def stat_scraper(link, driver):
options = Options()
# options.headless = True
options.add_extensions = '/Users/Philip/Documents/NBA prediction script/Incremental Pipelines/3.34.0_0'
browser = webdriver.Chrome(executable_path=driver, chrome_options=options)
browser.get(link)
while True:
try:
wait = WebDriverWait(browser, 10).until(
EC.visibility_of_element_located((
By.XPATH,
'/html/body/main/div[2]/div/div[2]/div/div/nba-stat-table/div[2]/div[1]'
)))
break
except TimeoutException or NoSuchElementException:
browser.refresh()
print('failed to find page')
logging.info('Failed to connect to page')
browser.find_element_by_xpath(
'/html/body/main/div[2]/div/div[2]/div/div/div[1]/div[1]/div/div/label/select/option[1]'
).click()
browser.find_element_by_xpath(
'/html/body/main/div[2]/div/div[2]/div/div/nba-stat-table/div[3]/div/div/select/option[1]'
).click()
table = browser.find_element_by_class_name('nba-stat-table')
content = table.get_attribute('innerHTML')
df = pd.read_html(content)[0]
browser.quit()
return format_matchup(df)
def gen_browser(driver):
options = Options()
options.headless = True
options.add_extensions = '/Users/Philip/Documents/NBA prediction script/Incremental Pipelines/3.34.0_0'
return webdriver.Chrome(executable_path=driver, chrome_options=options)
