How to Scrape YouTube Video Data

"""
KnoxProxy scraper for public YouTube video metadata.
Extracts title, view count, like count, and description from the
ytInitialData JSON blob embedded in a public watch page.
"""
import json
import random
import re
import time

import requests

PROXY_HOST = "proxy.knoxproxy.com"
PROXY_PORT = 10000  # residential rotating
PROXY_USER = "your_username"
PROXY_PASS = "your_password"

HEADERS = {
    "User-Agent": (
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
        "(KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36"
    ),
    "Accept-Language": "en-US,en;q=0.9",
}

INITIAL_DATA_RE = re.compile(r"var ytInitialData = (\{.*?\});</script>", re.DOTALL)


def proxy_dict(country: str = "us") -> dict:
    user = f"{PROXY_USER}-country-{country}"
    proxy_url = f"http://{user}:{PROXY_PASS}@{PROXY_HOST}:{PROXY_PORT}"
    return {"http": proxy_url, "https": proxy_url}


def fetch_youtube_video(video_id: str, max_retries: int = 3) -> dict:
    url = f"https://www.youtube.com/watch?v={video_id}"
    cookies = {"CONSENT": "YES+1"}  # skip the EU/UK consent interstitial

    for attempt in range(1, max_retries + 1):
        try:
            resp = requests.get(
                url, headers=HEADERS, cookies=cookies, proxies=proxy_dict(), timeout=20
            )
            if resp.status_code == 200:
                return parse_youtube_video(resp.text, video_id)
            print(f"Attempt {attempt}: YouTube returned status {resp.status_code}")
        except requests.exceptions.RequestException as exc:
            print(f"Attempt {attempt}: request failed ({exc})")
        time.sleep(random.uniform(2, 5))

    raise RuntimeError(f"Failed to fetch YouTube video {video_id} after {max_retries} attempts")


def parse_youtube_video(html: str, video_id: str) -> dict:
    match = INITIAL_DATA_RE.search(html)
    if not match:
        return {"video_id": video_id, "error": "ytInitialData not found"}

    data = json.loads(match.group(1))
    results = data.get("contents", {}).get("twoColumnWatchNextResults", {})
    primary = results.get("results", {}).get("results", {}).get("contents", [{}])[0]
    video_info = primary.get("videoPrimaryInfoRenderer", {})
    return {
        "video_id": video_id,
        "title": video_info.get("title", {}).get("runs", [{}])[0].get("text"),
        "view_count": video_info.get("viewCount", {})
        .get("videoViewCountRenderer", {})
        .get("viewCount", {})
        .get("simpleText"),
    }


if __name__ == "__main__":
    for video_id in ["dQw4w9WgXcQ"]:
        print(fetch_youtube_video(video_id))
        time.sleep(random.uniform(2, 5))

{
  "video_id": "dQw4w9WgXcQ",
  "title": "Example Channel - Official Video",
  "view_count": "1,482,309 views"
}