mlb_scraper.py 文件源码

def load_stats_tables_from_history_page(url):
  """Load all the prediction tables from a Numberfire history page"""
  soup = getSoupFromURL(url)
  #salary = load_player_salary_table(soup)
  projection_months = ['%s-schedule' % month for month in
                       ['March', 'April', 'May', 'June', 'July', 'August', 'September', 'October']]
  month_tables = []
  for month in projection_months:
    month_schedule = soup.find('div', attrs={'id': month})
    month_table = load_player_history_table(month_schedule)
    if month_table is not None:
      month_tables.append(month_table)
  if month_tables:
    all_predictions = pandas.concat(month_tables)
    all_predictions.sort_index(inplace=True)
    if all_predictions.index.duplicated().any():
      print 'Duplicate games scraped!'
      import IPython
      IPython.embed()
  else:
    all_predictions = None
  return all_predictions