[linter] youtube.py

This commit is contained in:
pukkandan 2021-02-04 20:27:26 +05:30
parent 545cc85d11
commit 8a784c74d1

View file

@ -7,6 +7,7 @@
import os.path import os.path
import random import random
import re import re
import time
import traceback import traceback
from .common import InfoExtractor, SearchInfoExtractor from .common import InfoExtractor, SearchInfoExtractor
@ -30,9 +31,8 @@
int_or_none, int_or_none,
mimetype2ext, mimetype2ext,
parse_codecs, parse_codecs,
parse_count,
parse_duration, parse_duration,
qualities, # qualities,
remove_start, remove_start,
smuggle_url, smuggle_url,
str_or_none, str_or_none,
@ -1494,7 +1494,7 @@ def feed_entry(name):
formats = [] formats = []
itags = [] itags = []
player_url = None player_url = None
q = qualities(['tiny', 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres']) # q = qualities(['tiny', 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'])
streaming_data = player_response.get('streamingData') or {} streaming_data = player_response.get('streamingData') or {}
streaming_formats = streaming_data.get('formats') or [] streaming_formats = streaming_data.get('formats') or []
streaming_formats.extend(streaming_data.get('adaptiveFormats') or []) streaming_formats.extend(streaming_data.get('adaptiveFormats') or [])
@ -1909,10 +1909,9 @@ def chapter_time(mmlir):
if not xsrf_token: if not xsrf_token:
xsrf_token = self._search_regex( xsrf_token = self._search_regex(
r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>(?:(?!\2).)+)\2', r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>(?:(?!\2).)+)\2',
video_webpage, 'xsrf token', group='xsrf_token', fatal=False) webpage, 'xsrf token', group='xsrf_token', fatal=False)
# annotations # annotations
video_annotations = None
if get_annotations: if get_annotations:
invideo_url = try_get( invideo_url = try_get(
player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str) player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str)
@ -1923,9 +1922,9 @@ def chapter_time(mmlir):
if not xsrf_field_name: if not xsrf_field_name:
xsrf_field_name = self._search_regex( xsrf_field_name = self._search_regex(
r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2', r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2',
video_webpage, 'xsrf field name', webpage, 'xsrf field name',
group='xsrf_field_name', default='session_token') group='xsrf_field_name', default='session_token')
video_annotations = self._download_webpage( info['annotations'] = self._download_webpage(
self._proto_relative_url(invideo_url), self._proto_relative_url(invideo_url),
video_id, note='Downloading annotations', video_id, note='Downloading annotations',
errnote='Unable to download video annotations', fatal=False, errnote='Unable to download video annotations', fatal=False,
@ -1955,12 +1954,14 @@ def search_dict(partial, key):
for o in search_dict(i, key): for o in search_dict(i, key):
yield o yield o
try: continuations = []
ncd = next(search_dict(yt_initial_data, 'nextContinuationData')) if initial_data:
continuations = [ncd['continuation']] try:
# Handle videos where comments have been disabled entirely ncd = next(search_dict(initial_data, 'nextContinuationData'))
except StopIteration: continuations = [ncd['continuation']]
continuations = [] # Handle videos where comments have been disabled entirely
except StopIteration:
pass
def get_continuation(continuation, session_token, replies=False): def get_continuation(continuation, session_token, replies=False):
query = { query = {
@ -2034,10 +2035,8 @@ def get_continuation(continuation, session_token, replies=False):
'parent': 'root' 'parent': 'root'
}) })
if 'replies' not in meta_comment['commentThreadRenderer']: if 'replies' not in meta_comment['commentThreadRenderer']:
continue continue
reply_continuations = [rcn['nextContinuationData']['continuation'] for rcn in meta_comment['commentThreadRenderer']['replies']['commentRepliesRenderer']['continuations']] reply_continuations = [rcn['nextContinuationData']['continuation'] for rcn in meta_comment['commentThreadRenderer']['replies']['commentRepliesRenderer']['continuations']]
while reply_continuations: while reply_continuations:
time.sleep(1) time.sleep(1)
@ -2061,13 +2060,10 @@ def get_continuation(continuation, session_token, replies=False):
'parent': comment['commentId'] 'parent': comment['commentId']
}) })
if 'continuations' not in reply_comment_meta or len(reply_comment_meta['continuations']) == 0: if 'continuations' not in reply_comment_meta or len(reply_comment_meta['continuations']) == 0:
continue continue
reply_continuations += [rcn['nextContinuationData']['continuation'] for rcn in reply_comment_meta['continuations']] reply_continuations += [rcn['nextContinuationData']['continuation'] for rcn in reply_comment_meta['continuations']]
self.to_screen('Comments downloaded %s of ~%s' % (len(video_comments), expected_video_comment_count)) self.to_screen('Comments downloaded %s of ~%s' % (len(video_comments), expected_video_comment_count))
if 'continuations' in item_section: if 'continuations' in item_section:
continuations += [ncd['nextContinuationData']['continuation'] for ncd in item_section['continuations']] continuations += [ncd['nextContinuationData']['continuation'] for ncd in item_section['continuations']]
time.sleep(1) time.sleep(1)