Tidy up cleanup rule and keep lintian happy.

[youtubedl] / youtube_dl / extractor / svt.py

diff --git a/youtube_dl/extractor/svt.py b/youtube_dl/extractor/svt.py
index 399c3b8eedbe57006a07eb187f1a78c4f090e6af..1c04dfb7bf757477d134cc7caa223ab47d0800ba 100644 (file)
--- a/youtube_dl/extractor/svt.py
+++ b/youtube_dl/extractor/svt.py
@@ -6,56 +6,80 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,

+    dict_get,
+    int_or_none,
+    try_get,

 )
 
 
 class SVTBaseIE(InfoExtractor):
 )
 
 
 class SVTBaseIE(InfoExtractor):

-    def _extract_video(self, url, video_id):
-        info = self._download_json(url, video_id)
-
-        title = info['context']['title']
-        thumbnail = info['context'].get('thumbnailImage')
-
-        video_info = info['video']
+    def _extract_video(self, video_info, video_id):

         formats = []
         for vr in video_info['videoReferences']:
         formats = []
         for vr in video_info['videoReferences']:

+            player_type = vr.get('playerType')

             vurl = vr['url']
             ext = determine_ext(vurl)
             if ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
                     vurl, video_id,
                     ext='mp4', entry_protocol='m3u8_native',
             vurl = vr['url']
             ext = determine_ext(vurl)
             if ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
                     vurl, video_id,
                     ext='mp4', entry_protocol='m3u8_native',

-                    m3u8_id=vr.get('playerType')))
+                    m3u8_id=player_type, fatal=False))

             elif ext == 'f4m':
                 formats.extend(self._extract_f4m_formats(
                     vurl + '?hdcore=3.3.0', video_id,
             elif ext == 'f4m':
                 formats.extend(self._extract_f4m_formats(
                     vurl + '?hdcore=3.3.0', video_id,

-                    f4m_id=vr.get('playerType')))
+                    f4m_id=player_type, fatal=False))
+            elif ext == 'mpd':
+                if player_type == 'dashhbbtv':
+                    formats.extend(self._extract_mpd_formats(
+                        vurl, video_id, mpd_id=player_type, fatal=False))

             else:
                 formats.append({
             else:
                 formats.append({

-                    'format_id': vr.get('playerType'),
+                    'format_id': player_type,

                     'url': vurl,
                 })
                     'url': vurl,
                 })

+        if not formats and video_info.get('rights', {}).get('geoBlockedSweden'):
+            self.raise_geo_restricted('This video is only available in Sweden')

         self._sort_formats(formats)
 
         subtitles = {}
         self._sort_formats(formats)
 
         subtitles = {}

-        subtitle_references = video_info.get('subtitleReferences')
+        subtitle_references = dict_get(video_info, ('subtitles', 'subtitleReferences'))

         if isinstance(subtitle_references, list):
             for sr in subtitle_references:
                 subtitle_url = sr.get('url')
         if isinstance(subtitle_references, list):
             for sr in subtitle_references:
                 subtitle_url = sr.get('url')

+                subtitle_lang = sr.get('language', 'sv')

                 if subtitle_url:
                 if subtitle_url:

-                    subtitles.setdefault('sv', []).append({'url': subtitle_url})
+                    if determine_ext(subtitle_url) == 'm3u8':
+                        # TODO(yan12125): handle WebVTT in m3u8 manifests
+                        continue
+
+                    subtitles.setdefault(subtitle_lang, []).append({'url': subtitle_url})

 
 

-        duration = video_info.get('materialLength')
-        age_limit = 18 if video_info.get('inappropriateForChildren') else 0
+        title = video_info.get('title')
+
+        series = video_info.get('programTitle')
+        season_number = int_or_none(video_info.get('season'))
+        episode = video_info.get('episodeTitle')
+        episode_number = int_or_none(video_info.get('episodeNumber'))
+
+        duration = int_or_none(dict_get(video_info, ('materialLength', 'contentDuration')))
+        age_limit = None
+        adult = dict_get(
+            video_info, ('inappropriateForChildren', 'blockedForChildren'),
+            skip_false_values=False)
+        if adult is not None:
+            age_limit = 18 if adult else 0

 
         return {
             'id': video_id,
             'title': title,
             'formats': formats,
             'subtitles': subtitles,
 
         return {
             'id': video_id,
             'title': title,
             'formats': formats,
             'subtitles': subtitles,

-            'thumbnail': thumbnail,

             'duration': duration,
             'age_limit': age_limit,
             'duration': duration,
             'age_limit': age_limit,

+            'series': series,
+            'season_number': season_number,
+            'episode': episode,
+            'episode_number': episode_number,

         }
 
 
         }
 
 


@@ -63,11 +87,11 @@ class SVTIE(SVTBaseIE):
     _VALID_URL = r'https?://(?:www\.)?svt\.se/wd\?(?:.*?&)?widgetId=(?P<widget_id>\d+)&.*?\barticleId=(?P<id>\d+)'
     _TEST = {
         'url': 'http://www.svt.se/wd?widgetId=23991&sectionId=541&articleId=2900353&type=embed&contextSectionId=123&autostart=false',
     _VALID_URL = r'https?://(?:www\.)?svt\.se/wd\?(?:.*?&)?widgetId=(?P<widget_id>\d+)&.*?\barticleId=(?P<id>\d+)'
     _TEST = {
         'url': 'http://www.svt.se/wd?widgetId=23991&sectionId=541&articleId=2900353&type=embed&contextSectionId=123&autostart=false',

-        'md5': '9648197555fc1b49e3dc22db4af51d46',
+        'md5': '33e9a5d8f646523ce0868ecfb0eed77d',

         'info_dict': {
             'id': '2900353',
         'info_dict': {
             'id': '2900353',

-            'ext': 'flv',
-            'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
+            'ext': 'mp4',
+            'title': 'Stjärnorna skojar till det - under SVT-intervjun',

             'duration': 27,
             'age_limit': 0,
         },
             'duration': 27,
             'age_limit': 0,
         },


@@ -84,15 +108,20 @@ class SVTIE(SVTBaseIE):
         mobj = re.match(self._VALID_URL, url)
         widget_id = mobj.group('widget_id')
         article_id = mobj.group('id')
         mobj = re.match(self._VALID_URL, url)
         widget_id = mobj.group('widget_id')
         article_id = mobj.group('id')

-        return self._extract_video(
+
+        info = self._download_json(

             'http://www.svt.se/wd?widgetId=%s&articleId=%s&format=json&type=embed&output=json' % (widget_id, article_id),
             article_id)
 
             'http://www.svt.se/wd?widgetId=%s&articleId=%s&format=json&type=embed&output=json' % (widget_id, article_id),
             article_id)
 

+        info_dict = self._extract_video(info['video'], article_id)
+        info_dict['title'] = info['context']['title']
+        return info_dict
+

 
 class SVTPlayIE(SVTBaseIE):
     IE_DESC = 'SVT Play and Öppet arkiv'
 
 class SVTPlayIE(SVTBaseIE):
     IE_DESC = 'SVT Play and Öppet arkiv'

-    _VALID_URL = r'https?://(?:www\.)?(?P<host>svtplay|oppetarkiv)\.se/video/(?P<id>[0-9]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/(?:video|klipp)/(?P<id>[0-9]+)'
+    _TESTS = [{

         'url': 'http://www.svtplay.se/video/5996901/flygplan-till-haile-selassie/flygplan-till-haile-selassie-2',
         'md5': '2b6704fe4a28801e1a098bbf3c5ac611',
         'info_dict': {
         'url': 'http://www.svtplay.se/video/5996901/flygplan-till-haile-selassie/flygplan-till-haile-selassie-2',
         'md5': '2b6704fe4a28801e1a098bbf3c5ac611',
         'info_dict': {


@@ -108,12 +137,50 @@ class SVTPlayIE(SVTBaseIE):
                 }]
             },
         },
                 }]
             },
         },

-    }
+    }, {
+        # geo restricted to Sweden
+        'url': 'http://www.oppetarkiv.se/video/5219710/trollflojten',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.svtplay.se/klipp/9023742/stopptid-om-bjorn-borg',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        host = mobj.group('host')
-        return self._extract_video(
-            'http://www.%s.se/video/%s?output=json' % (host, video_id),
-            video_id)
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        data = self._parse_json(
+            self._search_regex(
+                r'root\["__svtplay"\]\s*=\s*([^;]+);',
+                webpage, 'embedded data', default='{}'),
+            video_id, fatal=False)
+
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        if data:
+            video_info = try_get(
+                data, lambda x: x['context']['dispatcher']['stores']['VideoTitlePageStore']['data']['video'],
+                dict)
+            if video_info:
+                info_dict = self._extract_video(video_info, video_id)
+                info_dict.update({
+                    'title': data['context']['dispatcher']['stores']['MetaStore']['title'],
+                    'thumbnail': thumbnail,
+                })
+                return info_dict
+
+        video_id = self._search_regex(
+            r'<video[^>]+data-video-id=["\']([\da-zA-Z-]+)',
+            webpage, 'video id', default=None)
+
+        if video_id:
+            data = self._download_json(
+                'http://www.svt.se/videoplayer-api/video/%s' % video_id, video_id)
+            info_dict = self._extract_video(data, video_id)
+            if not info_dict.get('title'):
+                info_dict['title'] = re.sub(
+                    r'\s*\|\s*.+?$', '',
+                    info_dict.get('episode') or self._og_search_title(webpage))
+            return info_dict