tubearchivist/tubearchivist
1
0
Fork 0
mirror of https://github.com/tubearchivist/tubearchivist.git synced 2025-03-17 19:30:12 +00:00
Code Issues Projects Releases Wiki Activity

remove workarounds for merged channel extraction failure

Browse Source
This commit is contained in:
Simon 2024-07-06 16:50:29 +02:00
parent c9007431bf
commit 039a49387c
No known key found for this signature in database
GPG Key ID: 2C15AA5E89985DD4
1 changed files with 1 additions and 59 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
tubearchivist/home/src/index/channel.py
View File

@ -6,46 +6,16 @@ functionality:
import json
import os
import re
from datetime import datetime
import requests
from home.src.download.thumbnails import ThumbManager
from home.src.download.yt_dlp_base import YtWrap
from home.src.es.connect import ElasticWrap, IndexPaginate
from home.src.index.generic import YouTubeItem
from home.src.index.playlist import YoutubePlaylist
from home.src.ta.helper import requests_headers
from home.src.ta.settings import EnvironmentSettings
def banner_extractor(channel_id: str) -> dict[str, str] | None:
"""workaround for new channel renderer, upstream #9893"""
url = f"https://www.youtube.com/channel/{channel_id}?hl=en"
cookies = {"SOCS": "CAI"}
response = requests.get(
url, cookies=cookies, headers=requests_headers(), timeout=30
)
if not response.ok:
return None
matched_urls = re.findall(
r'"(https://yt3.googleusercontent.com/[^"]+=w(\d{3,4})-fcrop64[^"]*)"',
response.text,
)
if not matched_urls:
return None
sorted_urls = sorted(matched_urls, key=lambda x: int(x[1]), reverse=True)
banner = sorted_urls[0][0]
channel_art_fallback = {
"channel_banner_url": banner,
"channel_tvart_url": banner.split("-fcrop64")[0],
}
return channel_art_fallback
class YoutubeChannel(YouTubeItem):
"""represents a single youtube channel"""
@ -87,7 +57,7 @@ class YoutubeChannel(YouTubeItem):
"channel_id": self.youtube_id,
"channel_last_refresh": int(datetime.now().timestamp()),
"channel_name": self.youtube_meta["uploader"],
"channel_subs": self._extract_follower_count(),
"channel_subs": self.youtube_meta.get("channel_follower_count", 0),
"channel_subscribed": False,
"channel_tags": self._parse_tags(self.youtube_meta.get("tags")),
"channel_banner_url": self._get_banner_art(),
@ -95,34 +65,6 @@ class YoutubeChannel(YouTubeItem):
"channel_tvart_url": self._get_tv_art(),
"channel_views": self.youtube_meta.get("view_count") or 0,
}
self._inject_fallback()
def _inject_fallback(self):
"""fallback channel art work, workaround for upstream #9893"""
if self.json_data["channel_banner_url"]:
return
print(f"{self.youtube_id}: attempt art fallback extraction")
fallback = banner_extractor(self.youtube_id)
if fallback:
print(f"{self.youtube_id}: fallback succeeded: {fallback}")
self.json_data.update(fallback)
def _extract_follower_count(self) -> int:
"""workaround for upstream #9893, extract subs from first video"""
subs = self.youtube_meta.get("channel_follower_count")
if subs is not None:
return subs
entries = self.youtube_meta.get("entries", [])
if entries:
first_entry = entries[0]
if isinstance(first_entry, dict):
subs_entry = first_entry.get("channel_follower_count")
if subs_entry is not None:
return subs_entry
return 0
def _parse_tags(self, tags):
"""parse channel tags"""