Parse out team names of practice reports to fix bug where only opponent report exists

src/queries/nfl_teams/practice_reports.py

@@ -1,8 +1,10 @@
+from bs4 import BeautifulSoup
 import datetime
 from multiprocessing import Pool
 import numpy as np
 import pandas as pd
 from pydantic import BaseModel, Field
+import requests
 from typing import Optional
 from urllib.parse import urljoin
 
@@ -72,11 +74,23 @@ class PracticeReportRawRow(BaseModel):
         return cls(**{DAY_OF_WEEK_STRING_MAPPING.get(k, k): cls.replace_nan(v) for k, v in input_dict.items()})
 
 
+def get_injury_report_dataframe(team: NFLTeam):
+    injury_report_url = urljoin(team.injury_report_url, f"week/REG-{CURRENT_WEEK}")
+    report_request = requests.get(injury_report_url)
+    report_soup = BeautifulSoup(report_request.content)
+    team_names_spans = report_soup.find_all("span", {"class": "nfl-o-injury-report__club-name"})
+    assert team_names_spans
+    team_names_str = [x.get_text() for x in team_names_spans]
+    assert team_names_str[0] == team.team_full_name
+    tables = report_soup.find_all("table")
+    df_report = pd.read_html(str(tables))[0]
+    return df_report
+
+
 def scrape_team_injury_report(team: NFLTeam) -> pd.DataFrame:
     print(f"Scraping Injury Report for: {team.team_full_name}")
-    injury_report_url = urljoin(team.injury_report_url, f"week/REG-{CURRENT_WEEK}")
     try:
-        team_report = pd.read_html(injury_report_url)[0]
+        team_report = get_injury_report_dataframe(team)
     except Exception:
         print(f"Failed to scrape practice report for: {team.team_full_name}")
         return pd.DataFrame()