[shahid] Add new extractor

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 06f21064b699fe8b3012836949c655e6e284ef29..6c1d4f08a30fd9b4d4880446fd436ae60cedf915 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -502,6 +502,7 @@ from .senateisvp import SenateISVPIE
 from .servingsys import ServingSysIE
 from .sexu import SexuIE
 from .sexykarma import SexyKarmaIE
+from .shahid import ShahidIE
 from .shared import SharedIE
 from .sharesix import ShareSixIE
 from .sina import SinaIE

diff --git a/youtube_dl/extractor/shahid.py b/youtube_dl/extractor/shahid.py
new file mode 100644 (file)
index 0000000..d492070
--- /dev/null
+++ b/youtube_dl/extractor/shahid.py
@@ -0,0 +1,56 @@
+from .common import InfoExtractor
+from ..utils import get_element_by_id
+
+class ShahidIE(InfoExtractor):
+    _VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P<id>\d+)/?'
+    _TESTS = [
+        {
+            'url': 'https://shahid.mbc.net/ar/episode/108084/%D8%AE%D9%88%D8%A7%D8%B7%D8%B1-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-11-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1.html',
+            'info_dict': {
+                'id': '108084',
+                'ext': 'm3u8',
+                'title': 'بسم الله',
+                'description': 'بسم الله'
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            }
+        },
+        {
+            #shahid plus subscriber only
+            'url': 'https://shahid.mbc.net/ar/series/90497/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011.html',
+            'only_matching': True
+        }
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        json_data = self._parse_json(
+            get_element_by_id('jsonld', webpage),
+            video_id
+        )
+        title = json_data['name']
+        thumbnail = json_data['image']
+        categories = json_data['genre']
+        description = json_data['description']
+        player_json_data = self._download_json(
+            'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-'+video_id+'.type-player.html',
+            video_id
+        )['data']
+        if 'url' in player_json_data:
+            m3u8_url = player_json_data['url']
+        else:
+            for error in json_data['error'].values():
+                self.report_warning(error)
+            return
+        formats = self._extract_m3u8_formats(m3u8_url, video_id)
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'description': description,
+            'formats': formats,
+        }