From 39ed931e533a750d1716b74c1fd8133d0b9bc684 Mon Sep 17 00:00:00 2001 From: pukkandan Date: Sun, 4 Apr 2021 03:35:17 +0530 Subject: [PATCH] Update to ytdl-commit-654b4f4 [youtube] prioritize information from YoutubeIE for playlist entries https://github.com/ytdl-org/youtube-dl/commit/654b4f4ff2718f38b3182c1188c5d569c14cc70a --- yt_dlp/extractor/arnes.py | 101 ++++++++++++++++++ yt_dlp/extractor/common.py | 5 +- yt_dlp/extractor/extractors.py | 6 ++ yt_dlp/extractor/palcomp3.py | 148 +++++++++++++++++++++++++++ yt_dlp/extractor/screencastomatic.py | 48 ++++++--- yt_dlp/extractor/youtube.py | 28 ++++- 6 files changed, 313 insertions(+), 23 deletions(-) create mode 100644 yt_dlp/extractor/arnes.py create mode 100644 yt_dlp/extractor/palcomp3.py diff --git a/yt_dlp/extractor/arnes.py b/yt_dlp/extractor/arnes.py new file mode 100644 index 0000000000..c0032fcab9 --- /dev/null +++ b/yt_dlp/extractor/arnes.py @@ -0,0 +1,101 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import ( + compat_parse_qs, + compat_urllib_parse_urlparse, +) +from ..utils import ( + float_or_none, + int_or_none, + parse_iso8601, + remove_start, +) + + +class ArnesIE(InfoExtractor): + IE_NAME = 'video.arnes.si' + IE_DESC = 'Arnes Video' + _VALID_URL = r'https?://video\.arnes\.si/(?:[a-z]{2}/)?(?:watch|embed|api/(?:asset|public/video))/(?P[0-9a-zA-Z]{12})' + _TESTS = [{ + 'url': 'https://video.arnes.si/watch/a1qrWTOQfVoU?t=10', + 'md5': '4d0f4d0a03571b33e1efac25fd4a065d', + 'info_dict': { + 'id': 'a1qrWTOQfVoU', + 'ext': 'mp4', + 'title': 'Linearna neodvisnost, definicija', + 'description': 'Linearna neodvisnost, definicija', + 'license': 'PRIVATE', + 'creator': 'Polona Oblak', + 'timestamp': 1585063725, + 'upload_date': '20200324', + 'channel': 'Polona Oblak', + 'channel_id': 'q6pc04hw24cj', + 'channel_url': 'https://video.arnes.si/?channel=q6pc04hw24cj', + 'duration': 596.75, + 'view_count': int, + 'tags': ['linearna_algebra'], + 'start_time': 10, + } + }, { + 'url': 'https://video.arnes.si/api/asset/s1YjnV7hadlC/play.mp4', + 'only_matching': True, + }, { + 'url': 'https://video.arnes.si/embed/s1YjnV7hadlC', + 'only_matching': True, + }, { + 'url': 'https://video.arnes.si/en/watch/s1YjnV7hadlC', + 'only_matching': True, + }, { + 'url': 'https://video.arnes.si/embed/s1YjnV7hadlC?t=123&hideRelated=1', + 'only_matching': True, + }, { + 'url': 'https://video.arnes.si/api/public/video/s1YjnV7hadlC', + 'only_matching': True, + }] + _BASE_URL = 'https://video.arnes.si' + + def _real_extract(self, url): + video_id = self._match_id(url) + + video = self._download_json( + self._BASE_URL + '/api/public/video/' + video_id, video_id)['data'] + title = video['title'] + + formats = [] + for media in (video.get('media') or []): + media_url = media.get('url') + if not media_url: + continue + formats.append({ + 'url': self._BASE_URL + media_url, + 'format_id': remove_start(media.get('format'), 'FORMAT_'), + 'format_note': media.get('formatTranslation'), + 'width': int_or_none(media.get('width')), + 'height': int_or_none(media.get('height')), + }) + self._sort_formats(formats) + + channel = video.get('channel') or {} + channel_id = channel.get('url') + thumbnail = video.get('thumbnailUrl') + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': self._BASE_URL + thumbnail, + 'description': video.get('description'), + 'license': video.get('license'), + 'creator': video.get('author'), + 'timestamp': parse_iso8601(video.get('creationTime')), + 'channel': channel.get('name'), + 'channel_id': channel_id, + 'channel_url': self._BASE_URL + '/?channel=' + channel_id if channel_id else None, + 'duration': float_or_none(video.get('duration'), 1000), + 'view_count': int_or_none(video.get('views')), + 'tags': video.get('hashtags'), + 'start_time': int_or_none(compat_parse_qs( + compat_urllib_parse_urlparse(url).query).get('t', [None])[0]), + } diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py index 60db922048..0cd217eb3d 100644 --- a/yt_dlp/extractor/common.py +++ b/yt_dlp/extractor/common.py @@ -3221,7 +3221,10 @@ def _get_cookies(self, url): """ Return a compat_cookies.SimpleCookie with the cookies for the url """ req = sanitized_Request(url) self._downloader.cookiejar.add_cookie_header(req) - return compat_cookies.SimpleCookie(req.get_header('Cookie')) + cookie = req.get_header('Cookie') + if cookie and sys.version_info[0] == 2: + cookie = str(cookie) + return compat_cookies.SimpleCookie(cookie) def _apply_first_set_cookie_header(self, url_handle, cookie): """ diff --git a/yt_dlp/extractor/extractors.py b/yt_dlp/extractor/extractors.py index d9e6742bab..58a850c933 100644 --- a/yt_dlp/extractor/extractors.py +++ b/yt_dlp/extractor/extractors.py @@ -80,6 +80,7 @@ ArteTVEmbedIE, ArteTVPlaylistIE, ) +from .arnes import ArnesIE from .asiancrush import ( AsianCrushIE, AsianCrushPlaylistIE, @@ -927,6 +928,11 @@ PacktPubIE, PacktPubCourseIE, ) +from .palcomp3 import ( + PalcoMP3IE, + PalcoMP3ArtistIE, + PalcoMP3VideoIE, +) from .pandoratv import PandoraTVIE from .parliamentliveuk import ParliamentLiveUKIE from .patreon import PatreonIE diff --git a/yt_dlp/extractor/palcomp3.py b/yt_dlp/extractor/palcomp3.py new file mode 100644 index 0000000000..fb29d83f9f --- /dev/null +++ b/yt_dlp/extractor/palcomp3.py @@ -0,0 +1,148 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + int_or_none, + str_or_none, + try_get, +) + + +class PalcoMP3BaseIE(InfoExtractor): + _GQL_QUERY_TMPL = '''{ + artist(slug: "%s") { + %s + } +}''' + _ARTIST_FIELDS_TMPL = '''music(slug: "%%s") { + %s + }''' + _MUSIC_FIELDS = '''duration + hls + mp3File + musicID + plays + title''' + + def _call_api(self, artist_slug, artist_fields): + return self._download_json( + 'https://www.palcomp3.com.br/graphql/', artist_slug, query={ + 'query': self._GQL_QUERY_TMPL % (artist_slug, artist_fields), + })['data'] + + def _parse_music(self, music): + music_id = compat_str(music['musicID']) + title = music['title'] + + formats = [] + hls_url = music.get('hls') + if hls_url: + formats.append({ + 'url': hls_url, + 'protocol': 'm3u8_native', + 'ext': 'mp4', + }) + mp3_file = music.get('mp3File') + if mp3_file: + formats.append({ + 'url': mp3_file, + }) + + return { + 'id': music_id, + 'title': title, + 'formats': formats, + 'duration': int_or_none(music.get('duration')), + 'view_count': int_or_none(music.get('plays')), + } + + def _real_initialize(self): + self._ARTIST_FIELDS_TMPL = self._ARTIST_FIELDS_TMPL % self._MUSIC_FIELDS + + def _real_extract(self, url): + artist_slug, music_slug = re.match(self._VALID_URL, url).groups() + artist_fields = self._ARTIST_FIELDS_TMPL % music_slug + music = self._call_api(artist_slug, artist_fields)['artist']['music'] + return self._parse_music(music) + + +class PalcoMP3IE(PalcoMP3BaseIE): + IE_NAME = 'PalcoMP3:song' + _VALID_URL = r'https?://(?:www\.)?palcomp3\.com(?:\.br)?/(?P[^/]+)/(?P[^/?&#]+)' + _TESTS = [{ + 'url': 'https://www.palcomp3.com/maiaraemaraisaoficial/nossas-composicoes-cuida-bem-dela/', + 'md5': '99fd6405b2d8fd589670f6db1ba3b358', + 'info_dict': { + 'id': '3162927', + 'ext': 'mp3', + 'title': 'Nossas Composições - CUIDA BEM DELA', + 'duration': 210, + 'view_count': int, + } + }] + + @classmethod + def suitable(cls, url): + return False if PalcoMP3VideoIE.suitable(url) else super(PalcoMP3IE, cls).suitable(url) + + +class PalcoMP3ArtistIE(PalcoMP3BaseIE): + IE_NAME = 'PalcoMP3:artist' + _VALID_URL = r'https?://(?:www\.)?palcomp3\.com(?:\.br)?/(?P[^/?&#]+)' + _TESTS = [{ + 'url': 'https://www.palcomp3.com.br/condedoforro/', + 'info_dict': { + 'id': '358396', + 'title': 'Conde do Forró', + }, + 'playlist_mincount': 188, + }] + _ARTIST_FIELDS_TMPL = '''artistID + musics { + nodes { + %s + } + } + name''' + + @ classmethod + def suitable(cls, url): + return False if re.match(PalcoMP3IE._VALID_URL, url) else super(PalcoMP3ArtistIE, cls).suitable(url) + + def _real_extract(self, url): + artist_slug = self._match_id(url) + artist = self._call_api(artist_slug, self._ARTIST_FIELDS_TMPL)['artist'] + + def entries(): + for music in (try_get(artist, lambda x: x['musics']['nodes'], list) or []): + yield self._parse_music(music) + + return self.playlist_result( + entries(), str_or_none(artist.get('artistID')), artist.get('name')) + + +class PalcoMP3VideoIE(PalcoMP3BaseIE): + IE_NAME = 'PalcoMP3:video' + _VALID_URL = r'https?://(?:www\.)?palcomp3\.com(?:\.br)?/(?P[^/]+)/(?P[^/?&#]+)/?#clipe' + _TESTS = [{ + 'url': 'https://www.palcomp3.com/maiaraemaraisaoficial/maiara-e-maraisa-voce-faz-falta-aqui-ao-vivo-em-vicosa-mg/#clipe', + 'add_ie': ['Youtube'], + 'info_dict': { + 'id': '_pD1nR2qqPg', + 'ext': 'mp4', + 'title': 'Maiara e Maraisa - Você Faz Falta Aqui - DVD Ao Vivo Em Campo Grande', + 'description': 'md5:7043342c09a224598e93546e98e49282', + 'upload_date': '20161107', + 'uploader_id': 'maiaramaraisaoficial', + 'uploader': 'Maiara e Maraisa', + } + }] + _MUSIC_FIELDS = 'youtubeID' + + def _parse_music(self, music): + youtube_id = music['youtubeID'] + return self.url_result(youtube_id, 'Youtube', youtube_id) diff --git a/yt_dlp/extractor/screencastomatic.py b/yt_dlp/extractor/screencastomatic.py index b5e76c9af0..0afdc17158 100644 --- a/yt_dlp/extractor/screencastomatic.py +++ b/yt_dlp/extractor/screencastomatic.py @@ -2,12 +2,18 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import js_to_json +from ..utils import ( + get_element_by_class, + int_or_none, + remove_start, + strip_or_none, + unified_strdate, +) class ScreencastOMaticIE(InfoExtractor): - _VALID_URL = r'https?://screencast-o-matic\.com/watch/(?P[0-9a-zA-Z]+)' - _TEST = { + _VALID_URL = r'https?://screencast-o-matic\.com/(?:(?:watch|player)/|embed\?.*?\bsc=)(?P[0-9a-zA-Z]+)' + _TESTS = [{ 'url': 'http://screencast-o-matic.com/watch/c2lD3BeOPl', 'md5': '483583cb80d92588f15ccbedd90f0c18', 'info_dict': { @@ -16,22 +22,30 @@ class ScreencastOMaticIE(InfoExtractor): 'title': 'Welcome to 3-4 Philosophy @ DECV!', 'thumbnail': r're:^https?://.*\.jpg$', 'description': 'as the title says! also: some general info re 1) VCE philosophy and 2) distance learning.', - 'duration': 369.163, + 'duration': 369, + 'upload_date': '20141216', } - } + }, { + 'url': 'http://screencast-o-matic.com/player/c2lD3BeOPl', + 'only_matching': True, + }, { + 'url': 'http://screencast-o-matic.com/embed?ff=true&sc=cbV2r4Q5TL&fromPH=true&a=1', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - jwplayer_data = self._parse_json( - self._search_regex( - r"(?s)jwplayer\('mp4Player'\).setup\((\{.*?\})\);", webpage, 'setup code'), - video_id, transform_source=js_to_json) - - info_dict = self._parse_jwplayer_data(jwplayer_data, video_id, require_title=False) - info_dict.update({ - 'title': self._og_search_title(webpage), - 'description': self._og_search_description(webpage), + webpage = self._download_webpage( + 'https://screencast-o-matic.com/player/' + video_id, video_id) + info = self._parse_html5_media_entries(url, webpage, video_id)[0] + info.update({ + 'id': video_id, + 'title': get_element_by_class('overlayTitle', webpage), + 'description': strip_or_none(get_element_by_class('overlayDescription', webpage)) or None, + 'duration': int_or_none(self._search_regex( + r'player\.duration\s*=\s*function\(\)\s*{\s*return\s+(\d+);\s*};', + webpage, 'duration', default=None)), + 'upload_date': unified_strdate(remove_start( + get_element_by_class('overlayPublished', webpage), 'Published: ')), }) - return info_dict + return info diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 3e19d18a00..016750a70f 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -379,7 +379,7 @@ def _extract_video(self, renderer): (lambda x: x['ownerText']['runs'][0]['text'], lambda x: x['shortBylineText']['runs'][0]['text']), compat_str) return { - '_type': 'url_transparent', + '_type': 'url', 'ie_key': YoutubeIE.ie_key(), 'id': video_id, 'url': video_id, @@ -2681,6 +2681,13 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor): }, { 'url': 'https://www.youtube.com/TheYoungTurks/live', 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/hashtag/cctv9', + 'info_dict': { + 'id': 'cctv9', + 'title': '#cctv9', + }, + 'playlist_mincount': 350, }] @classmethod @@ -2841,6 +2848,16 @@ def _post_thread_continuation_entries(self, post_thread_continuation): for entry in self._post_thread_entries(renderer): yield entry + r''' # unused + def _rich_grid_entries(self, contents): + for content in contents: + video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict) + if video_renderer: + entry = self._video_entry(video_renderer) + if entry: + yield entry + ''' + @staticmethod def _build_continuation_query(continuation, ctp=None): query = { @@ -3083,10 +3100,10 @@ def _extract_from_tabs(self, item_id, webpage, data, tabs): channel_name = renderer.get('title') channel_url = renderer.get('channelUrl') channel_id = renderer.get('externalId') - - if not renderer: + else: renderer = try_get( data, lambda x: x['metadata']['playlistMetadataRenderer'], dict) + if renderer: title = renderer.get('title') description = renderer.get('description', '') @@ -3112,11 +3129,12 @@ def _extract_from_tabs(self, item_id, webpage, data, tabs): 'width': int_or_none(t.get('width')), 'height': int_or_none(t.get('height')), }) - if playlist_id is None: playlist_id = item_id if title is None: - title = playlist_id + title = ( + try_get(data, lambda x: x['header']['hashtagHeaderRenderer']['hashtag']['simpleText']) + or playlist_id) title += format_field(selected_tab, 'title', ' - %s') metadata = {