github/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2025-08-23 06:35:51 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Playlist data should include title of videos now ytdl-org#31336

Browse source
This commit is contained in:
Eric Zhang 2022-11-30 16:03:38 -05:00
commit 165bf773e8
1 changed files with 13 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

14
youtube_dl/extractor/youtube.py
View file

@ -315,7 +315,9 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
title = try_get( title = try_get(
renderer, renderer,
(lambda x: x['title']['runs'][0]['text'], (lambda x: x['title']['runs'][0]['text'],
lambda x: x['title']['simpleText']), compat_str) lambda x: x['title']['simpleText'],
lambda x: x['headline']['simpleText']), compat_str)
# print("TITLE OF VIDEO: ", title)
description = try_get( description = try_get(
renderer, lambda x: x['descriptionSnippet']['runs'][0]['text'], renderer, lambda x: x['descriptionSnippet']['runs'][0]['text'],
compat_str) compat_str)
@ -2644,6 +2646,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
def _video_entry(self, video_renderer): def _video_entry(self, video_renderer):
video_id = video_renderer.get('videoId') video_id = video_renderer.get('videoId')
# print("VIDEO TITLE", video_renderer['headline']['simpleText'])
if video_id: if video_id:
return self._extract_video(video_renderer) return self._extract_video(video_renderer)
@ -2688,11 +2691,13 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
yield entry yield entry
def _rich_grid_entries(self, contents): def _rich_grid_entries(self, contents):
# print("_rich_grid_entries contents", contents)
for content in contents: for content in contents:
video_renderer = try_get(content, video_renderer = try_get(content,
(lambda x: x['richItemRenderer']['content']['videoRenderer'], (lambda x: x['richItemRenderer']['content']['videoRenderer'],
lambda x: x['richItemRenderer']['content']['reelItemRenderer']), lambda x: x['richItemRenderer']['content']['reelItemRenderer']),
dict) dict)
# print("_rich_grid_entries video_renderer", video_renderer)
if video_renderer: if video_renderer:
entry = self._video_entry(video_renderer) entry = self._video_entry(video_renderer)
if entry: if entry:
@ -2745,6 +2750,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
def _entries(self, tab, item_id, webpage): def _entries(self, tab, item_id, webpage):
tab_content = try_get(tab, lambda x: x['content'], dict) tab_content = try_get(tab, lambda x: x['content'], dict)
# print("_entries tab_content", tab_content)
if not tab_content: if not tab_content:
return return
slr_renderer = try_get(tab_content, lambda x: x['sectionListRenderer'], dict) slr_renderer = try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
@ -2980,6 +2986,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
channel_title = renderer.get('title') or item_id channel_title = renderer.get('title') or item_id
tab_title = selected_tab.get('title') tab_title = selected_tab.get('title')
title = channel_title or item_id title = channel_title or item_id
# print("TITLE OF VIDEO: ", title)
if tab_title: if tab_title:
title += ' - %s' % tab_title title += ' - %s' % tab_title
if selected_tab.get('expandedText'): if selected_tab.get('expandedText'):
@ -3001,6 +3008,9 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
playlist_id=playlist_id, playlist_title=title, playlist_id=playlist_id, playlist_title=title,
playlist_description=description) playlist_description=description)
playlist.update(self._extract_uploader(data)) playlist.update(self._extract_uploader(data))
# print("_extract_from_tabs playlist", playlist)
# for video in playlist['entries']:
# print(video)
return playlist return playlist
def _extract_from_playlist(self, item_id, url, data, playlist): def _extract_from_playlist(self, item_id, url, data, playlist):
@ -3031,6 +3041,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
'identity token', default=None) 'identity token', default=None)
def _real_extract(self, url): def _real_extract(self, url):
print("EXTRACTING INFORMATION")
item_id = self._match_id(url) item_id = self._match_id(url)
url = compat_urlparse.urlunparse( url = compat_urlparse.urlunparse(
compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com')) compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
@ -3047,6 +3058,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
data = self._extract_yt_initial_data(item_id, webpage) data = self._extract_yt_initial_data(item_id, webpage)
tabs = try_get( tabs = try_get(
data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list) data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
# print("TEST TEST TEST TABS PRINT: ", tabs)
if tabs: if tabs:
return self._extract_from_tabs(item_id, webpage, data, tabs) return self._extract_from_tabs(item_id, webpage, data, tabs)
playlist = try_get( playlist = try_get(