jimmy/t-youtube
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: DeepSeek API + transcript fixes; add OAuth captions scope

Browse Source
This commit is contained in:
Gan, Jimmy
2026-06-24 00:50:36 +08:00
parent 963e9dbdf1
commit 7b485abfbb
2 changed files with 21 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/summarizer.py
+14 -17
View File
@@ -28,38 +28,35 @@ Keep the entire summary under 150 words. Be extremely direct so I can decide in
Transcript:
{transcript}"""
COOKIES_PATH = None
for p in [os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "config/cookies.txt"),
"/app/config/cookies.txt"]:
if os.path.exists(p):
COOKIES_PATH = p
break
def download_transcript(video_id: str) -> str:
try:
session = requests.Session()
session.headers.update({
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36",
"Accept-Language": "en-US,en;q=0.9"
})
# Load cookies to bypass YouTube IP block
for p in [os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "config/cookies.txt"),
"/app/config/cookies.txt"]:
if os.path.exists(p):
from http.cookiejar import MozillaCookieJar
cj = MozillaCookieJar(p)
cj.load(ignore_discard=True, ignore_expires=True)
session.cookies.update({c.name: c.value for c in cj})
break
if COOKIES_PATH:
from http.cookiejar import MozillaCookieJar
cj = MozillaCookieJar(COOKIES_PATH)
cj.load(ignore_discard=True, ignore_expires=True)
session.cookies.update({c.name: c.value for c in cj})
transcript_list = YouTubeTranscriptApi(http_client=session).list(video_id)
# Try to find manual transcripts in preferred languages
try:
transcript = transcript_list.find_manually_created_transcript(['en', 'zh-Hans', 'zh-Hant', 'zh', 'ja'])
except Exception:
# Fallback to generated (auto-captions) in preferred languages
try:
transcript = transcript_list.find_generated_transcript(['en', 'zh-Hans', 'zh-Hant', 'zh', 'ja'])
except Exception:
# Fallback to any transcript
transcript = next(iter(transcript_list))
parts = transcript.fetch()
text = " ".join([part["text"] for part in parts])
return text
return " ".join([part["text"] for part in parts])
except Exception as e:
log.warning(f"Failed to fetch transcript for {video_id}: {e}")
return None