New upstream version 2016.12.01

[youtubedl] / youtube_dl / extractor / drtv.py

diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py
index 2d74ff855f1670e0dcb46e35d1875e8e9c9fd144..88d096b307cdf6d484ef6b89253f6cdbcb82deb0 100644 (file)
--- a/youtube_dl/extractor/drtv.py
+++ b/youtube_dl/extractor/drtv.py
@@ -4,26 +4,45 @@ from __future__ import unicode_literals
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,

+    int_or_none,
+    float_or_none,
+    mimetype2ext,

     parse_iso8601,
     parse_iso8601,

+    remove_end,

 )
 
 
 class DRTVIE(InfoExtractor):
 )
 
 
 class DRTVIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
+    _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'

 
 

-    _TEST = {
-        'url': 'https://www.dr.dk/tv/se/boern/ultra/panisk-paske/panisk-paske-5',
-        'md5': 'dc515a9ab50577fa14cc4e4b0265168f',
+    _TESTS = [{
+        'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10',
+        'md5': '25e659cccc9a2ed956110a299fdf5983',

         'info_dict': {
         'info_dict': {

-            'id': 'panisk-paske-5',
+            'id': 'klassen-darlig-taber-10',

             'ext': 'mp4',
             'ext': 'mp4',

-            'title': 'Panisk Påske (5)',
-            'description': 'md5:ca14173c5ab24cd26b0fcc074dff391c',
-            'timestamp': 1426984612,
-            'upload_date': '20150322',
-            'duration': 1455,
+            'title': 'Klassen - Dårlig taber (10)',
+            'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa',
+            'timestamp': 1471991907,
+            'upload_date': '20160823',
+            'duration': 606.84,

         },
         },

-    }
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang',
+        'md5': '2c37175c718155930f939ef59952474a',
+        'info_dict': {
+            'id': 'christiania-pusher-street-ryddes-drdkrjpo',
+            'ext': 'mp4',
+            'title': 'LIVE Christianias rydning af Pusher Street er i gang',
+            'description': '- Det er det fedeste, der er sket i 20 år, fortæller christianit til DR Nyheder.',
+            'timestamp': 1472800279,
+            'upload_date': '20160902',
+            'duration': 131.4,
+        },
+    }]

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


@@ -35,7 +54,8 @@ class DRTVIE(InfoExtractor):
                 'Video %s is not available' % video_id, expected=True)
 
         video_id = self._search_regex(
                 'Video %s is not available' % video_id, expected=True)
 
         video_id = self._search_regex(

-            r'data-(?:material-identifier|episode-slug)="([^"]+)"',
+            (r'data-(?:material-identifier|episode-slug)="([^"]+)"',
+                r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),

             webpage, 'video id')
 
         programcard = self._download_json(
             webpage, 'video id')
 
         programcard = self._download_json(


@@ -43,9 +63,12 @@ class DRTVIE(InfoExtractor):
             video_id, 'Downloading video JSON')
         data = programcard['Data'][0]
 
             video_id, 'Downloading video JSON')
         data = programcard['Data'][0]
 

-        title = data['Title']
-        description = data['Description']
-        timestamp = parse_iso8601(data['CreatedTime'])
+        title = remove_end(self._og_search_title(
+            webpage, default=None), ' | TV | DR') or data['Title']
+        description = self._og_search_description(
+            webpage, default=None) or data.get('Description')
+
+        timestamp = parse_iso8601(data.get('CreatedTime'))

 
         thumbnail = None
         duration = None
 
         thumbnail = None
         duration = None


@@ -56,16 +79,18 @@ class DRTVIE(InfoExtractor):
         subtitles = {}
 
         for asset in data['Assets']:
         subtitles = {}
 
         for asset in data['Assets']:

-            if asset['Kind'] == 'Image':
-                thumbnail = asset['Uri']
-            elif asset['Kind'] == 'VideoResource':
-                duration = asset['DurationInMilliseconds'] / 1000.0
-                restricted_to_denmark = asset['RestrictedToDenmark']
-                spoken_subtitles = asset['Target'] == 'SpokenSubtitles'
-                for link in asset['Links']:
-                    uri = link['Uri']
-                    target = link['Target']
-                    format_id = target
+            if asset.get('Kind') == 'Image':
+                thumbnail = asset.get('Uri')
+            elif asset.get('Kind') == 'VideoResource':
+                duration = float_or_none(asset.get('DurationInMilliseconds'), 1000)
+                restricted_to_denmark = asset.get('RestrictedToDenmark')
+                spoken_subtitles = asset.get('Target') == 'SpokenSubtitles'
+                for link in asset.get('Links', []):
+                    uri = link.get('Uri')
+                    if not uri:
+                        continue
+                    target = link.get('Target')
+                    format_id = target or ''

                     preference = None
                     if spoken_subtitles:
                         preference = -1
                     preference = None
                     if spoken_subtitles:
                         preference = -1


@@ -76,8 +101,8 @@ class DRTVIE(InfoExtractor):
                             video_id, preference, f4m_id=format_id))
                     elif target == 'HLS':
                         formats.extend(self._extract_m3u8_formats(
                             video_id, preference, f4m_id=format_id))
                     elif target == 'HLS':
                         formats.extend(self._extract_m3u8_formats(

-                            uri, video_id, 'mp4', preference=preference,
-                            m3u8_id=format_id))
+                            uri, video_id, 'mp4', entry_protocol='m3u8_native',
+                            preference=preference, m3u8_id=format_id))

                     else:
                         bitrate = link.get('Bitrate')
                         if bitrate:
                     else:
                         bitrate = link.get('Bitrate')
                         if bitrate:


@@ -85,7 +110,7 @@ class DRTVIE(InfoExtractor):
                         formats.append({
                             'url': uri,
                             'format_id': format_id,
                         formats.append({
                             'url': uri,
                             'format_id': format_id,

-                            'tbr': bitrate,
+                            'tbr': int_or_none(bitrate),

                             'ext': link.get('FileFormat'),
                         })
                 subtitles_list = asset.get('SubtitlesList')
                             'ext': link.get('FileFormat'),
                         })
                 subtitles_list = asset.get('SubtitlesList')


@@ -94,12 +119,18 @@ class DRTVIE(InfoExtractor):
                         'Danish': 'da',
                     }
                     for subs in subtitles_list:
                         'Danish': 'da',
                     }
                     for subs in subtitles_list:

-                        lang = subs['Language']
-                        subtitles[LANGS.get(lang, lang)] = [{'url': subs['Uri'], 'ext': 'vtt'}]
+                        if not subs.get('Uri'):
+                            continue
+                        lang = subs.get('Language') or 'da'
+                        subtitles.setdefault(LANGS.get(lang, lang), []).append({
+                            'url': subs['Uri'],
+                            'ext': mimetype2ext(subs.get('MimeType')) or 'vtt'
+                        })

 
         if not formats and restricted_to_denmark:
 
         if not formats and restricted_to_denmark:

-            raise ExtractorError(
-                'Unfortunately, DR is not allowed to show this program outside Denmark.', expected=True)
+            self.raise_geo_restricted(
+                'Unfortunately, DR is not allowed to show this program outside Denmark.',
+                expected=True)

 
         self._sort_formats(formats)
 
 
         self._sort_formats(formats)