fix scrapping for play by play and added deprecated team names (#242)

Author: krlu

basketball_reference_web_scraper/data.py

@@ -44,12 +44,15 @@ class Team(Enum):
     WASHINGTON_WIZARDS = "WASHINGTON WIZARDS"
 
     # DEPRECATED TEAMS
+    KANSAS_CITY_KINGS = "KANSAS CITY KINGS"
     CHARLOTTE_BOBCATS = "CHARLOTTE BOBCATS"
     NEW_JERSEY_NETS = "NEW JERSEY NETS"
     NEW_ORLEANS_HORNETS = "NEW ORLEANS HORNETS"
     NEW_ORLEANS_OKLAHOMA_CITY_HORNETS = "NEW ORLEANS/OKLAHOMA CITY HORNETS"
     SEATTLE_SUPERSONICS = "SEATTLE SUPERSONICS"
+    ST_LOUIS_HAWKS = "ST. LOUIS HAWKS"
     VANCOUVER_GRIZZLIES = "VANCOUVER GRIZZLIES"
+    WASHINGTON_BULLETS = "WASHINGTON BULLETS"
 
 
 class OutputType(Enum):
@@ -144,13 +147,16 @@ class Division(Enum):
     'WAS': Team.WASHINGTON_WIZARDS,
 
     # DEPRECATED TEAMS
+    'KCK': Team.KANSAS_CITY_KINGS,
     'NJN': Team.NEW_JERSEY_NETS,
     'NOH': Team.NEW_ORLEANS_HORNETS,
     'NOK': Team.NEW_ORLEANS_OKLAHOMA_CITY_HORNETS,
     'CHA': Team.CHARLOTTE_BOBCATS,
     'CHH': Team.CHARLOTTE_HORNETS,
     'SEA': Team.SEATTLE_SUPERSONICS,
+    'STL': Team.ST_LOUIS_HAWKS,
     'VAN': Team.VANCOUVER_GRIZZLIES,
+    "WSB": Team.WASHINGTON_BULLETS,
 }
 
 TEAM_TO_TEAM_ABBREVIATION = {v: k for k, v in TEAM_ABBREVIATIONS_TO_TEAM.items()}
@@ -190,11 +196,14 @@ class Division(Enum):
 
     # DEPRECATED TEAMS
     "CHARLOTTE BOBCATS": Team.CHARLOTTE_BOBCATS,
+    "KANSAS CITY KINGS": Team.KANSAS_CITY_KINGS,
     "NEW JERSEY NETS": Team.NEW_JERSEY_NETS,
     "NEW ORLEANS HORNETS": Team.NEW_ORLEANS_HORNETS,
     "NEW ORLEANS/OKLAHOMA CITY HORNETS": Team.NEW_ORLEANS_OKLAHOMA_CITY_HORNETS,
     "SEATTLE SUPERSONICS": Team.SEATTLE_SUPERSONICS,
+    "ST. LOUIS HAWKS": Team.ST_LOUIS_HAWKS,
     "VANCOUVER GRIZZLIES": Team.VANCOUVER_GRIZZLIES,
+    "WASHINGTON BULLETS": Team.WASHINGTON_BULLETS,
 }
 
 POSITION_ABBREVIATIONS_TO_POSITION = {

basketball_reference_web_scraper/html.py

@@ -669,6 +669,7 @@ def playoff_box_scores_table_container_query(self):
     Thus, the comment containing the playoff table is identified and parsed and then fed into lxml to create the element
     tree that will eventually be rendered on the page.
     """
+
     @property
     def playoff_box_scores_table(self):
         matching_containers = self.html.xpath(self.playoff_box_scores_table_container_query)
@@ -770,8 +771,8 @@ def team_names_query(self):
         return \
             '//*[@id="content"]' \
             '//div[@class="scorebox"]' \
-            '//div[@itemprop="performer"]' \
-            '//a[@itemprop="name"]'
+            '//strong' \
+            '//a'
 
     @property
     def play_by_play_table(self):
@@ -1065,17 +1066,17 @@ def league_abbreviation_query(self):
     @property
     def league_abbreviations(self):
         abbreviations = self.html.xpath(self.league_abbreviation_query)
-        
+
         if len(abbreviations) > 0:
             return abbreviations[0].text_content()
 
         return None
-    
+
 
 class PlayerPageTotalsRow:
     def __init__(self, html):
         self.html = html
-    
+
     @property
     def league_abbreviation(self):
         league_abbreviation_cells = self.html.xpath('.//td[@data-stat="lg_id"]')
@@ -1111,7 +1112,7 @@ def __eq__(self, other):
 class PlayerPage:
     def __init__(self, html):
         self.html = html
-    
+
     @property
     def name(self):
         name_headers = self.html.xpath('.//h1[@itemprop="name"]')