Merge 506966d1e8 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,
@@ -2409,6 +2410,10 @@ from .washingtonpost import (
     WashingtonPostIE,
 )
 from .wat import WatIE
+from .watchertv import (
+    WatcherTVIE,
+    WatcherTVSeasonIE,
+)
 from .wdr import (
     WDRIE,
     WDRElefantIE,

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/dropout.py

@@ -17,83 +17,12 @@ from ..utils import (
 )
 
 
-class DropoutIE(InfoExtractor):
+class DropoutBaseIE(InfoExtractor):
-    _LOGIN_URL = 'https://www.dropout.tv/login'
+    """Subclasses must define _HOST"""
-    _NETRC_MACHINE = 'dropout'
-
-    _VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?:[^/]+/)*videos/(?P<id>[^/]+)/?$'
-    _TESTS = [
-        {
-            'url': 'https://www.dropout.tv/game-changer/season:2/videos/yes-or-no',
-            'note': 'Episode in a series',
-            'md5': '5e000fdfd8d8fa46ff40456f1c2af04a',
-            'info_dict': {
-                'id': '738153',
-                'display_id': 'yes-or-no',
-                'ext': 'mp4',
-                'title': 'Yes or No',
-                'description': 'Ally, Brennan, and Zac are asked a simple question, but is there a correct answer?',
-                'release_date': '20200508',
-                'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/351e3f24-c4a3-459a-8b79-dc80f1e5b7fd.jpg',
-                'series': 'Game Changer',
-                'season_number': 2,
-                'season': 'Season 2',
-                'episode_number': 6,
-                'episode': 'Yes or No',
-                'duration': 1180,
-                'uploader_id': 'user80538407',
-                'uploader_url': 'https://vimeo.com/user80538407',
-                'uploader': 'OTT Videos',
-            },
-            'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
-        },
-        {
-            'url': 'https://www.dropout.tv/dimension-20-fantasy-high/season:1/videos/episode-1',
-            'note': 'Episode in a series (missing release_date)',
-            'md5': '712caf7c191f1c47c8f1879520c2fa5c',
-            'info_dict': {
-                'id': '320562',
-                'display_id': 'episode-1',
-                'ext': 'mp4',
-                'title': 'The Beginning Begins',
-                'description': 'The cast introduces their PCs, including a neurotic elf, a goblin PI, and a corn-worshipping cleric.',
-                'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/4421ed0d-f630-4c88-9004-5251b2b8adfa.jpg',
-                'series': 'Dimension 20: Fantasy High',
-                'season_number': 1,
-                'season': 'Season 1',
-                'episode_number': 1,
-                'episode': 'The Beginning Begins',
-                'duration': 6838,
-                'uploader_id': 'user80538407',
-                'uploader_url': 'https://vimeo.com/user80538407',
-                'uploader': 'OTT Videos',
-            },
-            'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
-        },
-        {
-            'url': 'https://www.dropout.tv/videos/misfits-magic-holiday-special',
-            'note': 'Episode not in a series',
-            'md5': 'c30fa18999c5880d156339f13c953a26',
-            'info_dict': {
-                'id': '1915774',
-                'display_id': 'misfits-magic-holiday-special',
-                'ext': 'mp4',
-                'title': 'Misfits & Magic Holiday Special',
-                'description': 'The magical misfits spend Christmas break at Gowpenny, with an unwelcome visitor.',
-                'release_date': '20211215',
-                'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/d91ea8a6-b250-42ed-907e-b30fb1c65176-8e24b8e5.jpg',
-                'duration': 11698,
-                'uploader_id': 'user80538407',
-                'uploader_url': 'https://vimeo.com/user80538407',
-                'uploader': 'OTT Videos',
-            },
-            'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
-        },
-    ]
 
     def _get_authenticity_token(self, display_id):
         signin_page = self._download_webpage(
-            self._LOGIN_URL, display_id, note='Getting authenticity token')
+            f'{self._HOST}/login', display_id, note='Getting authenticity token')
         return self._html_search_regex(
             r'name=["\']authenticity_token["\'] value=["\'](.+?)["\']',
             signin_page, 'authenticity_token')
@@ -104,7 +33,7 @@ class DropoutIE(InfoExtractor):
             return True
 
         response = self._download_webpage(
-            self._LOGIN_URL, display_id, note='Logging in', fatal=False,
+            f'{self._HOST}/login', display_id, note='Logging in', fatal=False,
             data=urlencode_postdata({
                 'email': username,
                 'password': password,
@@ -125,7 +54,7 @@ class DropoutIE(InfoExtractor):
         display_id = self._match_id(url)
 
         webpage = None
-        if self._get_cookies('https://www.dropout.tv').get('_session'):
+        if self._get_cookies(self._HOST).get('_session'):
             webpage = self._download_webpage(url, display_id)
         if not webpage or '<div id="watch-unauthorized"' in webpage:
             login_err = self._login(display_id)
@@ -148,7 +77,7 @@ class DropoutIE(InfoExtractor):
         return {
             '_type': 'url_transparent',
             'ie_key': VHXEmbedIE.ie_key(),
-            'url': VHXEmbedIE._smuggle_referrer(embed_url, 'https://www.dropout.tv'),
+            'url': VHXEmbedIE._smuggle_referrer(embed_url, self._HOST),
             'id': self._search_regex(r'embed\.vhx\.tv/videos/(.+?)\?', embed_url, 'id'),
             'display_id': display_id,
             'title': title,
@@ -165,9 +94,105 @@ class DropoutIE(InfoExtractor):
         }
 
 
-class DropoutSeasonIE(InfoExtractor):
+class DropoutIE(DropoutBaseIE):
+    _HOST = 'https://www.dropout.tv'
+    _NETRC_MACHINE = 'dropout'
+
+    _VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?:[^/]+/)*videos/(?P<id>[^/]+)/?$'
+    _TESTS = [
+        {
+            'url': 'https://www.dropout.tv/game-changer/season:2/videos/yes-or-no',
+            'note': 'Episode in a series',
+            'md5': 'fc55805bac60b1ce2ffdc35fb9c51195',
+            'info_dict': {
+                'id': '738153',
+                'display_id': 'yes-or-no',
+                'ext': 'mp4',
+                'title': 'Yes or No',
+                'description': 'Ally, Brennan, and Zac are asked a simple question, but is there a correct answer?',
+                'release_date': '20200508',
+                'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/351e3f24-c4a3-459a-8b79-dc80f1e5b7fd.jpg',
+                'series': 'Game Changer',
+                'season_number': 2,
+                'season': 'Season 2',
+                'episode_number': 6,
+                'episode': 'Yes or No',
+                'duration': 1180,
+                'uploader_id': 'user80538407',
+                'uploader_url': 'https://vimeo.com/user80538407',
+                'uploader': 'OTT Videos',
+            },
+            'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
+        },
+        {
+            'url': 'https://www.dropout.tv/ch-shorts/season:1/videos/post-apocalyptic-dane-cook',
+            'note': 'Episode in a series (missing release_date)',
+            'md5': 'f260b8d7d0fdbaceae713c9196dac07f',
+            'info_dict': {
+                'id': '449042',
+                'display_id': 'post-apocalyptic-dane-cook',
+                'ext': 'mp4',
+                'title': 'Post-Apocalyptic Dane Cook',
+                'description': 'Dane Cook is back with his all new special. Don\'t worry, it\'s not the end of the world.',
+                'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/5b0678df-d9c3-4864-b811-24db03072f4a.jpg',
+                'series': 'CH Shorts',
+                'season_number': 1,
+                'season': 'Season 1',
+                'episode_number': 1,
+                'episode': 'Post-Apocalyptic Dane Cook',
+                'duration': 135,
+                'uploader_id': 'user80538407',
+                'uploader_url': 'https://vimeo.com/user80538407',
+                'uploader': 'OTT Videos',
+            },
+            'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
+        },
+        {
+            'url': 'https://www.dropout.tv/videos/misfits-magic-holiday-special',
+            'note': 'Episode not in a series',
+            'md5': '147e0607bd877a791665c0b7219b512c',
+            'info_dict': {
+                'id': '1915774',
+                'display_id': 'misfits-magic-holiday-special',
+                'ext': 'mp4',
+                'title': 'Misfits & Magic Holiday Special',
+                'description': 'The magical misfits spend Christmas break at Gowpenny, with an unwelcome visitor.',
+                'release_date': '20211215',
+                'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/d91ea8a6-b250-42ed-907e-b30fb1c65176-8e24b8e5.jpg',
+                'duration': 11698,
+                'uploader_id': 'user80538407',
+                'uploader_url': 'https://vimeo.com/user80538407',
+                'uploader': 'OTT Videos',
+            },
+            'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
+        },
+    ]
+
+
+class DropoutSeasonBaseIE(InfoExtractor):
+    """Subclasses must define _VIDEO_IE"""
     _PAGE_SIZE = 24
+
+    def _fetch_page(self, url, season_id, page):
+        page += 1
+        webpage = self._download_webpage(
+            f'{url}?page={page}', season_id, note=f'Downloading page {page}', expected_status={400})
+        yield from [self.url_result(item_url, self._VIDEO_IE) for item_url in traverse_obj(
+            get_elements_html_by_class('browse-item-link', webpage), (..., {extract_attributes}, 'href'))]
+
+    def _real_extract(self, url):
+        season_id = self._match_id(url)
+        season_num = self._match_valid_url(url).group('season') or 1
+        season_title = season_id.replace('-', ' ').title()
+
+        return self.playlist_result(
+            OnDemandPagedList(functools.partial(self._fetch_page, url, season_id), self._PAGE_SIZE),
+            f'{season_id}-season-{season_num}', f'{season_title} - Season {season_num}')
+
+
+class DropoutSeasonIE(DropoutSeasonBaseIE):
     _VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?P<id>[^\/$&?#]+)(?:/?$|/season:(?P<season>[0-9]+)/?$)'
+    _VIDEO_IE = DropoutIE
     _TESTS = [
         {
             'url': 'https://www.dropout.tv/dimension-20-fantasy-high/season:1',
@@ -206,19 +231,3 @@ class DropoutSeasonIE(InfoExtractor):
             },
         },
     ]
-
-    def _fetch_page(self, url, season_id, page):
-        page += 1
-        webpage = self._download_webpage(
-            f'{url}?page={page}', season_id, note=f'Downloading page {page}', expected_status={400})
-        yield from [self.url_result(item_url, DropoutIE) for item_url in traverse_obj(
-            get_elements_html_by_class('browse-item-link', webpage), (..., {extract_attributes}, 'href'))]
-
-    def _real_extract(self, url):
-        season_id = self._match_id(url)
-        season_num = self._match_valid_url(url).group('season') or 1
-        season_title = season_id.replace('-', ' ').title()
-
-        return self.playlist_result(
-            OnDemandPagedList(functools.partial(self._fetch_page, url, season_id), self._PAGE_SIZE),
-            f'{season_id}-season-{season_num}', f'{season_title} - Season {season_num}')

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/watchertv.py

@@ -0,0 +1,110 @@
+from .dropout import DropoutBaseIE, DropoutSeasonBaseIE
+
+
+class WatcherTVIE(DropoutBaseIE):
+    _HOST = 'https://www.watchertv.com'
+    _NETRC_MACHINE = 'watchertv'
+
+    _VALID_URL = r'https?://(?:www\.)?watchertv\.com/(?:[^/]+/)*videos/(?P<id>[^/]+)/?$'
+    _TESTS = [
+        {
+            'url': 'https://www.watchertv.com/ghost-files/season:2/videos/gf-201',
+            'note': 'Episode in a series',
+            'md5': '99c9aab2cb62157467b7ef5e37266e4e',
+            'info_dict': {
+                'id': '3129338',
+                'display_id': 'gf-201',
+                'ext': 'mp4',
+                'title': 'The Death Row Poltergeists of Missouri State Penitentiary',
+                'description': 'Where Curiosity Meets Comedy',
+                'release_date': '20230825',
+                'thumbnail': 'https://vhx.imgix.net/watcherentertainment/assets/92c02f39-2ed6-4b51-9e63-1a907b82e2bc.png',
+                'series': 'Ghost Files',
+                'season_number': 2,
+                'season': 'Season 2',
+                'episode_number': 1,
+                'episode': 'The Death Row Poltergeists of Missouri State Penitentiary',
+                'duration': 3853,
+                'uploader_id': 'user80538407',
+                'uploader_url': 'https://vimeo.com/user80538407',
+                'uploader': 'OTT Videos',
+            },
+            'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
+        },
+        {
+            'url': 'https://www.watchertv.com/road-files/season:1/videos/rf101',
+            'note': 'Episode in a series (missing release_date)',
+            'md5': '02f9aaafc8ad9bd1be366cf6a61a68d8',
+            'info_dict': {
+                'id': '3187312',
+                'display_id': 'rf101',
+                'ext': 'mp4',
+                'title': 'Road Files: Haunted Hill House',
+                'description': 'Where Curiosity Meets Comedy',
+                'thumbnail': 'https://vhx.imgix.net/watcherentertainment/assets/7445f23c-a3e7-47fb-835a-d288273e2698.png',
+                'series': 'Road Files',
+                'season_number': 1,
+                'season': 'Season 1',
+                'episode_number': 1,
+                'episode': 'Road Files: Haunted Hill House',
+                'duration': 516,
+                'uploader_id': 'user80538407',
+                'uploader_url': 'https://vimeo.com/user80538407',
+                'uploader': 'OTT Videos',
+            },
+            'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
+        },
+        {
+            'url': 'https://www.watchertv.com/videos/welcome-beta-users',
+            'note': 'Episode not in a series',
+            'md5': 'fd1db805f9adc442c38d706bba21ad03',
+            'info_dict': {
+                'id': '3187107',
+                'display_id': 'welcome-beta-users',
+                'ext': 'mp4',
+                'title': 'Welcome to Watcher!',
+                'description': 'Where Curiosity Meets Comedy',
+                'release_date': '20240419',
+                'thumbnail': 'https://vhx.imgix.net/watcherentertainment/assets/fbb90dc8-ebb0-4597-9a83-95729e234030.jpg',
+                'duration': 92,
+                'uploader_id': 'user80538407',
+                'uploader_url': 'https://vimeo.com/user80538407',
+                'uploader': 'OTT Videos',
+            },
+            'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
+        },
+    ]
+
+
+class WatcherTVSeasonIE(DropoutSeasonBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?watchertv\.com/(?P<id>[^\/$&?#]+)(?:/?$|/season:(?P<season>[0-9]+)/?$)'
+    _VIDEO_IE = WatcherTVIE
+    _TESTS = [
+        {
+            'url': 'https://www.watchertv.com/ghost-files/season:1',
+            'note': 'Multi-season series with the season in the url',
+            'playlist_count': 8,
+            'info_dict': {
+                'id': 'ghost-files-season-1',
+                'title': 'Ghost Files - Season 1',
+            },
+        },
+        {
+            'url': 'https://www.watchertv.com/are-you-scared',
+            'note': 'Multi-season series with the season not in the url',
+            'playlist_count': 3,
+            'info_dict': {
+                'id': 'are-you-scared-season-1',
+                'title': 'Are You Scared - Season 1',
+            },
+        },
+        {
+            'url': 'https://www.watchertv.com/watcher-one-offs',
+            'note': 'Single-season series',
+            'playlist_count': 16,
+            'info_dict': {
+                'id': 'watcher-one-offs-season-1',
+                'title': 'Watcher One Offs - Season 1',
+            },
+        },
+    ]