Merge ddc7e9a1bb into be3579aaf0

Authored by: stratus-ss, bashonly

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

yt_dlp/extractor/_extractors.py

@@ -149,6 +149,7 @@ from .archiveorg import (
 from .arcpublishing import ArcPublishingIE
 from .ard import (
     ARDIE,
+    ARDAudiothekIE,
     ARDBetaMediathekIE,
     ARDMediathekCollectionIE,
 )
@@ -708,6 +709,7 @@ from .gab import (
     GabTVIE,
 )
 from .gaia import GaiaIE
+from .gamedevtv import GameDevTVDashboardIE
 from .gamejolt import (
     GameJoltCommunityIE,
     GameJoltGameIE,

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/ard.py

@@ -1,4 +1,5 @@
 import functools
+import json
 import re
 
 from .common import InfoExtractor
@@ -601,3 +602,120 @@ class ARDMediathekCollectionIE(InfoExtractor):
         return self.playlist_result(
             OnDemandPagedList(fetch_page, self._PAGE_SIZE), full_id, display_id=display_id,
             title=page_data.get('title'), description=page_data.get('synopsis'))
+
+
+class ARDAudiothekIE(InfoExtractor):
+    IE_NAME = 'ARD:audiothek'
+    _VALID_URL = r'''(?x)https://
+        (?:www\.)?ardaudiothek\.de/
+        (?:player|live|episode|(?P<playlist>sendung|serie|sammlung))/
+        (?P<display_id>(?(playlist)[^?#]+?|[^?#]+))/
+        (?P<id>[a-zA-Z0-9]+)
+        (?(playlist)/(?P<season>\d+)?/?(?:[?#]|$))'''
+
+    _TESTS = [{
+        'url': 'https://www.ardaudiothek.de/sendung/1live-caiman-club/53375276/',
+        'info_dict': {
+            'id': '53375276',
+            'title': '1LIVE Caiman Club',
+            'description': 'md5:003cff043a41b14cf045b960b89aaa86',
+        },
+        'playlist_mincount': 22,
+    }, {
+        'url': 'https://www.ardaudiothek.de/episode/1live-caiman-club/caiman-club-s04e04-cash-out/1live/13556081/',
+        'info_dict': {
+            'id': '13556081',
+            'ext': 'mp3',
+            'upload_date': '20240717',
+            'duration': 3339,
+            'title': 'CAIMAN CLUB (S04E04): Cash Out',
+            'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:d5014b612429c396',
+            'description': 'md5:8decf7974ed1cbf5a9d2c537940e1c4b',
+            'display_id': '1live-caiman-club/caiman-club-s04e04-cash-out/1live',
+            'timestamp': 1721181641,
+            'series': '1LIVE Caiman Club',
+
+        },
+    }]
+
+    _QUERY_PLAYLIST = '''\
+    show(id: "%s") {
+        title
+        description
+        items {
+            nodes {
+                url
+                episodeNumber
+                grouping
+                isPublished
+            }
+        }
+    }'''
+
+    _QUERY_ITEM = '''\
+    item(id: "%s") {
+        audioList {
+            href
+            distributionType
+        }
+        show {
+          title
+        }
+        image {
+          url
+        }
+        synopsis
+        title
+        duration
+        startDate
+    }'''
+
+    _GRAPHQL_ENDPOINT = 'https://api.ardaudiothek.de/graphql'
+
+    def _graphql_query(self, display_id, query):
+        return self._download_json(
+            self._GRAPHQL_ENDPOINT,
+            display_id,
+            data=json.dumps({'query': '{' + query + '}'}).encode(),
+            headers={
+                'Content-Type': 'application/json',
+            },
+        )['data']
+
+    def _real_extract(self, url):
+        video_id, display_id, playlist_type, season_number = self._match_valid_url(url).group(
+            'id', 'display_id', 'playlist', 'season')
+        if re.match('^[/-]*$', display_id):
+            display_id = video_id
+
+        if playlist_type:
+            playlist_info = self.graphql_query(display_id, self._QUERY_PLAYLIST % video_id)['show']
+            episodes = playlist_info['items']['nodes']
+            entries = []
+            for episode in episodes:
+                if episode['isPublished']:
+                    entries.append(self.url_result(
+                        episode['url'],
+                        ie=ARDAudiothekIE.ie_key()))
+            return self.playlist_result(entries, video_id, playlist_title=display_id, **traverse_obj(playlist_info, {
+                'title': ('title', {str}),
+                'description': ('description', {str}),
+            }))
+
+        return {
+            'display_id': display_id,
+            'formats': traverse_obj(self.graphql_query(display_id, self._QUERY_ITEM % video_id), (
+                'item', 'audioList', lambda _, v: url_or_none(v['href']), {
+                    'url': 'href',
+                    'format_id': ('distributionType', {str}),
+            })),
+            'id': video_id,
+            **traverse_obj(item, {
+                'description': ('synopsis', {str}),
+                'duration': ('duration', {int_or_none}),
+                'series': ('show', 'title'),
+                'thumbnail': ('image', 'url', {url_or_none}),
+                'timestamp': ('startDate', {parse_iso8601}),
+                'title': ('title', {str}),
+            }),
+        }

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)