Headless endless scroll selenium

Question

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.common.exceptions import StaleElementReferenceException, TimeoutException
from s         


        

Answer 1

Here is a set of things that made it work for me in headless mode:

• switch to PhantomJS
• pretend to be a different browser by setting a custom User-Agent string
• before scrolling into view of the last tweet, scroll to the top of the page (several times to increase reliability)

The code:

import time

def return_html_code(url):
    dcap = dict(webdriver.DesiredCapabilities.PHANTOMJS)
    dcap["phantomjs.page.settings.userAgent"] = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.57 Safari/537.36"

    driver = webdriver.PhantomJS(desired_capabilities=dcap)
    driver.maximize_window()

    driver.get(url)

    # initial wait for the tweets to load
    wait = WebDriverWait(driver, 30)
    wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, "li[data-item-id]")))
    # scroll down to the last tweet until there is no more tweets loaded
    while True:
        tweets = driver.find_elements_by_css_selector("li[data-item-id]")
        number_of_tweets = len(tweets)
        print(number_of_tweets)

        # move to the top and then to the bottom 5 times in a row
        for _ in range(5):
            driver.execute_script("window.scrollTo(0, 0)")
            driver.execute_script("arguments[0].scrollIntoView(true);", tweets[-1])
            time.sleep(0.5)

        try:
            wait.until(wait_for_more_than_n_elements_to_be_present((By.CSS_SELECTOR, "li[data-item-id]"), number_of_tweets))
        except TimeoutException:
            break