コード例 #1
0
    # Create the file headings
    player_data_w = open(scrapersettings.player_data, "w")
    #player_data_w.writelines("player_id\tplayer_name\tteam_id\tteam_name\tgame\tpos\tminutes\tfgm\tfga\tthree_fgm\tthree_fga\tft\tfta\tpts\toffreb\tdefreb\ttotreb\tast\tto\tstl\tblk\tfouls\tgame_date\tneutral_site\n")

if (scrapersettings.ind_team_stats == 1):
    # Create the file headings
    team_data_w = open(scrapersettings.team_data, "w")
    #team_data_w.writelines("game_id\tgame_date\tsite\tteam_id\tteam_name\tteam_minutes\tteam_fgm\tteam_fga\tteam_three_fgm\tteam_three_fga\tteam_ft\tteam_fta\tteam_pts\tteam_offreb\tteam_defreb\tteam_totreb\tteam_ast\tteam_to\tteam_stl\tteam_blk\tteam_fouls\n")


if (scrapersettings.ind_game_stats == 1) or (scrapersettings.ind_player_stats == 1) or (scrapersettings.ind_team_stats == 1):
    print "Generating individual statistics for players and/or teams"

    # Grab data
    # Parse our mappings file to get our list of teams
    team_mapping = scraperfunctions.get_team_mappings()

    # Parse our schedule file to get a list of games
    game_mapping = scraperfunctions.get_game_mappings()

    # Parse the stats tables
    team_stats_total = [] # Create an empty list for storing the team stats
    alphanum = re.compile(r'[^\w\s:]+')
    for value, game in enumerate(game_mapping): # For each game in our dictionary
        if scrapersettings.debugmode == 1: print "Processing game " + str(game) + " (" + str(value+1) + " of " + str(len(game_mapping)) + ")"
        game_url = game_mapping[game][4]
        # from the game_url grab box_score 
        try:
            result = requests.get(game_url)
            game_page_data = result.content
        except:
コード例 #2
0
import scrapersettings
import csv
import re
import requests
import urllib2
import time
#from urllib.request import urlopen
from bs4 import BeautifulSoup

tstats = open(scrapersettings.tstats_data, "w")
tstats.writelines("team\tstats\trankings\tvalue\n")

record = open(scrapersettings.record_data,"w")
record.writelines("team\twin\tlosses\n")

team_mapping = scraperfunctions.get_team_mappings()


for value, team in enumerate(team_mapping):
    roster_url = str(scrapersettings.domain_base) + "/team/" + team + "/" + str(scrapersettings.year_index)
    team_name = team_mapping[team][0]
    try:
        #time.sleep(2)
        r = requests.get(roster_url)
        # , timeout=10
        r.raise_for_status()
        #ht = urlopen(roster_url)
        #except HTTPError
    except Exception:
        roster_url = str(scrapersettings.domain_base) + "/team/" + team + "/" + str(scrapersettings.year_index) + "?game_sport_year_ctl_id=" + str(scrapersettings.year_index)
        #team_mainpage_data = scraperfunctions.grabber(roster_url,scrapersettings.params, scrapersettings.http_header)