Merge f2767e2ce0 into be3579aaf0

Authored by: stratus-ss, bashonly

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

yt_dlp/extractor/_extractors.py

@@ -376,6 +376,7 @@ from .chaturbate import ChaturbateIE
 from .chilloutzone import ChilloutzoneIE
 from .chzzk import (
     CHZZKLiveIE,
+    CHZZKChannelIE,
     CHZZKVideoIE,
 )
 from .cinemax import CinemaxIE
@@ -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/chzzk.py

@@ -85,6 +85,91 @@ class CHZZKLiveIE(InfoExtractor):
         }
 
 
+def _make_vod_result(data):
+    assert isinstance(data, dict)
+    if not data.get('videoId'):
+        return
+    return {
+        '_type': 'url_transparent',
+        'id': data.get('videoId'),
+        'title': data.get('videoTitle'),
+        'url': f'https://chzzk.naver.com/video/{data.get("videoNo")}',
+        'thumbnail': data.get('thumbnailImageUrl'),
+        'timestamp': data.get('publishDateAt'),
+        'view_count': data.get('readCount'),
+        'duration': data.get('duration'),
+        'age_limit': 19 if data.get('adult') else 0,
+        'was_live': True if data.get('videoType') == 'REPLAY' else False,
+    }
+
+
+class CHZZKChannelIE(InfoExtractor):
+    IE_NAME = 'chzzk:channel'
+    _VALID_URL = r'https?://chzzk\.naver\.com/(?P<id>[\da-f]{32})'
+    _TESTS = [{
+        'note': 'Both video and replay included',
+        'url': 'https://chzzk.naver.com/68f895c59a1043bc5019b5e08c83a5c5',
+        'info_dict': {
+            'id': '68f895c59a1043bc5019b5e08c83a5c5',
+            'channel_id': '68f895c59a1043bc5019b5e08c83a5c5',
+            'description': '나는 머찐 라디유 나는 머찐 라디유' * 26 + '나는 라디유',
+            'channel': '라디유radiyu',
+            'title': '라디유radiyu',
+            'channel_is_verified': False,
+        },
+        'playlist_mincount': 4,
+    }, {
+        'note': 'Video list paging',
+        'url': 'https://chzzk.naver.com/2d4aa2f79b0a397d032c479ef1b37a67',
+        'info_dict': {
+            'id': '2d4aa2f79b0a397d032c479ef1b37a67',
+            'channel_id': '2d4aa2f79b0a397d032c479ef1b37a67',
+            'description': '',
+            'channel': '진짜후추',
+            'title': '진짜후추',
+            'channel_is_verified': False,
+        },
+        'playlist_mincount': 86,
+    }]
+
+    def _real_extract(self, url):
+        channel_id = self._match_id(url)
+        # even if channel got banned, the video list is still available. but downloading videos leads to error
+        channel_meta = self._download_json(
+            f'https://api.chzzk.naver.com/service/v1/channels/{channel_id}', channel_id,
+            note='Downloading channel info', errnote='Unable to download channel info')
+        if channel_meta.get('code') != 200:
+            raise ExtractorError('The channel is not available: %s(%s)' % (
+                channel_meta.get("message"), channel_meta.get("code")), expected=True)
+
+        channel_meta = channel_meta.get('content')
+        if not channel_meta or not channel_meta.get('channelId'):
+            raise ExtractorError('The channel does not exist', expected=True)
+
+        total_count = 0
+        videos = []
+        current_count = 0
+        while current_count <= total_count:
+            videos_page = self._download_json(
+                f'https://api.chzzk.naver.com/service/v1/channels/{channel_id}/videos', channel_meta['channelName'],
+                query={'sortType': 'LATEST', 'pagingType': 'PAGE', 'size': 18, 'videoType': '', 'page': current_count},
+                note='Downloading videos page(%s/%s)' % (current_count + 1, total_count + 1), errnote='Unable to download videos page')
+            if videos_page.get('code') != 200:
+                raise ExtractorError('Unable to download videos page: %s(%s){videos_page.get("message")}' % (
+                    videos_page.get("message"), videos_page.get("code")), expected=True)
+            videos_page = videos_page['content']
+            videos.extend(map(_make_vod_result, videos_page['data']))
+            total_count = videos_page['totalPages']
+            current_count += 1
+        if len(videos) != total_count:
+            self.to_screen('Warning: The total count of videos is not equal to the actual count: %s != %s' % (len(videos), total_count))
+
+        return self.playlist_result(
+            videos, channel_id, channel_meta['channelName'], channel_meta['channelDescription'],
+            channel=channel_meta['channelName'], channel_id=channel_id, channel_is_verified=channel_meta['verifiedMark'],
+        )
+
+
 class CHZZKVideoIE(InfoExtractor):
     IE_NAME = 'chzzk:video'
     _VALID_URL = r'https?://chzzk\.naver\.com/video/(?P<id>\d+)'

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)