[ctv] Add new extractor (closes #27525)

youtube_dl/extractor/ctv.py

@@ -0,0 +1,52 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class CTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?ctv\.ca/(?P<id>(?:show|movie)s/[^/]+/[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.ctv.ca/shows/your-morning/wednesday-december-23-2020-s5e88',
+        'info_dict': {
+            'id': '2102249',
+            'ext': 'flv',
+            'title': 'Wednesday, December 23, 2020',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'description': 'Your Morning delivers original perspectives and unique insights into the headlines of the day.',
+            'timestamp': 1608732000,
+            'upload_date': '20201223',
+            'series': 'Your Morning',
+            'season': '2020-2021',
+            'season_number': 5,
+            'episode_number': 88,
+            'tags': ['Your Morning'],
+            'categories': ['Talk Show'],
+            'duration': 7467.126,
+        },
+    }, {
+        'url': 'https://www.ctv.ca/movies/adam-sandlers-eight-crazy-nights/adam-sandlers-eight-crazy-nights',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        content = self._download_json(
+            'https://www.ctv.ca/space-graphql/graphql', display_id, query={
+                'query': '''{
+  resolvedPath(path: "/%s") {
+    lastSegment {
+      content {
+        ... on AxisContent {
+          axisId
+          videoPlayerDestCode
+        }
+      }
+    }
+  }
+}''' % display_id,
+            })['data']['resolvedPath']['lastSegment']['content']
+        video_id = content['axisId']
+        return self.url_result(
+            '9c9media:%s:%s' % (content['videoPlayerDestCode'], video_id),
+            'NineCNineMedia', video_id)

youtube_dl/extractor/extractors.py

@@ -244,6 +244,7 @@ from .crunchyroll import (
 )
 from .cspan import CSpanIE
 from .ctsnews import CtsNewsIE
+from .ctv import CTVIE
 from .ctvnews import CTVNewsIE
 from .cultureunplugged import CultureUnpluggedIE
 from .curiositystream import (

youtube_dl/extractor/ninecninemedia.py

@@ -5,10 +5,11 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    parse_iso8601,
-    float_or_none,
     ExtractorError,
+    float_or_none,
     int_or_none,
+    parse_iso8601,
+    try_get,
 )
 
 
@@ -35,7 +36,7 @@ class NineCNineMediaIE(InfoExtractor):
                 '$include': '[HasClosedCaptions]',
             })
 
-        if content_package.get('Constraints', {}).get('Security', {}).get('Type'):
+        if try_get(content_package, lambda x: x['Constraints']['Security']['Type']):
             raise ExtractorError('This video is DRM protected.', expected=True)
 
         manifest_base_url = content_package_url + 'manifest.'
@@ -52,7 +53,7 @@ class NineCNineMediaIE(InfoExtractor):
         self._sort_formats(formats)
 
         thumbnails = []
-        for image in content.get('Images', []):
+        for image in (content.get('Images') or []):
             image_url = image.get('Url')
             if not image_url:
                 continue
@@ -70,7 +71,7 @@ class NineCNineMediaIE(InfoExtractor):
                     continue
                 container.append(e_name)
 
-        season = content.get('Season', {})
+        season = content.get('Season') or {}
 
         info = {
             'id': content_id,
@@ -79,13 +80,14 @@ class NineCNineMediaIE(InfoExtractor):
             'timestamp': parse_iso8601(content.get('BroadcastDateTime')),
             'episode_number': int_or_none(content.get('Episode')),
             'season': season.get('Name'),
-            'season_number': season.get('Number'),
+            'season_number': int_or_none(season.get('Number')),
             'season_id': season.get('Id'),
-            'series': content.get('Media', {}).get('Name'),
+            'series': try_get(content, lambda x: x['Media']['Name']),
             'tags': tags,
             'categories': categories,
             'duration': float_or_none(content_package.get('Duration')),
             'formats': formats,
+            'thumbnails': thumbnails,
         }
 
         if content_package.get('HasClosedCaptions'):