Mobile proxies for YouTube

import csv
import re

import requests

PROXY = "http://LOGIN:PASSWORD@HOST:PORT"
VIDEOS_FILE = "videos.txt"
REPORT_FILE = "videos_report.csv"
WATCH_URL = "https://www.youtube.com/watch?v={video_id}"
HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
    "(KHTML, like Gecko) Chrome/126.0 Safari/537.36",
    "Accept-Language": "en-US,en;q=0.8",
    "Cookie": "SOCS=CAI; CONSENT=YES+1",
}
STATUS = re.compile(r'"playabilityStatus":\{"status":"([A-Z_]+)"(?:[^{}]*?"reason":"([^"]*)")?')

proxies = {"http": PROXY, "https": PROXY} if PROXY else None


def playability(video_id):
    url = WATCH_URL.format(video_id=video_id)
    try:
        page = requests.get(url, headers=HEADERS, proxies=proxies, timeout=30).text
    except requests.RequestException as error:
        return "REQUEST_FAILED", type(error).__name__
    match = STATUS.search(page)
    if not match:
        return "UNKNOWN", "player data not found, YouTube may have served a consent or captcha page"
    return match.group(1), match.group(2) or ""


def main():
    with open(VIDEOS_FILE) as f:
        video_ids = [line.strip() for line in f if line.strip()]

    with open(REPORT_FILE, "w", newline="") as f:
        writer = csv.writer(f)
        writer.writerow(["video_id", "status", "reason"])
        for video_id in video_ids:
            status, reason = playability(video_id)
            writer.writerow([video_id, status, reason])
            print(f"{video_id}  {status:<16} {reason}")


if __name__ == "__main__":
    main()