Slow scrolling down the page using Selenium
I needed it for the same issue , i needed to scrape a social media website
y = 1000 for timer in range(0,50): driver.execute_script("window.scrollTo(0, "+str(y)+")") y += 1000 time.sleep(1)
the sleep every 1000 is to allow to load
After some experiments, finally I found a good solution:
def __scroll_down_page(self, speed=8): current_scroll_position, new_height= 0, 1 while current_scroll_position <= new_height: current_scroll_position += speed self.__driver.execute_script("window.scrollTo(0, {});".format(current_scroll_position)) new_height = self.__driver.execute_script("return document.body.scrollHeight")
Here is a different approach that worked for me involving scrolling into view of the last search result and waiting for additional elements to load before scrolling again:
# -*- coding: utf-8 -*-from selenium import webdriverfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.common.exceptions import StaleElementReferenceExceptionfrom selenium.webdriver.support import expected_conditions as ECclass wait_for_more_than_n_elements(object): def __init__(self, locator, count): self.locator = locator self.count = count def __call__(self, driver): try: count = len(EC._find_elements(driver, self.locator)) return count >= self.count except StaleElementReferenceException: return Falsedriver = webdriver.Firefox()dep_airport = ['BTS', 'BRU', 'PAR']arr_airport = 'MAD'dep_date = '2015-07-15'arr_date = '2015-08-15'airports_string = str(r'%20').join(dep_airport)dep_airport = airports_stringurl = "https://www.pelikan.sk/sk/flights/list?dfc=C%s&dtc=C%s&rfc=C%s&rtc=C%s&dd=%s&rd=%s&px=1000&ns=0&prc=&rng=1&rbd=0&ct=0" % (dep_airport, arr_airport, arr_airport, dep_airport, dep_date, arr_date)driver.maximize_window()driver.get(url)wait = WebDriverWait(driver, 60)wait.until(EC.invisibility_of_element_located((By.XPATH, '//img[contains(@src, "loading")]')))wait.until(EC.invisibility_of_element_located((By.XPATH, u'//div[. = "Poprosíme o trpezlivosť, hľadáme pre Vás ešte viac letov"]/preceding-sibling::img')))while True: # TODO: make the endless loop end results = driver.find_elements_by_css_selector("div.flightbox") print "Results count: %d" % len(results) # scroll to the last element driver.execute_script("arguments[0].scrollIntoView();", results[-1]) # wait for more results to load wait.until(wait_for_more_than_n_elements((By.CSS_SELECTOR, 'div.flightbox'), len(results)))
Notes:
- you would need to figure out when to stop the loop - for example, at a particular
len(results)
value wait_for_more_than_n_elements
is a custom Expected Condition which helps to identify when the next portion is loaded and we can scroll again