florian
ca1bdfd707
Instead of waiting a day or two until an episode has come out now the script checks for 3 days for a release and then waits another day for sponsorblock segments to be added.
126 lines
3.7 KiB
Python
126 lines
3.7 KiB
Python
import yt_dlp
|
|
import datetime
|
|
import contextlib
|
|
from dotenv import load_dotenv
|
|
import os
|
|
from helper import return_string_as_html
|
|
from simple_logger_handler import setup_logger
|
|
import json
|
|
import sponsorblock as sb
|
|
|
|
|
|
logger = setup_logger(__name__)
|
|
load_dotenv()
|
|
YOUTUBE_CHANNEL_URL = os.getenv("YOUTUBE_CHANNEL_URL")
|
|
|
|
|
|
def get_url_for_latest_video():
|
|
"""
|
|
Fetch the URL of the latest video from a YouTube channel.
|
|
"""
|
|
logger.info("[YouTube] Fetching latest video URL from YouTube channel")
|
|
options = {
|
|
"extract_flat": True,
|
|
"playlist_items": "1",
|
|
"quiet": True,
|
|
"forcejson": True,
|
|
"simulate": True,
|
|
}
|
|
|
|
try:
|
|
with open(os.devnull, "w") as devnull, contextlib.redirect_stdout(devnull):
|
|
with yt_dlp.YoutubeDL(options) as video:
|
|
info_dict = video.extract_info(YOUTUBE_CHANNEL_URL, download=False)
|
|
except Exception as e:
|
|
logger.error(f"[YouTube] Failed to fetch latest video info: {e}", exc_info=True)
|
|
return None
|
|
|
|
if "entries" in info_dict and len(info_dict["entries"]) > 0:
|
|
latest_url = info_dict["entries"][0]["url"]
|
|
logger.debug(f"[YouTube] Latest video URL found: {latest_url}")
|
|
return latest_url
|
|
else:
|
|
logger.warning("[YouTube] No entries found in channel feed")
|
|
return None
|
|
|
|
def get_youtube_data(url: str) -> dict:
|
|
"""
|
|
Fetch metadata for a given YouTube video URL.
|
|
"""
|
|
logger.info(f"Fetching YouTube metadata for video: {url}")
|
|
try:
|
|
with yt_dlp.YoutubeDL({"quiet": True, "noprogress": True}) as video:
|
|
info_dict = video.extract_info(url, download=False)
|
|
except Exception as e:
|
|
logger.error(f"[YouTube] Failed to fetch YouTube video info for {url}: {e}", exc_info=True)
|
|
return {}
|
|
|
|
video_data = {
|
|
"date": datetime.datetime.fromtimestamp(
|
|
info_dict["timestamp"], datetime.timezone.utc
|
|
).strftime("%Y-%m-%d"),
|
|
"title": info_dict["title"],
|
|
"description": info_dict.get("description", "")
|
|
}
|
|
|
|
logger.debug(f"[YouTube] Fetched video data: {json.dumps(video_data, indent=4)}")
|
|
return video_data
|
|
|
|
def check_for_sponsorblock_segments(youtube_video:str) -> bool:
|
|
client = sb.Client()
|
|
try:
|
|
segments = client.get_skip_segments(youtube_video)
|
|
except sb.errors.NotFoundException:
|
|
logger.debug(f"[SponsorBlock] No SponsorBlock information for video:{youtube_video}")
|
|
return False
|
|
|
|
if segments:
|
|
logger.info(f"[SponsorBlock] SponsorBlock segments found for video: {youtube_video}")
|
|
return True
|
|
|
|
def return_download_options(information:dict,track:str)->dict:
|
|
download_options = {
|
|
"quiet": True,
|
|
"noprogress": True,
|
|
"format": "bestaudio/best",
|
|
"extract_audio": True,
|
|
"audio_format": "mp3",
|
|
"outtmpl": f"perun-{information['date']}.%(ext)s",
|
|
"addmetadata": True,
|
|
"postprocessors":[
|
|
{"api": "https://sponsor.ajay.app",
|
|
"categories":["sponsor"],
|
|
"key": "SponsorBlock",
|
|
"when": "after_filter"
|
|
},
|
|
{
|
|
"force_keyframes": False,
|
|
"key": "ModifyChapters",
|
|
"remove_chapters_patterns": [],
|
|
"remove_ranges": [],
|
|
"remove_sponsor_segments": ["sponsor"],
|
|
"sponsorblock_chapter_title": "[SponsorBlock]: %(category_names)l"
|
|
},
|
|
{
|
|
"key": "FFmpegExtractAudio",
|
|
"preferredcodec": "mp3",
|
|
},
|
|
{
|
|
"key": "FFmpegMetadata",
|
|
}],
|
|
"postprocessor_args": [
|
|
"-metadata", f"title={information['title']}",
|
|
"-metadata", "artist=Perun",
|
|
"-metadata", f"track={track}",
|
|
"-metadata", f"date={information['date']}",
|
|
"-metadata", f"comment={return_string_as_html(information['description'])}",
|
|
"-metadata", f"description={return_string_as_html(information['description'])}",
|
|
],
|
|
"merge_output_format": "mp3"
|
|
}
|
|
logger.debug(f"[YouTube] Created download options:\n {json.dumps(download_options, indent=4)}")
|
|
return download_options
|
|
|
|
if __name__ == "__main__":
|
|
print(check_for_sponsorblock_segments("https://www.youtube.com/watch?v=M0t8UYZ9rrQ"))
|