Extract YouTube Channel IDs with Python

import re
import requests

API_KEY = "your_api_key_here"
BASE_URL = "https://www.googleapis.com/youtube/v3/channels"

def get_channel_id(url: str) -> str | None:
    """
    Resolve a YouTube channel URL to its Channel ID.

    Supports:
    - https://youtube.com/@handle
    - https://youtube.com/channel/UCxxxxxxxx
    - https://youtube.com/c/customname
    - https://youtube.com/user/username
    """
    url = url.strip()

    # Case 1: /channel/ format — ID is already in the URL
    match = re.search(r"youtube\.com/channel/(UC[a-zA-Z0-9_-]{22})", url)
    if match:
        return match.group(1)

    # Case 2: @handle format (post-2022)
    match = re.search(r"youtube\.com/(@[\w.-]+)", url)
    if match:
        resp = requests.get(BASE_URL, params={
            "part": "id",
            "forHandle": match.group(1),
            "key": API_KEY
        })
        resp.raise_for_status()
        items = resp.json().get("items", [])
        return items[0]["id"] if items else None

    # Case 3: Legacy /user/ format
    match = re.search(r"youtube\.com/user/([\w-]+)", url)
    if match:
        resp = requests.get(BASE_URL, params={
            "part": "id",
            "forUsername": match.group(1),
            "key": API_KEY
        })
        resp.raise_for_status()
        items = resp.json().get("items", [])
        return items[0]["id"] if items else None

    # Case 4: /c/ custom URL — API does not support this directly
    match = re.search(r"youtube\.com/c/([\w-]+)", url)
    if match:
        return _get_id_from_page(url)

    return None


def _get_id_from_page(url: str) -> str | None:
    """Extract Channel ID from YouTube page source."""
    headers = {"User-Agent": "Mozilla/5.0"}
    try:
        resp = requests.get(url, headers=headers, timeout=10)
        match = re.search(r'"channelId":"(UC[a-zA-Z0-9_-]{22})"', resp.text)
        return match.group(1) if match else None
    except Exception:
        return None


# Quick test
if __name__ == "__main__":
    test_urls = [
        "https://youtube.com/@mkbhd",
        "https://youtube.com/channel/UCBcRF18a7Qf58cCRy5xuWwQ",
        "https://youtube.com/user/marquesbrownlee",
    ]
    for url in test_urls:
        channel_id = get_channel_id(url)
        print(f"{url} → {channel_id}")

name,url
MKBHD,https://youtube.com/@mkbhd
Linus Tech Tips,https://youtube.com/@linustechtips
Veritasium,https://youtube.com/@veritasium

import csv
import time

def process_csv(input_path: str, output_path: str, delay: float = 0.5):
    """
    Read channel URLs from a CSV, look up Channel IDs, write results.
    delay: seconds to wait between API calls (rate limiting)
    """
    rows = []
    with open(input_path, newline="", encoding="utf-8") as f:
        reader = csv.DictReader(f)
        for row in reader:
            url = row.get("url", "").strip()
            channel_id = get_channel_id(url) if url else None
            rows.append({
                **row,
                "channel_id": channel_id or "NOT_FOUND",
            })
            print(f"Processed: {row.get('name', url)} → {channel_id}")
            time.sleep(delay)  # Stay within quota

    if rows:
        fieldnames = list(rows[0].keys())
        with open(output_path, "w", newline="", encoding="utf-8") as f:
            writer = csv.DictWriter(f, fieldnames=fieldnames)
            writer.writeheader()
            writer.writerows(rows)
        print(f"\nSaved {len(rows)} results to {output_path}")


process_csv("channels.csv", "channels_with_ids.csv")

import json
from pathlib import Path

CACHE_FILE = Path("channel_id_cache.json")

def load_cache() -> dict:
    if CACHE_FILE.exists():
        return json.loads(CACHE_FILE.read_text())
    return {}

def save_cache(cache: dict):
    CACHE_FILE.write_text(json.dumps(cache, indent=2))

def get_channel_id_cached(url: str) -> str | None:
    cache = load_cache()
    if url in cache:
        return cache[url]

    channel_id = get_channel_id(url)
    if channel_id:
        cache[url] = channel_id
        save_cache(cache)

    return channel_id

import time

def get_channel_id_safe(url: str, retries: int = 3) -> str | None:
    """get_channel_id with retry logic for transient errors."""
    for attempt in range(retries):
        try:
            return get_channel_id(url)
        except requests.exceptions.HTTPError as e:
            if e.response.status_code == 403:
                print("Quota exceeded. Wait until midnight Pacific or use a new key.")
                return None
            if attempt < retries - 1:
                time.sleep(2 ** attempt)
        except requests.exceptions.ConnectionError:
            if attempt < retries - 1:
                time.sleep(2 ** attempt)
    return None