Merge 10003ccacf into be3579aaf0

Authored by: stratus-ss, bashonly

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

yt_dlp/extractor/_extractors.py

@@ -682,6 +682,7 @@ from .francetv import (
     FranceTVIE,
     FranceTVInfoIE,
     FranceTVSiteIE,
+    FranceTVSiteShowIE,
 )
 from .freesound import FreesoundIE
 from .freespeech import FreespeechIE
@@ -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/francetv.py

@@ -449,3 +449,92 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor):
             webpage, 'video id')
 
         return self._make_url_result(video_id, url=url)
+
+
+class FranceTVSiteShowIE(FranceTVBaseInfoExtractor):
+    IE_NAME = 'FranceTVSite:playlist'
+    _VALID_URL = r'''(?x)
+    https?://(?:(?:www\.)?france\.tv|mobile\.france\.tv)/
+    (?:[^/]+)/(?P<id>[^/]+)/
+    (?:toutes-les-videos|saison-(?P<season_number>\d+))/?$'''
+
+    _TESTS = [{
+        'url': 'https://www.france.tv/france-3/wakfu/saison-1/',
+        'info_dict': {
+            'id': 'Wakfu Season 1',
+            'title': 'Wakfu',
+            'description': 'md5:7d34b24a7fdde32da265bf01580803c3',
+        },
+        'playlist_count': 26,
+    }, {
+        'url': 'https://www.france.tv/france-2/dix-pour-cent/toutes-les-videos/',
+        'info_dict': {
+            'id': 'Dix pour Cent All available videos',
+            'title': 'Dix pour Cent',
+        },
+        'playlist_mincount': 24,
+    }, {
+        'url': 'https://www.france.tv/france-2/drag-race-france/toutes-les-videos/',
+        'info_dict': {
+            'id': 'Drag Race France All available videos',
+            'title': 'Drag Race France',
+        },
+        'playlist_mincount': 32,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        url_groups = self._match_valid_url(url).groupdict()
+        is_seasons_url = url_groups.get('season_number') is not None
+        info_dict = {}
+
+        if is_seasons_url:
+            display_title = self._search_regex(
+                r'<div\s*class=(["\'])c-hero-banner-program__data-description\1\s*><h1\s*class=\1c-headlines\1\s*>(?P<display_title>[^<]+)</h1\s*></div\s*>',
+                webpage, name='display_title', group='display_title')
+            display_title = display_title.split('-')[0].strip()
+            internal_id = f'{display_title} Season {url_groups["season_number"]}'
+            info_dict['playlist_description'] = self._search_regex(
+                r'<div\s*class=(["\'])c-hero-banner-program__data-synopsis\1\s*>(?P<series_description>[^<]+)</div\s*>',
+                webpage, name='series_description', group='series_description', default=None).strip()
+        else:
+            display_title = self._search_regex(
+                r'<h1\s*class=(["\'])c-headlines\s*c-page-title\s*c-headlines--title-1\1\s*>(?P<display_title>[^<]+)</h1\s*>',
+                webpage, name='display_title', group='display_title').strip()
+            internal_id = f'{display_title} All available videos'
+
+        info_dict['playlist_id'] = internal_id
+        info_dict['playlist_title'] = display_title
+
+        def entries():
+            # The page contains only the first videos, some calls must be made to ge the complete video list
+            (more_base_url, current_page, more_page_number) = self._search_regex(
+                r'''(?x)
+                (?:data-current-page\s*=)\s*(["\'])(?P<current_page>(?:(?!\1).)+)\1\s*
+                (?:data-url\s*=)\s*\1(?P<more_base_url>(?:(?!\1).)+)\1\s*
+                (?:data-max-page\s*=)\s*\1(?P<more_page_number>(?:(?!\1).)+)\1''',
+                webpage, 'more_base_url', group=['more_base_url', 'current_page', 'more_page_number'])
+
+            parsed_url = urllib.parse.urlparse(url)
+            (scheme, netloc, _, _, _, _) = parsed_url
+
+            videos_list = ''.join([
+                self._download_webpage(f'{scheme}://{netloc}/{more_base_url}?page={page}',
+                                       f'{display_id} page {page + 1}')
+                for page in range(int(current_page), int(more_page_number) + 1)
+            ])
+
+            video_ids = [
+                match.group('id') for match in re.finditer(
+                    r'(?:data-main-video\s*=|(?:video_factory_id|videoId)["\']?\s*[:=])\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
+                    videos_list)
+            ]
+
+            for video_id in video_ids:
+                yield self.url_result(f'francetv:{video_id}', ie=FranceTVIE, video_id=video_id,
+                                      **FranceTVIE._extract_video(self, video_id, hostname=parsed_url.hostname))
+
+        return self.playlist_result(entries(), **info_dict)

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)