def scrape_pages(driver, env, team_rosters, players):
pitcher_list = []
batter_list = []
for i, player in players.iterrows():
my_player = env['MY_PLAYERS'].get(player['espn_name'])
team_id = team_rosters.get(player['bref_name'])
if player['bref_id'] == '':
continue
if team_id is not None:
player['team_id'] = team_id
TEAM_ROSTER_NAMES_FOUND[player['bref_name']] = True
elif TRANSLATIONS.get(player['bref_name']) is not None:
translation = TRANSLATIONS.get(player['bref_name'])
team_id = team_rosters.get(translation)
player['team_id'] = team_id
TEAM_ROSTER_NAMES_FOUND[translation] = True
else:
continue
if TRADES.get(player['bref_name']) is not None:
team_id = TRADES.get(player['bref_name'])
#if team_id != 8:
# continue
print('Scraping Player: ' + player['bref_name'] + ' index: ' + str(i) +
'\n\n')
current_player = Player(player)
if my_player is not None:
current_player.mine = True
# Baseball Reference
br_url = env['BR_URL'] + current_player.bref_id
if not current_player.batter:
br_url = br_url + '&t=p'
driver.get(br_url)
tr_xpath_start = '//*[@id="total"]/tbody/tr'
current_player = get_stats(driver, 'BR', tr_xpath_start, './/th[1]',
current_player)
tr_xpath_start = '//*[@id="plato"]/tbody/tr'
current_player = get_stats(driver, 'BR', tr_xpath_start, './/th[1]',
current_player)
if not current_player.batter:
tr_xpath_start = '//*[@id="total_extra"]/tbody/tr'
current_player = get_stats(driver, 'BR', tr_xpath_start,
'.//th[1]', current_player)
if current_player.batter:
batter_list.append(current_player.to_dict())
else:
pitcher_list.append(current_player.to_dict())
return {
'batter_list': batter_list,
'pitcher_list': pitcher_list,
}
