def get_video_transcript(self, video_id):
"""
Retrieves and formats transcripts for the passed video
TODO: If no captions are available, download audio track and pass into
Cloud Speech-to-Text? for now we just return None implying that we cant
perform sentiment analysis on the video content itself.
"""
video = YouTube('https://www.youtube.com/watch?v={}'.format(video_id))
captions = video.captions.get_by_language_code('en')
if not captions:
logger.info('Unable to return transcript for video %r!', video_id)
return
# format captions as plaintext and strip trailing whitespace and html
try:
captions = ElementTree.fromstring(captions.xml_captions)
except UnicodeEncodeError:
xml = captions.xml_captions.encode("utf-8")
captions = ElementTree.fromstring(xml)
captions_list = []
for subtitle in captions.getchildren():
text = subtitle.text or u''
caption = unescape(text.replace('\n', ' ').replace(' ', ' '))
captions_list.append(u"{text} ".format(text=caption))
transcript = clean_html(
html.fromstring(u''.join(captions_list).strip()))
return transcript.text_content().strip()
def xml_caption_to_srt(self, xml_captions):
"""Convert xml caption tracks to "SubRip Subtitle (srt)".
:param str xml_captions:
XML formatted caption tracks.
"""
segments = []
root = ElementTree.fromstring(xml_captions)
for i, child in enumerate(root.getchildren()):
text = child.text or ''
caption = unescape(
text
.replace('\n', ' ')
.replace(' ', ' '),
)
duration = float(child.attrib['dur'])
start = float(child.attrib['start'])
end = start + duration
sequence_number = i + 1 # convert from 0-indexed to 1.
line = (
'{seq}\n{start} --> {end}\n{text}\n'.format(
seq=sequence_number,
start=self.float_to_srt_time_format(start),
end=self.float_to_srt_time_format(end),
text=caption,
)
)
segments.append(line)
return '\n'.join(segments).strip()