debian/README.source: Change 'markup'.

[youtubedl] / youtube_dl / extractor / cwtv.py

diff --git a/youtube_dl/extractor/cwtv.py b/youtube_dl/extractor/cwtv.py
index ebd14cb1638b6309f1522c142502c0dac5d763a2..73382431b7c8dccf35d118b5506bfb38b29a9804 100644 (file)
--- a/youtube_dl/extractor/cwtv.py
+++ b/youtube_dl/extractor/cwtv.py
@@ -3,13 +3,17 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (

+    ExtractorError,

     int_or_none,
     int_or_none,

+    parse_age_limit,

     parse_iso8601,
     parse_iso8601,

+    smuggle_url,
+    str_or_none,

 )
 
 
 class CWTVIE(InfoExtractor):
 )
 
 
 class CWTVIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?cw(?:tv|seed)\.com/(?:shows/)?(?:[^/]+/){2}\?.*\bplay=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})'
+    _VALID_URL = r'https?://(?:www\.)?cw(?:tv(?:pr)?|seed)\.com/(?:shows/)?(?:[^/]+/)+[^?]*\?.*\b(?:play|watch)=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})'

     _TESTS = [{
         'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?play=6b15e985-9345-4f60-baf8-56e96be57c63',
         'info_dict': {
     _TESTS = [{
         'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?play=6b15e985-9345-4f60-baf8-56e96be57c63',
         'info_dict': {


@@ -28,7 +32,8 @@ class CWTVIE(InfoExtractor):
         'params': {
             # m3u8 download
             'skip_download': True,
         'params': {
             # m3u8 download
             'skip_download': True,

-        }
+        },
+        'skip': 'redirect to http://cwtv.com/shows/arrow/',

     }, {
         'url': 'http://www.cwseed.com/shows/whose-line-is-it-anyway/jeff-davis-4/?play=24282b12-ead2-42f2-95ad-26770c2c6088',
         'info_dict': {
     }, {
         'url': 'http://www.cwseed.com/shows/whose-line-is-it-anyway/jeff-davis-4/?play=24282b12-ead2-42f2-95ad-26770c2c6088',
         'info_dict': {


@@ -39,54 +44,54 @@ class CWTVIE(InfoExtractor):
             'duration': 1263,
             'series': 'Whose Line Is It Anyway?',
             'season_number': 11,
             'duration': 1263,
             'series': 'Whose Line Is It Anyway?',
             'season_number': 11,

-            'season': '11',

             'episode_number': 20,
             'upload_date': '20151006',
             'timestamp': 1444107300,
             'episode_number': 20,
             'upload_date': '20151006',
             'timestamp': 1444107300,

+            'age_limit': 14,
+            'uploader': 'CWTV',

         },
         'params': {
             # m3u8 download
             'skip_download': True,
         },
         'params': {
             # m3u8 download
             'skip_download': True,

-        }
+        },

     }, {
         'url': 'http://cwtv.com/thecw/chroniclesofcisco/?play=8adebe35-f447-465f-ab52-e863506ff6d6',
         'only_matching': True,
     }, {
         'url': 'http://cwtv.com/thecw/chroniclesofcisco/?play=8adebe35-f447-465f-ab52-e863506ff6d6',
         'only_matching': True,

+    }, {
+        'url': 'http://cwtvpr.com/the-cw/video?watch=9eee3f60-ef4e-440b-b3b2-49428ac9c54e',
+        'only_matching': True,
+    }, {
+        'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?watch=6b15e985-9345-4f60-baf8-56e96be57c63',
+        'only_matching': True,

     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

-        video_data = self._download_json(
-            'http://metaframe.digitalsmiths.tv/v2/CWtv/assets/%s/partner/132?format=json' % video_id, video_id)
-
-        formats = self._extract_m3u8_formats(
-            video_data['videos']['variantplaylist']['uri'], video_id, 'mp4')
-        self._sort_formats(formats)
-
-        thumbnails = [{
-            'url': image['uri'],
-            'width': image.get('width'),
-            'height': image.get('height'),
-        } for image_id, image in video_data['images'].items() if image.get('uri')] if video_data.get('images') else None
-
-        video_metadata = video_data['assetFields']
+        data = self._download_json(
+            'http://images.cwtv.com/feed/mobileapp/video-meta/apiversion_8/guid_' + video_id,
+            video_id)
+        if data.get('result') != 'ok':
+            raise ExtractorError(data['msg'], expected=True)
+        video_data = data['video']
+        title = video_data['title']
+        mpx_url = video_data.get('mpx_url') or 'http://link.theplatform.com/s/cwtv/media/guid/2703454149/%s?formats=M3U' % video_id

 
 

-        subtitles = {
-            'en': [{
-                'url': video_metadata['UnicornCcUrl'],
-            }],
-        } if video_metadata.get('UnicornCcUrl') else None
+        season = str_or_none(video_data.get('season'))
+        episode = str_or_none(video_data.get('episode'))
+        if episode and season:
+            episode = episode[len(season):]

 
         return {
 
         return {

+            '_type': 'url_transparent',

             'id': video_id,
             'id': video_id,

-            'title': video_metadata['title'],
-            'description': video_metadata.get('description'),
-            'duration': int_or_none(video_metadata.get('duration')),
-            'series': video_metadata.get('seriesName'),
-            'season_number': int_or_none(video_metadata.get('seasonNumber')),
-            'season': video_metadata.get('seasonName'),
-            'episode_number': int_or_none(video_metadata.get('episodeNumber')),
-            'timestamp': parse_iso8601(video_data.get('startTime')),
-            'thumbnails': thumbnails,
-            'formats': formats,
-            'subtitles': subtitles,
+            'title': title,
+            'url': smuggle_url(mpx_url, {'force_smil_url': True}),
+            'description': video_data.get('description_long'),
+            'duration': int_or_none(video_data.get('duration_secs')),
+            'series': video_data.get('series_name'),
+            'season_number': int_or_none(season),
+            'episode_number': int_or_none(episode),
+            'timestamp': parse_iso8601(video_data.get('start_time')),
+            'age_limit': parse_age_limit(video_data.get('rating')),
+            'ie_key': 'ThePlatform',

         }
         }