Last active
January 27, 2017 14:06
-
-
Save oztalha/65cac41fea69484158f267d236101d1a to your computer and use it in GitHub Desktop.
Python script to scrape NBA game logs (saves each season as a separate html file)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from selenium import webdriver | |
from selenium.webdriver.common.keys import Keys | |
import pandas as pd | |
import time | |
driver = webdriver.Chrome() | |
#driver.get('http://stats.nba.com/teams/gamelogs/#!?Season=ALLTIME&SeasonType=Regular%20Season') | |
for year in range(2016,1945,-1): | |
url = 'http://stats.nba.com/teams/gamelogs/#!?Season='+str(year)+'-'+format((year+1)%100,'02d')+'&SeasonType=Regular%20Season' | |
driver.get(url) | |
time.sleep(3) | |
driver.get(url) #page needs to be refreshed | |
for i in range(50): | |
time.sleep(3) | |
try: | |
#driver.execute_script("window.scrollTo(0, document.body.scrollHeight);") | |
driver.find_element_by_class_name('table-addrows__button').click() | |
except: | |
pass | |
with open('session'+str(year)+'.htm', 'w') as out: | |
out.write(driver.page_source) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment