[ie/eplus] Add login support and DRM detection (#8661)

Authored by: pzhlkj6612

README.md

@@ -1333,6 +1333,7 @@ The available fields are:
  - `was_live` (boolean): Whether this video was originally a live stream
  - `playable_in_embed` (string): Whether this video is allowed to play in embedded players on other sites
  - `availability` (string): Whether the video is "private", "premium_only", "subscriber_only", "needs_auth", "unlisted" or "public"
+ - `media_type` (string): The type of media as classified by the site, e.g. "episode", "clip", "trailer"
  - `start_time` (numeric): Time in seconds where the reproduction should start, as specified in the URL
  - `end_time` (numeric): Time in seconds where the reproduction should end, as specified in the URL
  - `extractor` (string): Name of the extractor

yt_dlp/extractor/aenetworks.py

@@ -121,11 +121,21 @@ class AENetworksIE(AENetworksBaseIE):
         'info_dict': {
             'id': '22253814',
             'ext': 'mp4',
-            'title': 'Winter is Coming',
-            'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
+            'title': 'Winter Is Coming',
+            'description': 'md5:a40e370925074260b1c8a633c632c63a',
             'timestamp': 1338306241,
             'upload_date': '20120529',
             'uploader': 'AENE-NEW',
+            'duration': 2592.0,
+            'thumbnail': r're:^https?://.*\.jpe?g$',
+            'chapters': 'count:5',
+            'tags': 'count:14',
+            'categories': ['Mountain Men'],
+            'episode_number': 1,
+            'episode': 'Episode 1',
+            'season': 'Season 1',
+            'season_number': 1,
+            'series': 'Mountain Men',
         },
         'params': {
             # m3u8 download
@@ -143,6 +153,15 @@ class AENetworksIE(AENetworksBaseIE):
             'timestamp': 1452634428,
             'upload_date': '20160112',
             'uploader': 'AENE-NEW',
+            'duration': 1277.695,
+            'thumbnail': r're:^https?://.*\.jpe?g$',
+            'chapters': 'count:4',
+            'tags': 'count:23',
+            'episode': 'Episode 1',
+            'episode_number': 1,
+            'season': 'Season 9',
+            'season_number': 9,
+            'series': 'Duck Dynasty',
         },
         'params': {
             # m3u8 download

yt_dlp/extractor/bitchute.py

@@ -7,8 +7,10 @@ from ..utils import (
     ExtractorError,
     OnDemandPagedList,
     clean_html,
+    extract_attributes,
     get_element_by_class,
     get_element_by_id,
+    get_element_html_by_class,
     get_elements_html_by_class,
     int_or_none,
     orderedSet,
@@ -17,6 +19,7 @@ from ..utils import (
     traverse_obj,
     unified_strdate,
     urlencode_postdata,
+    urljoin,
 )
 
 
@@ -34,6 +37,25 @@ class BitChuteIE(InfoExtractor):
             'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'BitChute',
             'upload_date': '20170103',
+            'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
+            'channel': 'BitChute',
+            'channel_url': 'https://www.bitchute.com/channel/bitchute/'
+        },
+    }, {
+        # test case: video with different channel and uploader
+        'url': 'https://www.bitchute.com/video/Yti_j9A-UZ4/',
+        'md5': 'f10e6a8e787766235946d0868703f1d0',
+        'info_dict': {
+            'id': 'Yti_j9A-UZ4',
+            'ext': 'mp4',
+            'title': 'Israel at War | Full Measure',
+            'description': 'md5:38cf7bc6f42da1a877835539111c69ef',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'sharylattkisson',
+            'upload_date': '20231106',
+            'uploader_url': 'https://www.bitchute.com/profile/9K0kUWA9zmd9/',
+            'channel': 'Full Measure with Sharyl Attkisson',
+            'channel_url': 'https://www.bitchute.com/channel/sharylattkisson/'
         },
     }, {
         # video not downloadable in browser, but we can recover it
@@ -48,6 +70,9 @@ class BitChuteIE(InfoExtractor):
             'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'BitChute',
             'upload_date': '20181113',
+            'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
+            'channel': 'BitChute',
+            'channel_url': 'https://www.bitchute.com/channel/bitchute/'
         },
         'params': {'check_formats': None},
     }, {
@@ -99,6 +124,11 @@ class BitChuteIE(InfoExtractor):
             reason = clean_html(get_element_by_id('page-detail', webpage)) or page_title
             self.raise_geo_restricted(reason)
 
+    @staticmethod
+    def _make_url(html):
+        path = extract_attributes(get_element_html_by_class('spa', html) or '').get('href')
+        return urljoin('https://www.bitchute.com', path)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(
@@ -121,12 +151,19 @@ class BitChuteIE(InfoExtractor):
                 'Video is unavailable. Please make sure this video is playable in the browser '
                 'before reporting this issue.', expected=True, video_id=video_id)
 
+        details = get_element_by_class('details', webpage) or ''
+        uploader_html = get_element_html_by_class('creator', details) or ''
+        channel_html = get_element_html_by_class('name', details) or ''
+
         return {
             'id': video_id,
             'title': self._html_extract_title(webpage) or self._og_search_title(webpage),
             'description': self._og_search_description(webpage, default=None),
             'thumbnail': self._og_search_thumbnail(webpage),
-            'uploader': clean_html(get_element_by_class('owner', webpage)),
+            'uploader': clean_html(uploader_html),
+            'uploader_url': self._make_url(uploader_html),
+            'channel': clean_html(channel_html),
+            'channel_url': self._make_url(channel_html),
             'upload_date': unified_strdate(self._search_regex(
                 r'at \d+:\d+ UTC on (.+?)\.', publish_date, 'upload date', fatal=False)),
             'formats': formats,
@@ -154,6 +191,9 @@ class BitChuteChannelIE(InfoExtractor):
                     'thumbnail': r're:^https?://.*\.jpg$',
                     'uploader': 'BitChute',
                     'upload_date': '20170103',
+                    'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
+                    'channel': 'BitChute',
+                    'channel_url': 'https://www.bitchute.com/channel/bitchute/',
                     'duration': 16,
                     'view_count': int,
                 },
@@ -169,7 +209,7 @@ class BitChuteChannelIE(InfoExtractor):
         'info_dict': {
             'id': 'wV9Imujxasw9',
             'title': 'Bruce MacDonald and "The Light of Darkness"',
-            'description': 'md5:04913227d2714af1d36d804aa2ab6b1e',
+            'description': 'md5:747724ef404eebdfc04277714f81863e',
         }
     }]
 

yt_dlp/extractor/cbc.py

@@ -180,6 +180,13 @@ class CBCPlayerIE(InfoExtractor):
             'thumbnail': 'http://thumbnails.cbc.ca/maven_legacy/thumbnails/sonali-karnick-220.jpg',
             'chapters': [],
             'duration': 494.811,
+            'categories': ['AudioMobile/All in a Weekend Montreal'],
+            'tags': 'count:8',
+            'location': 'Quebec',
+            'series': 'All in a Weekend Montreal',
+            'season': 'Season 2015',
+            'season_number': 2015,
+            'media_type': 'Excerpt',
         },
     }, {
         'url': 'http://www.cbc.ca/player/play/2164402062',
@@ -195,25 +202,37 @@ class CBCPlayerIE(InfoExtractor):
             'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/277/67/cancer_852x480_2164412612.jpg',
             'chapters': [],
             'duration': 186.867,
+            'series': 'CBC News: Windsor at 6:00',
+            'categories': ['News/Canada/Windsor'],
+            'location': 'Windsor',
+            'tags': ['cancer'],
+            'creator': 'Allison Johnson',
+            'media_type': 'Excerpt',
         },
     }, {
         # Has subtitles
         # These broadcasts expire after ~1 month, can find new test URL here:
         # https://www.cbc.ca/player/news/TV%20Shows/The%20National/Latest%20Broadcast
-        'url': 'http://www.cbc.ca/player/play/2249992771553',
-        'md5': '2f2fb675dd4f0f8a5bb7588d1b13bacd',
+        'url': 'http://www.cbc.ca/player/play/2284799043667',
+        'md5': '9b49f0839e88b6ec0b01d840cf3d42b5',
         'info_dict': {
-            'id': '2249992771553',
+            'id': '2284799043667',
             'ext': 'mp4',
-            'title': 'The National | Women’s soccer pay, Florida seawater, Swift quake',
-            'description': 'md5:adba28011a56cfa47a080ff198dad27a',
-            'timestamp': 1690596000,
-            'duration': 2716.333,
+            'title': 'The National | Hockey coach charged, Green grants, Safer drugs',
+            'description': 'md5:84ef46321c94bcf7d0159bb565d26bfa',
+            'timestamp': 1700272800,
+            'duration': 2718.833,
             'subtitles': {'eng': [{'ext': 'vtt', 'protocol': 'm3u8_native'}]},
-            'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/481/326/thumbnail.jpeg',
+            'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/907/171/thumbnail.jpeg',
             'uploader': 'CBCC-NEW',
             'chapters': 'count:5',
-            'upload_date': '20230729',
+            'upload_date': '20231118',
+            'categories': 'count:4',
+            'series': 'The National - Full Show',
+            'tags': 'count:1',
+            'creator': 'News',
+            'location': 'Canada',
+            'media_type': 'Full Program',
         },
     }]
 

yt_dlp/extractor/common.py

@@ -382,6 +382,7 @@ class InfoExtractor:
                     'private', 'premium_only', 'subscriber_only', 'needs_auth',
                     'unlisted' or 'public'. Use 'InfoExtractor._availability'
                     to set it
+    media_type:     The type of media as classified by the site, e.g. "episode", "clip", "trailer"
     _old_archive_ids: A list of old archive ids needed for backward compatibility
     _format_sort_fields: A list of fields to use for sorting formats
     __post_extractor: A function to be called just before the metadata is

yt_dlp/extractor/cwtv.py

@@ -46,6 +46,10 @@ class CWTVIE(InfoExtractor):
             'timestamp': 1444107300,
             'age_limit': 14,
             'uploader': 'CWTV',
+            'thumbnail': r're:^https?://.*\.jpe?g$',
+            'chapters': 'count:4',
+            'episode': 'Episode 20',
+            'season': 'Season 11',
         },
         'params': {
             # m3u8 download

yt_dlp/extractor/eplus.py

@@ -1,15 +1,20 @@
+import json
+
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     try_call,
     unified_timestamp,
+    urlencode_postdata,
 )
 
 
 class EplusIbIE(InfoExtractor):
-    IE_NAME = 'eplus:inbound'
-    IE_DESC = 'e+ (イープラス) overseas'
-    _VALID_URL = r'https?://live\.eplus\.jp/ex/player\?ib=(?P<id>(?:\w|%2B|%2F){86}%3D%3D)'
+    _NETRC_MACHINE = 'eplus'
+    IE_NAME = 'eplus'
+    IE_DESC = 'e+ (イープラス)'
+    _VALID_URL = [r'https?://live\.eplus\.jp/ex/player\?ib=(?P<id>(?:\w|%2B|%2F){86}%3D%3D)',
+                  r'https?://live\.eplus\.jp/(?P<id>sample|\d+)']
     _TESTS = [{
         'url': 'https://live.eplus.jp/ex/player?ib=YEFxb3Vyc2Dombnjg7blkrLlrablnJLjgrnjgq%2Fjg7zjg6vjgqLjgqTjg4njg6vlkIzlpb3kvJpgTGllbGxhIQ%3D%3D',
         'info_dict': {
@@ -29,14 +34,97 @@ class EplusIbIE(InfoExtractor):
             'No video formats found!',
             'Requested format is not available',
         ],
+    }, {
+        'url': 'https://live.eplus.jp/sample',
+        'info_dict': {
+            'id': 'stream1ng20210719-test-005',
+            'title': 'Online streaming test for DRM',
+            'live_status': 'was_live',
+            'release_date': '20210719',
+            'release_timestamp': 1626703200,
+            'description': None,
+        },
+        'params': {
+            'skip_download': True,
+            'ignore_no_formats_error': True,
+        },
+        'expected_warnings': [
+            'Could not find the playlist URL. This event may not be accessible',
+            'No video formats found!',
+            'Requested format is not available',
+            'This video is DRM protected',
+        ],
+    }, {
+        'url': 'https://live.eplus.jp/2053935',
+        'info_dict': {
+            'id': '331320-0001-001',
+            'title': '丘みどり2020配信LIVE Vol.2 ～秋麗～ 【Streaming+(配信チケット)】',
+            'live_status': 'was_live',
+            'release_date': '20200920',
+            'release_timestamp': 1600596000,
+        },
+        'params': {
+            'skip_download': True,
+            'ignore_no_formats_error': True,
+        },
+        'expected_warnings': [
+            'Could not find the playlist URL. This event may not be accessible',
+            'No video formats found!',
+            'Requested format is not available',
+        ],
     }]
 
+    _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36 Edg/119.0.0.0'
+
+    def _login(self, username, password, urlh):
+        if not self._get_cookies('https://live.eplus.jp/').get('ci_session'):
+            raise ExtractorError('Unable to get ci_session cookie')
+
+        cltft_token = urlh.headers.get('X-CLTFT-Token')
+        if not cltft_token:
+            raise ExtractorError('Unable to get X-CLTFT-Token')
+        self._set_cookie('live.eplus.jp', 'X-CLTFT-Token', cltft_token)
+
+        login_json = self._download_json(
+            'https://live.eplus.jp/member/api/v1/FTAuth/idpw', None,
+            note='Sending pre-login info', errnote='Unable to send pre-login info', headers={
+                'Content-Type': 'application/json; charset=UTF-8',
+                'Referer': urlh.url,
+                'X-Cltft-Token': cltft_token,
+                'Accept': '*/*',
+            }, data=json.dumps({
+                'loginId': username,
+                'loginPassword': password,
+            }).encode())
+        if not login_json.get('isSuccess'):
+            raise ExtractorError('Login failed: Invalid id or password', expected=True)
+
+        self._request_webpage(
+            urlh.url, None, note='Logging in', errnote='Unable to log in',
+            data=urlencode_postdata({
+                'loginId': username,
+                'loginPassword': password,
+                'Token.Default': cltft_token,
+                'op': 'nextPage',
+            }), headers={'Referer': urlh.url})
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        webpage, urlh = self._download_webpage_handle(
+            url, video_id, headers={'User-Agent': self._USER_AGENT})
+        if urlh.url.startswith('https://live.eplus.jp/member/auth'):
+            username, password = self._get_login_info()
+            if not username:
+                self.raise_login_required()
+            self._login(username, password, urlh)
+            webpage = self._download_webpage(
+                url, video_id, headers={'User-Agent': self._USER_AGENT})
 
         data_json = self._search_json(r'<script>\s*var app\s*=', webpage, 'data json', video_id)
 
+        if data_json.get('drm_mode') == 'ON':
+            self.report_drm(video_id)
+
         delivery_status = data_json.get('delivery_status')
         archive_mode = data_json.get('archive_mode')
         release_timestamp = try_call(lambda: unified_timestamp(data_json['event_datetime']) - 32400)
@@ -64,7 +152,7 @@ class EplusIbIE(InfoExtractor):
         formats = []
 
         m3u8_playlist_urls = self._search_json(
-            r'var listChannels\s*=', webpage, 'hls URLs', video_id, contains_pattern=r'\[.+\]', default=[])
+            r'var\s+listChannels\s*=', webpage, 'hls URLs', video_id, contains_pattern=r'\[.+\]', default=[])
         if not m3u8_playlist_urls:
             if live_status == 'is_upcoming':
                 self.raise_no_formats(

yt_dlp/extractor/mediaset.py

@@ -73,6 +73,7 @@ class MediasetIE(ThePlatformBaseIE):
             'season_number': 5,
             'episode_number': 5,
             'chapters': [{'start_time': 0.0, 'end_time': 3409.08}, {'start_time': 3409.08, 'end_time': 6565.008}],
+            'categories': ['Informazione'],
         },
     }, {
         # DRM
@@ -149,6 +150,7 @@ class MediasetIE(ThePlatformBaseIE):
             'season_number': 12,
             'episode': 'Episode 8',
             'episode_number': 8,
+            'categories': ['Intrattenimento'],
         },
         'params': {
             'skip_download': True,

yt_dlp/extractor/nbc.py

@@ -53,6 +53,8 @@ class NBCIE(ThePlatformIE):  # XXX: Do not subclass from concrete IE
                 'chapters': 'count:1',
                 'tags': 'count:4',
                 'thumbnail': r're:https?://.+\.jpg',
+                'categories': ['Series/The Tonight Show Starring Jimmy Fallon'],
+                'media_type': 'Full Episode',
             },
             'params': {
                 'skip_download': 'm3u8',
@@ -131,6 +133,8 @@ class NBCIE(ThePlatformIE):  # XXX: Do not subclass from concrete IE
                 'tags': 'count:10',
                 'age_limit': 0,
                 'thumbnail': r're:https?://.+\.jpg',
+                'categories': ['Series/Quantum Leap 2022'],
+                'media_type': 'Highlight',
             },
             'params': {
                 'skip_download': 'm3u8',

yt_dlp/extractor/scrippsnetworks.py

@@ -114,6 +114,8 @@ class ScrippsNetworksIE(InfoExtractor):
             'timestamp': 1475678834,
             'upload_date': '20161005',
             'uploader': 'SCNI-SCND',
+            'tags': 'count:10',
+            'creator': 'Cooking Channel',
             'duration': 29.995,
             'chapters': [{'start_time': 0.0, 'end_time': 29.995, 'title': '<Untitled Chapter 1>'}],
             'thumbnail': 'https://images.dds.discovery.com/up/tp/Scripps_-_Food_Category_Prod/122/987/0260338_630x355.jpg',

yt_dlp/extractor/theplatform.py

@@ -104,6 +104,10 @@ class ThePlatformBaseIE(OnceIE):
                 _add_chapter(chapter.get('startTime'), chapter.get('endTime'))
             _add_chapter(tp_chapters[-1].get('startTime'), tp_chapters[-1].get('endTime') or duration)
 
+        def extract_site_specific_field(field):
+            # A number of sites have custom-prefixed keys, e.g. 'cbc$seasonNumber'
+            return traverse_obj(info, lambda k, v: v and k.endswith(f'${field}'), get_all=False)
+
         return {
             'title': info['title'],
             'subtitles': subtitles,
@@ -113,6 +117,14 @@ class ThePlatformBaseIE(OnceIE):
             'timestamp': int_or_none(info.get('pubDate'), 1000) or None,
             'uploader': info.get('billingCode'),
             'chapters': chapters,
+            'creator': traverse_obj(info, ('author', {str})) or None,
+            'categories': traverse_obj(info, (
+                'categories', lambda _, v: v.get('label') in ('category', None), 'name', {str})) or None,
+            'tags': traverse_obj(info, ('keywords', {lambda x: re.split(r'[;,]\s?', x) if x else None})),
+            'location': extract_site_specific_field('region'),
+            'series': extract_site_specific_field('show'),
+            'season_number': int_or_none(extract_site_specific_field('seasonNumber')),
+            'media_type': extract_site_specific_field('programmingType') or extract_site_specific_field('type'),
         }
 
     def _extract_theplatform_metadata(self, path, video_id):