Merge ab81421072 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,
@@ -1416,6 +1417,7 @@ from .nuum import (
 from .nuvid import NuvidIE
 from .nytimes import (
     NYTimesArticleIE,
+    NYTimesAudioIE,
     NYTimesCookingIE,
     NYTimesCookingRecipeIE,
     NYTimesIE,

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/nytimes.py

@@ -10,6 +10,7 @@ from ..utils import (
     float_or_none,
     get_elements_html_by_class,
     int_or_none,
+    js_to_json,
     merge_dicts,
     mimetype2ext,
     parse_iso8601,
@@ -418,3 +419,223 @@ class NYTimesCookingRecipeIE(InfoExtractor):
             'thumbnails': [{'url': thumb_url} for thumb_url in traverse_obj(
                 recipe_data, ('image', 'crops', 'recipe', ..., {url_or_none}))],
         }
+
+
+class NYTimesAudioIE(NYTimesBaseIE):
+    _VALID_URL = r"https?://(?:www\.)?nytimes\.com/\d{4}/\d{2}/\d{2}/(?:podcasts|books)/(?:[\w-]+/)?(?P<id>[^./?#]+)(?:\.html)?"
+    _TESTS = [
+        {
+            "url": "http://www.nytimes.com/2016/10/14/podcasts/revelations-from-the-final-weeks.html",
+            "md5": "cd402e44a059c8caf3b5f514c9264d0f",
+            "info_dict": {
+                "id": "100000004709062",
+                "title": "Revelations From the Final Weeks",
+                "ext": "mp3",
+                "description": "md5:fb5c6b93b12efc51649b4847fe066ee4",
+                "timestamp": 1476448332,
+                "upload_date": "20161014",
+                "creators": [''],
+                "series": "The Run-Up",
+                "episode": "‘He Was Like an Octopus’",
+                "episode_number": 20,
+                "duration": 2130,
+                "thumbnail": r"re:https?://\w+\.nyt.com/images/.*\.jpg",
+            },
+        },
+        {
+            "url": "https://www.nytimes.com/2023/11/25/podcasts/poultry-slam.html",
+            "info_dict": {
+                "id": "100000009191248",
+                "title": "Poultry Slam",
+                "ext": "mp3",
+                "description": "md5:1e6f16b21bb9287b8a1fe563145a72fe",
+                "timestamp": 1700911084,
+                "upload_date": "20231125",
+                "creators": [],
+                "series": "This American Life",
+                "episode": "Poultry Slam",
+                "duration": 3523,
+                "thumbnail": r"re:https?://\w+\.nyt.com/images/.*\.png",
+            },
+            "params": {
+                "skip_download": True,
+            },
+        },
+        {
+            "url": "http://www.nytimes.com/2016/10/16/books/review/inside-the-new-york-times-book-review-the-rise-of-hitler.html",
+            "info_dict": {
+                "id": "100000004709479",
+                "title": "Inside The New York Times Book Review: The Rise of Hitler",
+                "ext": "mp3",
+                "description": "md5:288161c98c098a0c24f07a94af7108c3",
+                "timestamp": 1476461513,
+                "upload_date": "20161014",
+                "creators": ['Pamela Paul'],
+                "series": "",
+                "episode": "The Rise of Hitler",
+                "duration": 3475,
+                "thumbnail": r"re:https?://\w+\.nyt.com/images/.*\.jpg",
+            },
+            "params": {
+                "skip_download": True,
+            },
+        },
+        {
+            "url": "https://www.nytimes.com/2023/12/07/podcasts/the-daily/nikki-haley.html",
+            "info_dict": {
+                "id": "100000009214128",
+                "title": "Nikki Haley’s Moment",
+                "ext": "mp3",
+                "description": "md5:bf9f532fe689967ef1c458bcb057f3e5",
+                "timestamp": 1701946819,
+                "upload_date": "20231207",
+                "creators": [],
+                "series": "The Daily",
+                "episode": "Listen to ‘The Daily’: Nikki Haley’s Moment",
+                "duration": 1908,
+            },
+            "params": {
+                "skip_download": True,
+            },
+        },
+        {
+            "url": "https://www.nytimes.com/2023/12/18/podcasts/israel-putin.html",
+            "md5": "708b4fd393ca103280fe9e56d91b08b5",
+            "info_dict": {
+                "id": "100000009227362",
+                "title": "Pressure Mounts on Israel, and Putin Profits Off Boycott",
+                "ext": "mp3",
+                "description": "Hear the news in five minutes.",
+                "timestamp": 1702897212,
+                "upload_date": "20231218",
+                "creators": [],
+                "series": "The Headlines",
+                "episode": "The Headlines",
+                "duration": 298,
+                "thumbnail": r"re:https?://\w+\.nyt.com/images/.*\.jpg",
+            },
+        },
+    ]
+
+    def _extract_content_from_block(self, block):
+        return traverse_obj(
+            block,
+            {
+                "creators": ("data", "track", "credit", all),
+                "duration": (
+                    ("data", "media"),
+                    ("track", "length"),
+                    ("duration", None),
+                    {int_or_none},
+                ),
+                "series": (
+                    ("data", "media"),
+                    ("podcast", "podcastSeries"),
+                    ("title", None),
+                    {str_or_none},
+                ),
+                "episode": (
+                    ("data", "media"),
+                    ("track", "headline"),
+                    ("title", "default"), {str}),
+                "episode_number": (
+                    "data",
+                    "podcast",
+                    "episode",
+                    {lambda v: v.split()[1]},
+                    {int_or_none},
+                ),
+                "url": (
+                    ("data", "media"),
+                    ("track", "fileUrl"),
+                    ("source", None),
+                    {url_or_none},
+                ),
+                "vcodec": "none",
+            },
+            get_all=False,
+        )
+
+    def _real_extract(self, url):
+        page_id = self._match_id(url)
+        webpage = self._download_webpage(url, page_id)
+
+        art_json = self._search_json(
+            r"window\.__preloadedData\s*=",
+            webpage,
+            "media details",
+            page_id,
+            transform_source=js_to_json,
+        )["initialData"]["data"]["article"]
+
+        blocks = traverse_obj(
+            art_json,
+            (
+                "sprinkledBody",
+                "content",
+                lambda _, v: v["__typename"]
+                in ("InteractiveBlock", "HeaderMultimediaBlock"),
+                "media",
+            ),
+        )
+        if not blocks:
+            raise ExtractorError("Unable to extract any media blocks from webpage")
+
+        common_info = {
+            "title": remove_end(
+                self._html_extract_title(webpage), " - The New York Times"
+            ),
+            "description": self._html_search_meta(
+                ["og:description", "twitter:description"], webpage
+            ),
+            "id": traverse_obj(
+                art_json, ("sourceId")
+            ),  # poltry slam is under art_json > 'sourceId'
+            **traverse_obj(
+                art_json,
+                {
+                    "id": (
+                        "sprinkledBody",
+                        "content",
+                        ...,
+                        "media",
+                        "sourceId",
+                        any,
+                        {str},
+                    ),
+                    "title": ("headline", "default"),
+                    "description": ("summary"),
+                    "timestamp": ("firstPublished", {parse_iso8601}),
+                    "thumbnails": (
+                        "promotionalMedia",
+                        "assetCrops",
+                        ...,
+                        "renditions",
+                        ...,
+                        all,
+                        {self._extract_thumbnails},
+                    ),
+                },
+            ),
+        }
+
+        entries = []
+        for block in blocks:
+            if block.get("html"):
+                block = self._search_json(
+                    r"function\s+getFlexData\(\)\s*\{\s*return",
+                    block.get("html"),
+                    "Retrieve the inner JSON",
+                    page_id,
+                )
+            entries.append(
+                merge_dicts(self._extract_content_from_block(block), common_info)
+            )
+
+        if len(entries) > 1:
+            return self.playlist_result(entries, page_id, **common_info)
+
+        return {
+            "id": page_id,
+            **entries[0],
+        }