Imported Debian patch 2015.11.27.1-1.1

[youtubedl] / youtube_dl / extractor / nrk.py

diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py
index cc70c295014f95fcb7e74f2f009889b5ca135663..8ac38a174b4c64bbc8a3b40ec36c10d6fab595fa 100644 (file)
--- a/youtube_dl/extractor/nrk.py
+++ b/youtube_dl/extractor/nrk.py
@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

+from ..compat import compat_urlparse

 from ..utils import (
     ExtractorError,
     float_or_none,
 from ..utils import (
     ExtractorError,
     float_or_none,


@@ -13,7 +14,7 @@ from ..utils import (
 
 
 class NRKIE(InfoExtractor):
 
 
 class NRKIE(InfoExtractor):

-    _VALID_URL = r'(?:nrk:|http://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)'
+    _VALID_URL = r'(?:nrk:|https?://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)'

 
     _TESTS = [
         {
 
     _TESTS = [
         {


@@ -49,7 +50,7 @@ class NRKIE(InfoExtractor):
 
         if data['usageRights']['isGeoBlocked']:
             raise ExtractorError(
 
         if data['usageRights']['isGeoBlocked']:
             raise ExtractorError(

-                'NRK har ikke rettig-heter til å vise dette programmet utenfor Norge',
+                'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',

                 expected=True)
 
         video_url = data['mediaUrl'] + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81'
                 expected=True)
 
         video_url = data['mediaUrl'] + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81'


@@ -76,7 +77,7 @@ class NRKIE(InfoExtractor):
 
 
 class NRKPlaylistIE(InfoExtractor):
 
 
 class NRKPlaylistIE(InfoExtractor):

-    _VALID_URL = r'http://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)'

 
     _TESTS = [{
         'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
 
     _TESTS = [{
         'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',


@@ -116,11 +117,12 @@ class NRKPlaylistIE(InfoExtractor):
 
 
 class NRKTVIE(InfoExtractor):
 
 
 class NRKTVIE(InfoExtractor):

-    _VALID_URL = r'(?P<baseurl>http://tv\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
+    IE_DESC = 'NRK TV and NRK Radio'
+    _VALID_URL = r'(?P<baseurl>https?://(?:tv|radio)\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'

 
     _TESTS = [
         {
 
     _TESTS = [
         {

-            'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
+            'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',

             'md5': 'adf2c5454fa2bf032f47a9f8fb351342',
             'info_dict': {
                 'id': 'MUHH48000314',
             'md5': 'adf2c5454fa2bf032f47a9f8fb351342',
             'info_dict': {
                 'id': 'MUHH48000314',


@@ -132,7 +134,7 @@ class NRKTVIE(InfoExtractor):
             },
         },
         {
             },
         },
         {

-            'url': 'http://tv.nrk.no/program/mdfp15000514',
+            'url': 'https://tv.nrk.no/program/mdfp15000514',

             'md5': '383650ece2b25ecec996ad7b5bb2a384',
             'info_dict': {
                 'id': 'mdfp15000514',
             'md5': '383650ece2b25ecec996ad7b5bb2a384',
             'info_dict': {
                 'id': 'mdfp15000514',


@@ -145,7 +147,7 @@ class NRKTVIE(InfoExtractor):
         },
         {
             # single playlist video
         },
         {
             # single playlist video

-            'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
+            'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',

             'md5': 'adbd1dbd813edaf532b0a253780719c2',
             'info_dict': {
                 'id': 'MSPO40010515-part2',
             'md5': 'adbd1dbd813edaf532b0a253780719c2',
             'info_dict': {
                 'id': 'MSPO40010515-part2',


@@ -157,7 +159,7 @@ class NRKTVIE(InfoExtractor):
             'skip': 'Only works from Norway',
         },
         {
             'skip': 'Only works from Norway',
         },
         {

-            'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
+            'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',

             'playlist': [
                 {
                     'md5': '9480285eff92d64f06e02a5367970a7a',
             'playlist': [
                 {
                     'md5': '9480285eff92d64f06e02a5367970a7a',


@@ -188,31 +190,22 @@ class NRKTVIE(InfoExtractor):
                 'duration': 6947.5199999999995,
             },
             'skip': 'Only works from Norway',
                 'duration': 6947.5199999999995,
             },
             'skip': 'Only works from Norway',

+        },
+        {
+            'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
+            'only_matching': True,

         }
     ]
 
         }
     ]
 

-    def _debug_print(self, txt):
-        if self._downloader.params.get('verbose', False):
-            self.to_screen('[debug] %s' % txt)
-
-    def _get_subtitles(self, subtitlesurl, video_id, baseurl):
-        url = "%s%s" % (baseurl, subtitlesurl)
-        self._debug_print('%s: Subtitle url: %s' % (video_id, url))
-        captions = self._download_xml(
-            url, video_id, 'Downloading subtitles')
-        lang = captions.get('lang', 'no')
-        return {lang: [
-            {'ext': 'ttml', 'url': url},
-        ]}
-

     def _extract_f4m(self, manifest_url, video_id):
     def _extract_f4m(self, manifest_url, video_id):

-        return self._extract_f4m_formats(manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id)
+        return self._extract_f4m_formats(
+            manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id, f4m_id='hds')

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         part_id = mobj.group('part_id')
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         part_id = mobj.group('part_id')

-        baseurl = mobj.group('baseurl')
+        base_url = mobj.group('baseurl')

 
         webpage = self._download_webpage(url, video_id)
 
 
         webpage = self._download_webpage(url, video_id)
 


@@ -268,15 +261,18 @@ class NRKTVIE(InfoExtractor):
 
         m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage)
         if m3u8_url:
 
         m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage)
         if m3u8_url:

-            formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4'))
+            formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4', m3u8_id='hls'))

         self._sort_formats(formats)
 
         subtitles_url = self._html_search_regex(
         self._sort_formats(formats)
 
         subtitles_url = self._html_search_regex(

-            r'data-subtitlesurl[ ]*=[ ]*"([^"]+)"',
-            webpage, 'subtitle URL', default=None)
-        subtitles = None
+            r'data-subtitlesurl\s*=\s*(["\'])(?P<url>.+?)\1',
+            webpage, 'subtitle URL', default=None, group='url')
+        subtitles = {}

         if subtitles_url:
         if subtitles_url:

-            subtitles = self.extract_subtitles(subtitles_url, video_id, baseurl)
+            subtitles['no'] = [{
+                'ext': 'ttml',
+                'url': compat_urlparse.urljoin(base_url, subtitles_url),
+            }]

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,