scrape_bsbr.py 文件源码

def get_active_players():
  letters = list('abcdefghijklmnopqrstuvwxyz')
  player_and_url_list = []
  print 'Checking currently active players on baseball-reference.com...'
  pbar = progressbar.ProgressBar(widgets=[progressbar.Percentage(), ' ', progressbar.Bar(), ' ', progressbar.ETA()])
  for letter in pbar(letters):
    letter_page = getSoupFromURL('http://www.baseball-reference.com/players/%s/' % (letter))
    # we don't just need active players (<b> tags), we need anyone who played in 2015!
    prefix_sections = letter_page.findAll('pre')
    for section in prefix_sections:
      player_and_url_list += list(_parse_bsbr_prefix_section(section))
  bref_id_dict = dict(player_and_url_list)
  return bref_id_dict