ysblf.py

import json
import time
from pathlib import Path

from bs4 import BeautifulSoup as bs
from selenium import webdriver
from selenium.webdriver.chrome.service import Service

with open(Path.home() / "ysblf.txt", "r", encoding="utf-8") as file:
    ysblf_links = file.read().split()


def chrome_driver():
    s = Service(str(Path.home() / "bin/opt/chromedriver"))

    options = webdriver.ChromeOptions()
    options.binary_location = r"/usr/bin/brave-browser"
    options.add_argument("-incognito")
    options.add_argument("headless")
    options.add_experimental_option("excludeSwitches", ["enable-automation"])

    browser = webdriver.Chrome(service=s, options=options)

    return browser


def get_video_url(chapter: str):
    browser = chrome_driver()
    browser.get(chapter)

    time.sleep(30)

    html = browser.page_source
    browser.close()

    soup = bs(html, "html.parser")
    iframe = soup.find_all("iframe")

    url_video = f"https:{iframe[2]['src']}"

    script = soup.find_all("script")

    with open("script.json", "r", encoding="utf-8") as f:
        f.write(script[42].text)
        json_data = json.loads(f.read().split("=", 1)[1])

    ysblf_key = list(json_data["pages"].keys())[1]
    season = json_data["pages"][ysblf_key]["metadata"]["title"].split(" | ")[0]
    title = json_data["pages"][ysblf_key]["analytics"]["convivaAssetName"]
    file_name = f"{season} - {title}"

    return file_name, url_video


data_ysblf = {}

for x in ysblf_links:
    print(f"Processing: {x}")
    for i in range(5):
        try:
            time.sleep(20)
            filename, urlvideo = get_video_url(x)
            data_ysblf[filename] = urlvideo
            break
        except TypeError:
            continue