from time import sleep import random from selenium import webdriver from selenium.webdriver.chrome.service import Service from selenium.webdriver.chrome.options import Options 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.action_chains import ActionChains # These, absolute PSYCHOPATHS, are using cloudflare to identify bot traffic. # random sleep has been introduced to reduce the potential for being flagged. base_url = "https://www.curseforge.com" file_path = 'SteveOnlineModpack_List.txt' mod_version = '1.20.1' # Important page elements download_row_xpath = '/html/body/div[2]/div/main/div[1]/div[2]/div/section/div[3]/div/div[2]/a' download_button_xpath = '/html/body/div[2]/div/main/div[1]/div[2]/div/section/section/h2/div/div/a[1]' # Options user_agent = 'user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36' chrome_options = Options() chrome_options.add_argument(user_agent) chrome_options.add_argument('--allow-running-insecure-content') chrome_options.add_argument('--ignore-certificate-errors') chrome_options.add_argument('--safebrowsing-disable-download-protection') chrome_options.add_argument("--disable-features=InsecureDownloadWarnings") chrome_options.add_experimental_option("prefs", { "safebrowsing.enabled": False, "download.default_directory": "/home/spaulding/Downloads/mods/", "download.prompt_for_download": False, "download.directory_upgrade": True, "safebrowsing_for_trusted_sources_enabled": False, }) driver = webdriver.Chrome(service=Service(), options=chrome_options) driver.maximize_window() def do_sleep(start, finish, action): print(action) sleep(float(random.randrange(start, finish))) return def do_cf(url): files_query_string = f"/files/all?page=1&pageSize=10&version={mod_version}&gameVersionTypeId=1&showAlphaFiles=hide" files_url = f'{url}{files_query_string}' try: do_sleep(3, 6, 'Try URL..') driver.get(files_url) do_sleep(3, 6, 'Find file rows..') WebDriverWait(driver, 30).until( EC.presence_of_element_located((By.XPATH, download_row_xpath)) ) do_sleep(3, 6, 'Find first download row..') download_list_link = driver.find_element(By.XPATH, download_row_xpath) do_sleep(1, 3, 'Setup action chain..') actions = ActionChains(driver) do_sleep(1, 3, 'Click on first download element') actions.move_to_element(download_list_link).click().perform() do_sleep(3, 6, 'Wait for download page..') WebDriverWait(driver, 30).until( EC.presence_of_element_located((By.XPATH, download_button_xpath)) ) do_sleep(1, 3, 'Find download button..') download_btn = driver.find_element(By.XPATH, download_button_xpath) do_sleep(3, 6, 'Click download button..') actions.move_to_element(download_btn).click().perform() do_sleep(12, 24, 'Wait for download to start..') except Exception as e: print('!!!!!!!!!!!!!!!!!!!') print('Could not download file from URL: %s' % url) print('Error: %s' % e) print('!!!!!!!!!!!!!!!!!!!') count = 0 with open(file_path, 'r') as f: for line in f: count += 1 print('Processing line %s' % count) print(line) do_cf(line) print('============================================') # End the session driver.quit()