youtube_transcript.py

!pip install youtube_transcript_api

# -*- coding: utf-8 -*-

from youtube_transcript_api import YouTubeTranscriptApi
from urllib.parse import urlparse, parse_qs

urltext = "https://youtu.be/jzTjCgWlFRU"

args = [urltext]

def extract_video_id(url):
    query = urlparse(url)
    if query.hostname == 'youtu.be': return query.path[1:]
    if query.hostname in {'www.youtube.com', 'youtube.com'}:
        if query.path == '/watch': return parse_qs(query.query)['v'][0]
        if query.path[:7] == '/embed/': return query.path.split('/')[2]
        if query.path[:3] == '/v/': return query.path.split('/')[2]
    # fail?
    else:
        return None

for url in args:
    video_id = extract_video_id(url)
    print('youtube video_id:',video_id)
    print()

line =[]
line[:] = YouTubeTranscriptApi.get_transcript(video_id,languages=['en'])
transcript = YouTubeTranscriptApi.list_transcripts(video_id)    

english = transcript.find_transcript(['en'])
#print(english.fetch())

caption_line = []
for count, dict_obj in enumerate(english.fetch()):
    print("time", dict_obj['start']  , ': ',end='')
    print(dict_obj['text'] )
    caption_line.append(dict_obj['text'])

print()
print()
print("************************************************************************************")
print()
print("Youtube captions")
print("- - - - - - - - - - - - - - - - - - translated - - - - - - - - - - - - - - - - - - -")
print()
print()

translated = english.translate('ja')
for count, dict_obj in enumerate(translated.fetch()):# japanese
    print("time", dict_obj['start'] , ": ",end='')
    print(dict_obj['text'])


# text_list = []

# for l in line:

#     #print("start:", l['start'])
#     print(l['text'])
#     #print()
#     #print("duration:", l['duration'])

#     temp1 = l['text']
#     temp2 = temp1.rstrip()
#     text_list.append(temp2)

# del line

#for text in text_list:
#    print(text)