Merge 38e08a1147 into be3579aaf0

Authored by: stratus-ss, bashonly

Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>

yt_dlp/extractor/_extractors.py

@@ -708,6 +708,7 @@ from .gab import (
     GabTVIE,
 )
 from .gaia import GaiaIE
+from .gamedevtv import GameDevTVDashboardIE
 from .gamejolt import (
     GameJoltCommunityIE,
     GameJoltGameIE,
@@ -2490,6 +2491,7 @@ from .xinpianchang import XinpianchangIE
 from .xminus import XMinusIE
 from .xnxx import XNXXIE
 from .xstream import XstreamIE
+from .xumo import XumoIE
 from .xvideos import (
     XVideosIE,
     XVideosQuickiesIE,

yt_dlp/extractor/adobepass.py

@@ -1362,7 +1362,7 @@ class AdobePassIE(InfoExtractor):  # XXX: Conventionally, base classes should en
 
     def _download_webpage_handle(self, *args, **kwargs):
         headers = self.geo_verification_headers()
-        headers.update(kwargs.get('headers', {}))
+        headers.update(kwargs.get('headers') or {})
         kwargs['headers'] = headers
         return super()._download_webpage_handle(
             *args, **kwargs)

yt_dlp/extractor/gamedevtv.py

@@ -0,0 +1,141 @@
+import json
+
+from .common import InfoExtractor
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    int_or_none,
+    join_nonempty,
+    parse_iso8601,
+    str_or_none,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class GameDevTVDashboardIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?gamedev\.tv/dashboard/courses/(?P<course_id>\d+)(?:/(?P<lecture_id>\d+))?'
+    _NETRC_MACHINE = 'gamedevtv'
+    _TESTS = [{
+        'url': 'https://www.gamedev.tv/dashboard/courses/25',
+        'info_dict': {
+            'id': '25',
+            'title': 'Complete Blender Creator 3: Learn 3D Modelling for Beginners',
+            'tags': ['blender', 'course', 'all', 'box modelling', 'sculpting'],
+            'categories': ['Blender', '3D Art'],
+            'thumbnail': 'https://gamedev-files.b-cdn.net/courses/qisc9pmu1jdc.jpg',
+            'upload_date': '20220516',
+            'timestamp': 1652694420,
+            'modified_date': '20241027',
+            'modified_timestamp': 1730049658,
+        },
+        'playlist_count': 100,
+    }, {
+        'url': 'https://www.gamedev.tv/dashboard/courses/63/2279',
+        'info_dict': {
+            'id': 'df04f4d8-68a4-4756-a71b-9ca9446c3a01',
+            'ext': 'mp4',
+            'modified_timestamp': 1701695752,
+            'upload_date': '20230504',
+            'episode': 'MagicaVoxel Community Course Introduction',
+            'series_id': '63',
+            'title': 'MagicaVoxel Community Course Introduction',
+            'timestamp': 1683195397,
+            'modified_date': '20231204',
+            'categories': ['3D Art', 'MagicaVoxel'],
+            'season': 'MagicaVoxel Community Course',
+            'tags': ['MagicaVoxel', 'all', 'course'],
+            'series': 'MagicaVoxel 3D Art Mini Course',
+            'duration': 1405,
+            'episode_number': 1,
+            'season_number': 1,
+            'season_id': '219',
+            'description': 'md5:a378738c5bbec1c785d76c067652d650',
+            'display_id': '63-219-2279',
+            'alt_title': '1_CC_MVX MagicaVoxel Community Course Introduction.mp4',
+            'thumbnail': 'https://vz-23691c65-6fa.b-cdn.net/df04f4d8-68a4-4756-a71b-9ca9446c3a01/thumbnail.jpg',
+        },
+    }]
+    _API_HEADERS = {}
+
+    def _perform_login(self, username, password):
+        try:
+            response = self._download_json(
+                'https://api.gamedev.tv/api/students/login', None, 'Logging in',
+                headers={'Content-Type': 'application/json'},
+                data=json.dumps({
+                    'email': username,
+                    'password': password,
+                    'cart_items': [],
+                }).encode())
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and e.cause.status == 401:
+                raise ExtractorError('Invalid username/password', expected=True)
+            raise
+
+        self._API_HEADERS['Authorization'] = f'{response["token_type"]} {response["access_token"]}'
+
+    def _real_initialize(self):
+        if not self._API_HEADERS.get('Authorization'):
+            self.raise_login_required(
+                'This content is only available with purchase', method='password')
+
+    def _entries(self, data, course_id, course_info, selected_lecture):
+        for section in traverse_obj(data, ('sections', ..., {dict})):
+            section_info = traverse_obj(section, {
+                'season_id': ('id', {str_or_none}),
+                'season': ('title', {str}),
+                'season_number': ('order', {int_or_none}),
+            })
+            for lecture in traverse_obj(section, ('lectures', lambda _, v: url_or_none(v['video']['playListUrl']))):
+                if selected_lecture and str(lecture.get('id')) != selected_lecture:
+                    continue
+                display_id = join_nonempty(course_id, section_info.get('season_id'), lecture.get('id'))
+                formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+                    lecture['video']['playListUrl'], display_id, 'mp4', m3u8_id='hls')
+                yield {
+                    **course_info,
+                    **section_info,
+                    'id': display_id,  # fallback
+                    'display_id': display_id,
+                    'formats': formats,
+                    'subtitles': subtitles,
+                    'series': course_info.get('title'),
+                    'series_id': course_id,
+                    **traverse_obj(lecture, {
+                        'id': ('video', 'guid', {str}),
+                        'title': ('title', {str}),
+                        'alt_title': ('video', 'title', {str}),
+                        'description': ('description', {clean_html}),
+                        'episode': ('title', {str}),
+                        'episode_number': ('order', {int_or_none}),
+                        'duration': ('video', 'duration_in_sec', {int_or_none}),
+                        'timestamp': ('video', 'created_at', {parse_iso8601}),
+                        'modified_timestamp': ('video', 'updated_at', {parse_iso8601}),
+                        'thumbnail': ('video', 'thumbnailUrl', {url_or_none}),
+                    }),
+                }
+
+    def _real_extract(self, url):
+        course_id, lecture_id = self._match_valid_url(url).group('course_id', 'lecture_id')
+        data = self._download_json(
+            f'https://api.gamedev.tv/api/courses/my/{course_id}', course_id,
+            headers=self._API_HEADERS)['data']
+
+        course_info = traverse_obj(data, {
+            'title': ('title', {str}),
+            'tags': ('tags', ..., 'name', {str}),
+            'categories': ('categories', ..., 'title', {str}),
+            'timestamp': ('created_at', {parse_iso8601}),
+            'modified_timestamp': ('updated_at', {parse_iso8601}),
+            'thumbnail': ('image', {url_or_none}),
+        })
+
+        entries = self._entries(data, course_id, course_info, lecture_id)
+        if lecture_id:
+            lecture = next(entries, None)
+            if not lecture:
+                raise ExtractorError('Lecture not found')
+            return lecture
+        return self.playlist_result(entries, course_id, **course_info)

yt_dlp/extractor/xumo.py

@@ -0,0 +1,178 @@
+from .common import InfoExtractor
+from ..utils import determine_ext, int_or_none, smuggle_url, traverse_obj, unsmuggle_url, url_or_none
+
+
+class XumoIE(InfoExtractor):
+    _VALID_URL = r'https?://play\.?xumo\.com/[^?#]+/(?P<id>XM[A-Z0-9]{12})'
+    _TESTS = [{
+        # movie
+        'url': 'https://play.xumo.com/free-movies/a-circus-tale-and-a-love-song/XM041I5U497VD3',
+        'params': {
+            'check_formats': True,
+        },
+        'md5': 'eaac858a8db4ee5a67d6d16920c24e15',
+        'info_dict': {
+            'id': 'XM041I5U497VD3',
+            'title': 'A Circus Tale & A Love Song',
+            'ext': 'mp4',
+            'description': 'md5:aa6372f4785c528ff04c94a275f63446',
+            'duration': 6887,
+            'release_year': 2016,
+            'thumbnail': r're:^https?://.*\.jpg$',
+        },
+    }, {
+        # entire series
+        'url': 'https://play.xumo.com/tv-shows/super-mario-world/XM0AN69OG47PRN',
+        'params': {
+            'skip_download': True,
+        },
+        'playlist_count': 10,
+        'info_dict': {
+            'id': 'XM0AN69OG47PRN',
+            'title': 'Super Mario World',
+        },
+    }, {
+        # episode of series
+        'url': 'https://play.xumo.com/tv-shows/99991299/XM02D369HADFRR',
+        'md5': 'ed2f396272b39f2e0fe47f02b9ae34cc',
+        'info_dict': {
+            'id': 'XM02D369HADFRR',
+            'title': 'Fire Sale // Misadventures In Robin Hood Woods',
+            'ext': 'mp4',
+            'series': 'Super Mario World',
+            'season_number': 1,
+            'episode_number': 2,
+            'episode': 'Fire Sale // Misadventures In Robin Hood Woods',
+            'description': 'md5:48134d36781cf4b225ec0ee4f05356d3',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'season': 'Season 1',
+            'duration': 1368,
+        },
+    }, {
+        # video from network-based alternate URL scheme
+        'url': 'https://play.xumo.com/networks/fakenetworkname/99991299/XM02D369HADFRR',
+        'md5': 'ed2f396272b39f2e0fe47f02b9ae34cc',
+        'info_dict': {
+            'id': 'XM02D369HADFRR',
+            'title': 'Fire Sale // Misadventures In Robin Hood Woods',
+            'ext': 'mp4',
+            'series': 'Super Mario World',
+            'season_number': 1,
+            'episode_number': 2,
+            'episode': 'Fire Sale // Misadventures In Robin Hood Woods',
+            'description': 'md5:48134d36781cf4b225ec0ee4f05356d3',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'season': 'Season 1',
+            'duration': 1368,
+        },
+    }]
+
+    _INFO_URL = 'https://valencia-app-mds.xumo.com/v2/assets/asset/'
+    _INFO_QUERY_PARAMS = {
+        'f': [
+            'connectorId',
+            'title',
+            'providers',
+            'descriptions',
+            'runtime',
+            'originalReleaseYear',
+            'cuePoints',
+            'ratings',
+            'hasCaptions',
+            'availableSince',
+            'genres',
+            'season',
+            'episode',
+            'seasons',
+            'season:all',
+            'episodes.episodeTitle',
+            'episodes.runtime',
+            'episodes.descriptions',
+            'episodes.hasCaptions',
+            'episodes.ratings',
+        ],
+    }
+
+    def _get_video_links(self, video_id, info_json):
+        formats, subtitles = [], {}
+
+        for source in traverse_obj(info_json, ('providers', ..., 'sources', ...)) or []:
+            fmts, subs = [], {}
+
+            format_url = url_or_none(source.get('uri'))
+            if not format_url:
+                continue
+            ext = determine_ext(format_url)
+            if ext == 'm3u8':
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                    format_url, video_id, m3u8_id='hls', fatal=False)
+            elif ext == 'mpd':
+                fmts, subs = self._extract_mpd_formats_and_subtitles(
+                    format_url, video_id, mpd_id='dash', fatal=False)
+            elif format_url.endswith('.ism/Manifest'):
+                fmts, subs = self._extract_ism_formats_and_subtitles(
+                    format_url, video_id, ism_id='mss', fatal=False)
+
+            if source.get('drm'):
+                for f in fmts:
+                    f['has_drm'] = True
+
+            formats.extend(fmts)
+            subtitles = self._merge_subtitles(subtitles, subs)
+
+        for caption in traverse_obj(info_json, ('providers', ..., 'captions', ...)):
+            subtitles.setdefault(caption.get('lang') or 'und', []).append({
+                'url': caption.get('url'),
+            })
+        return formats, subtitles
+
+    def _real_extract(self, url):
+
+        url, smuggled_data = unsmuggle_url(url)
+
+        media_id = self._match_valid_url(url).group('id')
+        media_metadata = self._download_json(f'{self._INFO_URL}{media_id}.json', media_id, query=self._INFO_QUERY_PARAMS)
+
+        title = media_metadata.get('title')
+        content_type = media_metadata['contentType']
+
+        if content_type == 'SERIES':
+            # series => return set of URLs pointing to individual episodes and smuggle series title to avoid extra API call for each episode
+            return self.playlist_result([
+                self.url_result(
+                    smuggle_url(f'https://play.xumo.com/tv-shows/x/{episode["id"]}', {'series': title}),
+                    XumoIE, episode['id'], episode.get('episodeTitle'))
+                for episode in traverse_obj(media_metadata, ('seasons', ..., 'episodes', ...))
+            ], media_id, title)
+
+        # video => return video info
+
+        season_number = None
+        series_title = None
+
+        is_episode = content_type == 'EPISODIC'
+
+        if is_episode:
+            season_number = int_or_none(media_metadata.get('season'))
+            if smuggled_data:
+                series_title = traverse_obj(smuggled_data, 'series')
+            else:
+                series_data = self._download_json(f'{self._INFO_URL}{media_metadata["connectorId"]}.json', media_id, query=self._INFO_QUERY_PARAMS)
+                series_title = traverse_obj(series_data, 'title')
+
+        formats, subtitles = self._get_video_links(media_id, media_metadata)
+
+        return {
+            'id': media_id,
+            'title': title,
+            'description': traverse_obj(media_metadata, ('descriptions', ('large', 'medium', 'small', 'tiny')), get_all=False),
+            'release_year': media_metadata.get('originalReleaseYear'),
+            'duration': media_metadata.get('runtime'),
+            'thumbnail': f'https://image.xumo.com/v1/assets/asset/{media_id}/1024x576.jpg',
+            'formats': formats,
+            'subtitles': subtitles,
+            'episode_number': media_metadata.get('episode'),
+            'season_number': season_number,
+            'episode': title if is_episode else None,
+            'series': series_title,
+        }