from selenium import webdriver
import time
from selenium.webdriver.common.action_chains import ActionChains
import urllib.parse


def main():
    #Suchbegriff
    search_words = ['α Welle', 'schlafen']
    #Chrom öffnen
    driver = webdriver.Chrome('../chromedriver')
    s = '+'.join(map(urllib.parse.quote, search_words))
    driver.get("https://www.youtube.com/results?search_query=" + s + '&sp=CAM%253D')
    info_list = []
    time.sleep(1)
    for i in range(10):
        driver.execute_script("scrollBy(0, 1000);")
    for i in range(35, 45):
        info = {'title': '', 'url': '', 'channel': '', 'registrant': 0, 'release': ''}
        loop_flag = 0
        selector = f'#contents > ytd-item-section-renderer:nth-child({i // 20 + 1}) > #contents > ytd-video-renderer:nth-child({20 if i % 20 == 0 else i % 20}) > #dismissable > #video-title > yt-formatted-string'
        while loop_flag <= 2:
            try:
                element = driver.find_element_by_css_selector(selector)
                actions = ActionChains(driver)
                actions.move_to_element(element)
                actions.perform()
                info['url'] = element.get_attribute('href')
                break
            except Exception as e:
                print(i, e)
                print(selector)
                loop_flag += 1
                time.sleep(1)
        if not info['url'] == '':
            info_list += info
    print(info_list)
    print(len(info_list))
    driver.quit()


if __name__ == "__main__":
    main()

Recommended Posts