gistfile1.py

import urllib2

def get_player_profiles(player_list):
# Returns a dict of player profile URLs to be used in the next step
    # Dict will hold player profile pages indexed by player name
    player_profile_urls=dict.fromkeys(player_list)
    for n in player_list:
        names=n.split(' ')
        # Search for the player names at NFL.com to get their individual player profiles, which contain the
        # data we ultimately want.
        search_url="http://www.nfl.com/players/search?category=name&filter="+names[0]+"+"+names[1]+"&playerType=current&team=3410"
        results=urllib2.urlopen(search_url)
        for l in results.readlines():
            try:
                if l.count('<a href')>0 and l.count('profile?id'):
                # Search the returned HTMl for the hyper-link data for the speciic player.
                # This is mostly string clean up stiff to make the URL string ready for thte next step.
                    split1=l.split('=')
                    first_piece=split1[1].lstrip('"')
                    second_piece=split1[2].split('"')[0]
                    player_profile_urls[n]="http://www.nfl.com"+first_piece+"="+second_piece
            except UnicodeDecodeError:
                print "Ignoring UnicodeDecodeError"
        results.close()
    return player_profile_urls

player_urls=get_player_profiles(players)