Merge pull request #22 from dcstats/1.0.5

1.0.5
dcstats · Sep 30, 2022 · a019155 · a019155
2 parents 73a511d + 02a545b
commit a019155
Show file tree

Hide file tree

Showing 2 changed files with 30 additions and 20 deletions.
diff --git a/pyproject.toml b/pyproject.toml
@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "CBBpy"
-version = "1.0.4"
+version = "1.0.5"
 description = 'A Python-based web scraper for NCAA basketball.'
 readme = "README.md"
 authors = [{ name = "Daniel Cowan", email = "dnlcowan37@gmail.com" }]

diff --git a/src/cbbpy/mens_scraper.py b/src/cbbpy/mens_scraper.py
@@ -244,6 +244,10 @@ def get_game_pbp(game_id: str) -> pd.DataFrame:
             # GET PBP DATA
             div = soup.find("div", {"id": "gamepackage-play-by-play"})
             tables = div.find_all("table")
+
+            if '0th Half' in div.get_text():
+                tables = tables[1:]
+
             num_halves = len(tables)
             pbp_halves = []
 
@@ -392,27 +396,32 @@ def get_game_info(game_id: str) -> pd.DataFrame:
             except:
                 game_network = np.nan
 
-            game_arena_pre = game_info_div.find(
-                'div', {'class': 'caption-wrapper'})
-
-            if not game_arena_pre:
-                div_loc = game_info_div.find(
-                    'div', {'class': 'location-details'})
-                game_arena = div_loc.find('span', {'class': 'game-location'})
-
-                if game_arena:
-                    game_arena = game_arena.get_text().strip()
-                    game_loc = div_loc.find(
-                        'div', {'class': 'game-location'}).get_text().strip()
-
+            try:
+                game_arena_pre = game_info_div.find(
+                    'div', {'class': 'caption-wrapper'})
+
+                if not game_arena_pre:
+                    div_loc = game_info_div.find(
+                        'div', {'class': 'location-details'})
+                    game_arena = div_loc.find(
+                        'span', {'class': 'game-location'})
+
+                    if game_arena:
+                        game_arena = game_arena.get_text().strip()
+                        game_loc = div_loc.find(
+                            'div', {'class': 'game-location'}).get_text().strip()
+
+                    else:
+                        game_arena = game_info_div.find(
+                            'div', {'class': 'game-location'}).get_text().strip()
+                        game_loc = None
                 else:
-                    game_arena = game_info_div.find(
+                    game_arena = game_arena_pre.get_text().strip()
+                    game_loc = game_info_div.find(
                         'div', {'class': 'game-location'}).get_text().strip()
-                    game_loc = None
-            else:
-                game_arena = game_arena_pre.get_text().strip()
-                game_loc = game_info_div.find(
-                    'div', {'class': 'game-location'}).get_text().strip()
+            except:
+                game_arena = None
+                game_loc = None
 
             game_cap_pre = game_info_div.find_all(
                 "div", {"class": "game-info-note capacity"})
@@ -910,6 +919,7 @@ def _clean_pbp_table(table, info):
     df = df.dropna(axis=1, how="all")
     df.columns = [x.lower() for x in df.columns]
     df = df.loc[:, ~df.columns.str.contains('unnamed')]
+    df = df.rename(columns={'time_of_day': 'time'})
 
     # type handling
     df.time = df.time.astype(str)