Web scrapping with a double loop with selenium and using By.SELECTOR

Question

I am trying to get the pdf files from this website. I am trying to create a double loop so I can scroll over the years (Season) to get all the main pdf located in each year.

The line of code is not working is this one. The problem is, I can not make this line work (The one that is supposed to loop all over the years (Season):

for year in wait.until(EC.presence_of_all_elements_located((By.CSS_SELECTOR, "#season a aria-valuetext"))):
 year.click() 

This is the full code:

  os.chdir("C:..")
    driver = webdriver.Chrome("chromedriver.exe")
    wait = WebDriverWait(driver, 10)
    driver.get("http://www.motogp.com/en/Results+Statistics/")
    links = []


    for year in wait.until(EC.presence_of_all_elements_located((By.CSS_SELECTOR, "#season a aria-valuetext"))):
     year.click()                                                          
     for item in wait.until(EC.presence_of_all_elements_located((By.CSS_SELECTOR, "#event option"))):
         item.click()
         elem = wait.until(EC.presence_of_element_located((By.CLASS_NAME, "padleft5")))
         print(elem.get_attribute("href"))
         links.append(elem.get_attribute("href"))
         wait.until(EC.staleness_of(elem))

    driver.quit()

This is a previous post where I got help with the code above:

Scraping pdfs from this web

Answer 1

The solution below should work for you. First, we iterate over the # of years in the CSS slider. Then we work the list using your code example. Added a sleep command because I kept getting a timeout.

CODE

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.keys import Keys
import time

driver = webdriver.Chrome("chromedriver.exe")
wait = WebDriverWait(driver, 10)
driver.get("http://www.motogp.com/en/Results+Statistics/")

slider = driver.find_element_by_xpath('//*[@id="handle_season"]')

for year in range(68):
    wait.until(EC.presence_of_all_elements_located((By.XPATH, '//*[@id="event"]')))    
    for item in wait.until(EC.presence_of_all_elements_located((By.CSS_SELECTOR, "#event option"))):
        item.click()
        elem = wait.until(EC.presence_of_element_located((By.CLASS_NAME, "padleft5")))
        print(elem.get_attribute("href"))
        wait.until(EC.staleness_of(elem))

    slider.send_keys(Keys.ARROW_LEFT)
    time.sleep(1)


driver.quit()

Result:

Answer 2

If your working behind a firewall then a lot of times your EC’s won’t work. See if a time.sleep(10) function doesn’t get you past it, instead of an EC. Secondly, check the page_source before you run the EC... if you’re behind a firewall the HTML source code will tell you.