[TV2Hu] Fix `TV2HuIE` and add `TV2HuSeriesIE` (#804)

Closes #799 
Authored by: Ashish0804

yt_dlp/extractor/extractors.py

@@ -1440,7 +1440,10 @@ from .tv2dk import (
     TV2DKIE,
     TV2DKBornholmPlayIE,
 )
-from .tv2hu import TV2HuIE
+from .tv2hu import (
+    TV2HuIE,
+    TV2HuSeriesIE,
+)
 from .tv4 import TV4IE
 from .tv5mondeplus import TV5MondePlusIE
 from .tv5unis import (

yt_dlp/extractor/tv2hu.py

@@ -2,61 +2,109 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import (
+    traverse_obj,
+    UnsupportedError,
+)
 
 
 class TV2HuIE(InfoExtractor):
-    IE_NAME = 'tv2.hu'
-    _VALID_URL = r'https?://(?:www\.)?tv2\.hu/(?:[^/]+/)+(?P<id>\d+)_[^/?#]+?\.html'
+    IE_NAME = 'tv2play.hu'
+    _VALID_URL = r'https?://(?:www\.)?tv2play\.hu/(?!szalag/)(?P<id>[^#&?]+)'
     _TESTS = [{
-        'url': 'http://tv2.hu/ezek_megorultek/217679_ezek-megorultek---1.-adas-1.-resz.html',
-        'md5': '585e58e2e090f34603804bb2c48e98d8',
+        'url': 'https://tv2play.hu/mintaapak/mintaapak_213_epizod_resz',
         'info_dict': {
-            'id': '217679',
+            'id': '249240',
             'ext': 'mp4',
-            'title': 'Ezek megőrültek! - 1. adás 1. rész',
-            'upload_date': '20160826',
-            'thumbnail': r're:^https?://.*\.jpg$'
-        }
-    }, {
-        'url': 'http://tv2.hu/ezek_megorultek/teljes_adasok/217677_ezek-megorultek---1.-adas-2.-resz.html',
-        'only_matching': True
+            'title': 'Mintaapák - 213. epizód',
+            'series': 'Mintaapák',
+            'duration': 2164,
+            'description': 'md5:7350147e75485a59598e806c47967b07',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'release_date': '20210825',
+            'season_number': None,
+            'episode_number': 213,
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
-        'url': 'http://tv2.hu/musoraink/aktiv/aktiv_teljes_adas/217963_aktiv-teljes-adas---2016.08.30..html',
-        'only_matching': True
+        'url': 'https://tv2play.hu/taxi_2',
+        'md5': '585e58e2e090f34603804bb2c48e98d8',
+        'info_dict': {
+            'id': '199363',
+            'ext': 'mp4',
+            'title': 'Taxi 2',
+            'series': 'Taxi 2',
+            'duration': 5087,
+            'description': 'md5:47762155dc9a50241797ded101b1b08c',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'release_date': '20210118',
+            'season_number': None,
+            'episode_number': None,
+        },
+        'params': {
+            'skip_download': True,
+        },
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-        json_url = self._search_regex(
-            r'jsonUrl\s*=\s*"([^"]+)"', webpage, 'json url')
-        json_data = self._download_json(json_url, video_id)
-
-        formats = []
-        for b in ('bitrates', 'backupBitrates'):
-            bitrates = json_data.get(b, {})
-            m3u8_url = bitrates.get('hls')
-            if m3u8_url:
-                formats.extend(self._extract_wowza_formats(
-                    m3u8_url, video_id, skip_protocols=['rtmp', 'rtsp']))
-
-            for mp4_url in bitrates.get('mp4', []):
-                height = int_or_none(self._search_regex(
-                    r'\.(\d+)p\.mp4', mp4_url, 'height', default=None))
-                formats.append({
-                    'format_id': 'http' + ('-%d' % height if height else ''),
-                    'url': mp4_url,
-                    'height': height,
-                    'width': int_or_none(height / 9.0 * 16.0 if height else None),
-                })
+        id = self._match_id(url)
+        json_data = self._download_json(f'https://tv2play.hu/api/search/{id}', id)
+
+        if json_data['contentType'] == 'showpage':
+            ribbon_ids = traverse_obj(json_data, ('pages', ..., 'tabs', ..., 'ribbonIds'), get_all=False, expected_type=list)
+            entries = [self.url_result(f'https://tv2play.hu/szalag/{ribbon_id}',
+                                       ie=TV2HuSeriesIE.ie_key(), video_id=ribbon_id) for ribbon_id in ribbon_ids]
+            return self.playlist_result(entries, playlist_id=id)
+        elif json_data['contentType'] != 'video':
+            raise UnsupportedError(url)
+
+        video_id = str(json_data['id'])
+        player_id = json_data.get('playerId')
+        series_json = json_data.get('seriesInfo', {})
+
+        video_json_url = self._download_json(f'https://tv2play.hu/api/streaming-url?playerId={player_id}', video_id)['url']
+        video_json = self._download_json(video_json_url, video_id)
+        m3u8_url = self._proto_relative_url(traverse_obj(video_json, ('bitrates', 'hls')))
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id)
         self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'title': self._og_search_title(webpage).strip(),
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'upload_date': self._search_regex(
-                r'/vod/(\d{8})/', json_url, 'upload_date', default=None),
+            'title': json_data['title'],
+            'series': json_data.get('seriesTitle'),
+            'duration': json_data.get('length'),
+            'description': json_data.get('description'),
+            'thumbnail': 'https://tv2play.hu' + json_data.get('thumbnailUrl'),
+            'release_date': json_data.get('uploadedAt').replace('.', ''),
+            'season_number': series_json.get('seasonNr'),
+            'episode_number': series_json.get('episodeNr'),
             'formats': formats,
+            'subtitles': subtitles,
         }
+
+
+class TV2HuSeriesIE(InfoExtractor):
+    IE_NAME = 'tv2playseries.hu'
+    _VALID_URL = r'https?://(?:www\.)?tv2play\.hu/szalag/(?P<id>[^#&?]+)'
+
+    _TESTS = [{
+        'url': 'https://tv2play.hu/szalag/59?rendezes=nepszeruseg',
+        'playlist_mincount': 284,
+        'info_dict': {
+            'id': '59',
+        }
+    }]
+
+    def _real_extract(self, url):
+        id = self._match_id(url)
+        json_data = self._download_json(f'https://tv2play.hu/api/ribbons/{id}/0?size=100000', id)
+        entries = []
+        for card in json_data.get('cards', []):
+            video_id = card.get('slug')
+            if video_id:
+                entries.append(self.url_result(f'https://tv2play.hu/{video_id}',
+                                               ie=TV2HuIE.ie_key(), video_id=video_id))
+
+        return self.playlist_result(entries, playlist_id=id)