Getting names from HTML file via python -
def get_players(team_id, year): """ list of players in team in given year. inputs: team_id: string, three-letter id of team year: integer, year returns: list of strings players' names """ link = "http://espn.go.com/nba/team/stats/_/name/{}/year/{}/".format(team_id, year) soup = soup_link(link) game_stat_row = soup.find("tr", {"class": "colhead"}) player_names = [] name in game_stat_row: player_names.append(name) return player_names
hi want player names url: http://espn.go.com/nba/team/stats/_/name/por/year/2015/ giving html text not list of players. need find first occurence of each name , once. can me. thanks. using beautifulsoup way.
i use different way html code here
source = urllib2.urlopen(link) html = source.read() source.close(); soup = beautifulsoup(html, "html.parser")
since noticed rows end number used regex extract rows
players_table = soup.find_all("tr",{"class" : re.compile(r"\d+$")})
here code
from bs4 import beautifulsoup import urllib2 import re def get_players(team_id, year): link = "http://espn.go.com/nba/team/stats/_/name/{}/year/{}/".format(team_id, year) source = urllib2.urlopen(link) html = source.read() source.close(); soup = beautifulsoup(html, "html.parser") players_table = soup.find_all("tr",{"class" : re.compile(r"\d+$")}) player_names = [] table in players_table: in table.find_all('a'): player_names.append(a.get_text()) return player_names
Comments
Post a Comment