]> jfr.im git - yt-dlp.git/blobdiff - yt_dlp/extractor/adn.py
[ie/matchtv] Fix extractor (#10190)
[yt-dlp.git] / yt_dlp / extractor / adn.py
index 16f648de3eb51c7916f454603abe422be934ff75..7be990b9cf5dbcbd8f896b0a8cb706f5c2b87e40 100644 (file)
@@ -3,33 +3,52 @@
 import json
 import os
 import random
+import time
 
 from .common import InfoExtractor
 from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
-from ..compat import (
-    compat_HTTPError,
-    compat_b64decode,
-)
+from ..networking.exceptions import HTTPError
 from ..utils import (
+    ExtractorError,
     ass_subtitles_timecode,
     bytes_to_intlist,
     bytes_to_long,
-    ExtractorError,
     float_or_none,
     int_or_none,
     intlist_to_bytes,
     long_to_bytes,
+    parse_iso8601,
     pkcs1pad,
+    str_or_none,
     strip_or_none,
     try_get,
     unified_strdate,
     urlencode_postdata,
 )
+from ..utils.traversal import traverse_obj
 
 
-class ADNIE(InfoExtractor):
+class ADNBaseIE(InfoExtractor):
     IE_DESC = 'Animation Digital Network'
-    _VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
+    _NETRC_MACHINE = 'animationdigitalnetwork'
+    _BASE = 'animationdigitalnetwork.fr'
+    _API_BASE_URL = f'https://gw.api.{_BASE}/'
+    _PLAYER_BASE_URL = f'{_API_BASE_URL}player/'
+    _HEADERS = {}
+    _LOGIN_ERR_MESSAGE = 'Unable to log in'
+    _RSA_KEY = (0x9B42B08905199A5CCE2026274399CA560ECB209EE9878A708B1C0812E1BB8CB5D1FB7441861147C1A1F2F3A0476DD63A9CAC20D3E983613346850AA6CB38F16DC7D720FD7D86FC6E5B3D5BBC72E14CD0BF9E869F2CEA2CCAD648F1DCE38F1FF916CEFB2D339B64AA0264372344BC775E265E8A852F88144AB0BD9AA06C1A4ABB, 65537)
+    _POS_ALIGN_MAP = {
+        'start': 1,
+        'end': 3,
+    }
+    _LINE_ALIGN_MAP = {
+        'middle': 8,
+        'end': 4,
+    }
+
+
+class ADNIE(ADNBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.(?P<lang>fr|de)/video/[^/?#]+/(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://animationdigitalnetwork.fr/video/fruits-basket/9841-episode-1-a-ce-soir',
         'md5': '1c9ef066ceb302c86f80c2b371615261',
@@ -46,29 +65,35 @@ class ADNIE(InfoExtractor):
             'season_number': 1,
             'episode': 'À ce soir !',
             'episode_number': 1,
+            'thumbnail': str,
+            'season': 'Season 1',
         },
-        'skip': 'Only available in region (FR, ...)',
+        'skip': 'Only available in French and German speaking Europe',
     }, {
         'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
         'only_matching': True,
+    }, {
+        'url': 'https://animationdigitalnetwork.de/video/the-eminence-in-shadow/23550-folge-1',
+        'md5': '5c5651bf5791fa6fcd7906012b9d94e8',
+        'info_dict': {
+            'id': '23550',
+            'ext': 'mp4',
+            'episode_number': 1,
+            'duration': 1417,
+            'release_date': '20231004',
+            'series': 'The Eminence in Shadow',
+            'season_number': 2,
+            'episode': str,
+            'title': str,
+            'thumbnail': str,
+            'season': 'Season 2',
+            'comment_count': int,
+            'average_rating': float,
+            'description': str,
+        },
+        # 'skip': 'Only available in French and German speaking Europe',
     }]
 
-    _NETRC_MACHINE = 'animationdigitalnetwork'
-    _BASE = 'animationdigitalnetwork.fr'
-    _API_BASE_URL = 'https://gw.api.' + _BASE + '/'
-    _PLAYER_BASE_URL = _API_BASE_URL + 'player/'
-    _HEADERS = {}
-    _LOGIN_ERR_MESSAGE = 'Unable to log in'
-    _RSA_KEY = (0x9B42B08905199A5CCE2026274399CA560ECB209EE9878A708B1C0812E1BB8CB5D1FB7441861147C1A1F2F3A0476DD63A9CAC20D3E983613346850AA6CB38F16DC7D720FD7D86FC6E5B3D5BBC72E14CD0BF9E869F2CEA2CCAD648F1DCE38F1FF916CEFB2D339B64AA0264372344BC775E265E8A852F88144AB0BD9AA06C1A4ABB, 65537)
-    _POS_ALIGN_MAP = {
-        'start': 1,
-        'end': 3,
-    }
-    _LINE_ALIGN_MAP = {
-        'middle': 8,
-        'end': 4,
-    }
-
     def _get_subtitles(self, sub_url, video_id):
         if not sub_url:
             return None
@@ -85,9 +110,9 @@ def _get_subtitles(self, sub_url, video_id):
 
         # http://animationdigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
         dec_subtitles = unpad_pkcs7(aes_cbc_decrypt_bytes(
-            compat_b64decode(enc_subtitles[24:]),
+            base64.b64decode(enc_subtitles[24:]),
             binascii.unhexlify(self._K + '7fac1178830cfe0c'),
-            compat_b64decode(enc_subtitles[:24])))
+            base64.b64decode(enc_subtitles[:24])))
         subtitles_json = self._parse_json(dec_subtitles.decode(), None, fatal=False)
         if not subtitles_json:
             return None
@@ -110,7 +135,7 @@ def _get_subtitles(self, sub_url, video_id):
                 if start is None or end is None or text is None:
                     continue
                 alignment = self._POS_ALIGN_MAP.get(position_align, 2) + self._LINE_ALIGN_MAP.get(line_align, 0)
-                ssa += os.linesep + 'Dialogue: Marked=0,%s,%s,Default,,0,0,0,,%s%s' % (
+                ssa += os.linesep + 'Dialogue: Marked=0,{},{},Default,,0,0,0,,{}{}'.format(
                     ass_subtitles_timecode(start),
                     ass_subtitles_timecode(end),
                     '{\\a%d}' % alignment if alignment != 2 else '',
@@ -118,6 +143,8 @@ def _get_subtitles(self, sub_url, video_id):
 
             if sub_lang == 'vostf':
                 sub_lang = 'fr'
+            elif sub_lang == 'vostde':
+                sub_lang = 'de'
             subtitles.setdefault(sub_lang, []).extend([{
                 'ext': 'json',
                 'data': json.dumps(sub),
@@ -142,15 +169,15 @@ def _perform_login(self, username, password):
                 self._HEADERS = {'authorization': 'Bearer ' + access_token}
         except ExtractorError as e:
             message = None
-            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+            if isinstance(e.cause, HTTPError) and e.cause.status == 401:
                 resp = self._parse_json(
-                    e.cause.read().decode(), None, fatal=False) or {}
+                    e.cause.response.read().decode(), None, fatal=False) or {}
                 message = resp.get('message') or resp.get('code')
             self.report_warning(message or self._LOGIN_ERR_MESSAGE)
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        video_base_url = self._PLAYER_BASE_URL + 'video/%s/' % video_id
+        lang, video_id = self._match_valid_url(url).group('lang', 'id')
+        video_base_url = self._PLAYER_BASE_URL + f'video/{video_id}/'
         player = self._download_json(
             video_base_url + 'configuration', video_id,
             'Downloading player config JSON metadata',
@@ -159,16 +186,19 @@ def _real_extract(self, url):
 
         user = options['user']
         if not user.get('hasAccess'):
-            self.raise_login_required()
+            start_date = traverse_obj(options, ('video', 'startDate', {str}))
+            if (parse_iso8601(start_date) or 0) > time.time():
+                raise ExtractorError(f'This video is not available yet. Release date: {start_date}', expected=True)
+            self.raise_login_required('This video requires a subscription', method='password')
 
         token = self._download_json(
             user.get('refreshTokenUrl') or (self._PLAYER_BASE_URL + 'refresh/token'),
             video_id, 'Downloading access token', headers={
-                'x-player-refresh-token': user['refreshToken']
+                'X-Player-Refresh-Token': user['refreshToken'],
             }, data=b'')['token']
 
         links_url = try_get(options, lambda x: x['video']['url']) or (video_base_url + 'link')
-        self._K = ''.join([random.choice('0123456789abcdef') for _ in range(16)])
+        self._K = ''.join(random.choices('0123456789abcdef', k=16))
         message = bytes_to_intlist(json.dumps({
             'k': self._K,
             't': token,
@@ -186,23 +216,25 @@ def _real_extract(self, url):
             try:
                 links_data = self._download_json(
                     links_url, video_id, 'Downloading links JSON metadata', headers={
-                        'X-Player-Token': authorization
+                        'X-Player-Token': authorization,
+                        'X-Target-Distribution': lang,
+                        **self._HEADERS,
                     }, query={
                         'freeWithAds': 'true',
                         'adaptive': 'false',
                         'withMetadata': 'true',
-                        'source': 'Web'
+                        'source': 'Web',
                     })
                 break
             except ExtractorError as e:
-                if not isinstance(e.cause, compat_HTTPError):
+                if not isinstance(e.cause, HTTPError):
                     raise e
 
-                if e.cause.code == 401:
+                if e.cause.status == 401:
                     # This usually goes away with a different random pkcs1pad, so retry
                     continue
 
-                error = self._parse_json(e.cause.read(), video_id)
+                error = self._parse_json(e.cause.response.read(), video_id)
                 message = error.get('message')
                 if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country':
                     self.raise_geo_restricted(msg=message)
@@ -223,7 +255,7 @@ def _real_extract(self, url):
             for quality, load_balancer_url in qualities.items():
                 load_balancer_data = self._download_json(
                     load_balancer_url, video_id,
-                    'Downloading %s %s JSON metadata' % (format_id, quality),
+                    f'Downloading {format_id} {quality} JSON metadata',
                     fatal=False) or {}
                 m3u8_url = load_balancer_data.get('location')
                 if not m3u8_url:
@@ -234,11 +266,16 @@ def _real_extract(self, url):
                 if format_id == 'vf':
                     for f in m3u8_formats:
                         f['language'] = 'fr'
+                elif format_id == 'vde':
+                    for f in m3u8_formats:
+                        f['language'] = 'de'
                 formats.extend(m3u8_formats)
-        self._sort_formats(formats)
+
+        if not formats:
+            self.raise_login_required('This video requires a subscription', method='password')
 
         video = (self._download_json(
-            self._API_BASE_URL + 'video/%s' % video_id, video_id,
+            self._API_BASE_URL + f'video/{video_id}', video_id,
             'Downloading additional video metadata', fatal=False) or {}).get('video') or {}
         show = video.get('show') or {}
 
@@ -258,3 +295,40 @@ def _real_extract(self, url):
             'average_rating': float_or_none(video.get('rating') or metas.get('rating')),
             'comment_count': int_or_none(video.get('commentsCount')),
         }
+
+
+class ADNSeasonIE(ADNBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.(?P<lang>fr|de)/video/(?P<id>[^/?#]+)/?(?:$|[#?])'
+    _TESTS = [{
+        'url': 'https://animationdigitalnetwork.fr/video/tokyo-mew-mew-new',
+        'playlist_count': 12,
+        'info_dict': {
+            'id': '911',
+            'title': 'Tokyo Mew Mew New',
+        },
+        # 'skip': 'Only available in French end German speaking Europe',
+    }]
+
+    def _real_extract(self, url):
+        lang, video_show_slug = self._match_valid_url(url).group('lang', 'id')
+        show = self._download_json(
+            f'{self._API_BASE_URL}show/{video_show_slug}/', video_show_slug,
+            'Downloading show JSON metadata', headers=self._HEADERS)['show']
+        show_id = str(show['id'])
+        episodes = self._download_json(
+            f'{self._API_BASE_URL}video/show/{show_id}', video_show_slug,
+            'Downloading episode list', headers={
+                'X-Target-Distribution': lang,
+                **self._HEADERS,
+            }, query={
+                'order': 'asc',
+                'limit': '-1',
+            })
+
+        def entries():
+            for episode_id in traverse_obj(episodes, ('videos', ..., 'id', {str_or_none})):
+                yield self.url_result(
+                    f'https://animationdigitalnetwork.{lang}/video/{video_show_slug}/{episode_id}',
+                    ADNIE, episode_id)
+
+        return self.playlist_result(entries(), show_id, show.get('title'))