从youtube提取的自动英文字幕不包含可读形式的信息和重复的文本信息。
welcome<00:00:01.790><c> my</c><00:00:02.790><c> name</c><c.colorCCCCCC><00:00:02.820><c> is</c><00:00:03.210><c> Helga</c></c><c.colorE5E5E5><00:00:03.449><c> Vieira</c><00:00:03.929><c> and</c><00:00:04.080><c> this</c></c>
00:00:04.670 --> 00:00:04.680 align:start position:0%
welcome my name<c.colorCCCCCC> is Helga</c><c.colorE5E5E5> Vieira and this
</c>
我的代码：
def captions_test02(url):
ydl = youtube_dl.YoutubeDL({'writesubtitles': True, 'allsubtitles': True, 'writeautomaticsub': True})
res = ydl.extract_info(url, download=False)
if res['requested_subtitles'] and res['requested_subtitles']['en']:
print('Grabbing vtt file from ' + res['requested_subtitles']['en']['url'])
response = requests.get(res['requested_subtitles']['en']['url'], stream=True)
f1 = open("testfile01.txt", "w")
f1.write(response.text)
f1.close()
if len(res['subtitles']) > 0:
print('manual captions')
else:
print('automatic_captions')
else:
print('Youtube Video does not have any english captions')
if __name__ == '__main__': …在插入 4000 行中的 95 行视频元数据后，我遇到了以下错误。sqlalchemy.exc.TimeoutError: QueuePool limit of size 5 overflow 10 达到，连接超时，超时 30（此错误的背景：http://sqlalche。我/e/3o7r）。
根据
engine = db.create_engine(connect_string)
con = engine.connect()
_SessionFactory = sessionmaker(bind=engine)
Base = declarative_base()
def session_factory():
Base.metadata.create_all(engine)
return _SessionFactory()
视频对象
class Video(Base):
__tablename__ = 'video'
video_to_person = Table('video_to_person', Base.metadata,
Column('video_id', String, ForeignKey('video.vid')),
Column('person_id', Integer, ForeignKey('person.id'))
)
_vid = Column("vid",String, primary_key=True)
_webpage_url = Column("webpage_url", String)
_upload_date = Column("upload_date", Date)
_uploader = Column("uploader", String)
_view_count = Column("view_count", DECIMAL)
_like_count = Column("like_count", DECIMAL)
_dislike_count = Column("dislike_count", DECIMAL)
_format …