
             
             try:
-                event_coords = scrape_api_events(game_id, shift_to_espn = shift_to_espn)
+                event_coords = scrape_api_events(game_id, shift_to_espn = True)
                 api_coords = event_coords
                 api_coords['coordinate_source'] = 'api'
                 if len(event_coords[(event_coords.event.isin(ewc)) & (pd.isna(event_coords.coords_x))]) > 0:
                     raise ExpatError('Bad takes, dude!')
                 event_coords['game_id'] = int(game_id)
+                print('Attempting to merge events again')
                 events = single.merge(event_coords, on = ['event_player_1', 'game_seconds', 'version', 'period', 'game_id', 'event'], how = 'left')
+                print('Merged events again, we have this many rows:', len(events))
                 try:
                     events = fix_missing(single, event_coords, events)
                 except IndexError as e:
@@ -2528,10 +2522,13 @@ def full_scrape_1by1(game_id_list, live = False, shift_to_espn = True):
                         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)
+                        print('Here is the ESPN ID:', espn_id)
                         event_coords = scrape_espn_events(int(espn_id))
+                        print('Scraped ESPN Events, we have this many rows:', len(event_coords))
                         event_coords['coordinate_source'] = 'espn'
+                        print('Attempting to merge events')
                         events = single.merge(event_coords, on = ['event_player_1', 'game_seconds', 'period', 'version', 'event'], how = 'left').drop(columns = ['espn_id'])
+                        print('Merged events, we have this many rows:', len(events))
                         try:
                             events = fix_missing(single, event_coords, events)
                         except IndexError as e:
@@ -2690,6 +2687,7 @@ def full_scrape_1by1(game_id_list, live = False, shift_to_espn = True):
             
         except AttributeError as e:
             print(str(game_id) + ' does not have an HTML report. Here is the error: ' + str(e))
+            print(traceback.format_exc())
             i = i + 1
             continue
             
@@ -2796,6 +2794,7 @@ def full_scrape(game_id_list, live = True, shift = False):
     hidden_patrick = 0
     
     df = full_scrape_1by1(game_id_list, live, shift_to_espn = shift)
+    print('Full scrape complete, we have this many rows:', len(df))
 
     # Fixing the Pettersson issue for event player. Just going downstream for this.
     try:
@@ -2830,7 +2829,6 @@ def full_scrape(game_id_list, live = True, shift = False):
         )
     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-6.0.4 → topdownhockey_scraper-6.0.7/src/TopDownHockey_Scraper.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: TopDownHockey_Scraper
-Version: 6.0.4
+Version: 6.0.7
 Summary: The TopDownHockey Scraper
 Home-page: https://github.com/TopDownHockey/TopDownHockey_Scraper
 Author: Patrick Bacon