Merge tag 'upstream/2016.06.25'

[youtubedl] / youtube_dl / extractor / rai.py

diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py
index ba3dd707f8b5d38363dacce62e9fe684265c6a96..e36ce1aa1940deafd5a633bec814e7462008c3b1 100644 (file)
--- a/youtube_dl/extractor/rai.py
+++ b/youtube_dl/extractor/rai.py
@@ -2,23 +2,30 @@ from __future__ import unicode_literals
 
 import re
 
 
 import re
 

-from .subtitles import SubtitlesInfoExtractor
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse,
+    compat_urlparse,
+)

 from ..utils import (
 from ..utils import (

+    ExtractorError,
+    determine_ext,

     parse_duration,
     unified_strdate,
     parse_duration,
     unified_strdate,

-    compat_urllib_parse,
+    int_or_none,
+    xpath_text,

 )
 
 
 )
 
 

-class RaiIE(SubtitlesInfoExtractor):
-    _VALID_URL = r'(?P<url>http://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html)'
+class RaiTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/(?:[^/]+/)+media/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html'

     _TESTS = [
         {
             'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
     _TESTS = [
         {
             'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html',

-            'md5': 'c064c0b2d09c278fb293116ef5d0a32d',
+            'md5': '96382709b61dd64a6b88e0f791e6df4c',

             'info_dict': {
                 'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
             'info_dict': {
                 'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',

-                'ext': 'mp4',
+                'ext': 'flv',

                 'title': 'Report del 07/04/2014',
                 'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
                 'upload_date': '20140407',
                 'title': 'Report del 07/04/2014',
                 'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
                 'upload_date': '20140407',


@@ -27,16 +34,14 @@ class RaiIE(SubtitlesInfoExtractor):
         },
         {
             'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
         },
         {
             'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',

-            'md5': '8bb9c151924ce241b74dd52ef29ceafa',
+            'md5': 'd9751b78eac9710d62c2447b224dea39',

             'info_dict': {
                 'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
             'info_dict': {
                 'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',

-                'ext': 'mp4',
+                'ext': 'flv',

                 'title': 'TG PRIMO TEMPO',
                 'title': 'TG PRIMO TEMPO',

-                'description': '',

                 'upload_date': '20140612',
                 'duration': 1758,
             },
                 'upload_date': '20140612',
                 'duration': 1758,
             },

-            'skip': 'Error 404',

         },
         {
             'url': 'http://www.rainews.it/dl/rainews/media/state-of-the-net-Antonella-La-Carpia-regole-virali-7aafdea9-0e5d-49d5-88a6-7e65da67ae13.html',
         },
         {
             'url': 'http://www.rainews.it/dl/rainews/media/state-of-the-net-Antonella-La-Carpia-regole-virali-7aafdea9-0e5d-49d5-88a6-7e65da67ae13.html',


@@ -52,64 +57,108 @@ class RaiIE(SubtitlesInfoExtractor):
         },
         {
             'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-b4a49761-e0cc-4b14-8736-2729f6f73132-tg2.html',
         },
         {
             'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-b4a49761-e0cc-4b14-8736-2729f6f73132-tg2.html',

-            'md5': '35694f062977fe6619943f08ed935730',

             'info_dict': {
                 'id': 'b4a49761-e0cc-4b14-8736-2729f6f73132',
                 'ext': 'mp4',
                 'title': 'Alluvione in Sardegna e dissesto idrogeologico',
                 'description': 'Edizione delle ore 20:30 ',
             'info_dict': {
                 'id': 'b4a49761-e0cc-4b14-8736-2729f6f73132',
                 'ext': 'mp4',
                 'title': 'Alluvione in Sardegna e dissesto idrogeologico',
                 'description': 'Edizione delle ore 20:30 ',

+            },
+            'skip': 'invalid urls',
+        },
+        {
+            'url': 'http://www.ilcandidato.rai.it/dl/ray/media/Il-Candidato---Primo-episodio-Le-Primarie-28e5525a-b495-45e8-a7c3-bc48ba45d2b6.html',
+            'md5': '496ab63e420574447f70d02578333437',
+            'info_dict': {
+                'id': '28e5525a-b495-45e8-a7c3-bc48ba45d2b6',
+                'ext': 'flv',
+                'title': 'Il Candidato - Primo episodio: "Le Primarie"',
+                'description': 'md5:364b604f7db50594678f483353164fb8',
+                'upload_date': '20140923',
+                'duration': 386,

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

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
+        media = self._download_json(
+            'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-%s.html?json' % video_id,
+            video_id, 'Downloading video JSON')

 
 

-        media = self._download_json('%s?json' % mobj.group('url'), video_id, 'Downloading video JSON')
-
-        title = media.get('name')
-        description = media.get('desc')
-        thumbnail = media.get('image_300') or media.get('image_medium') or media.get('image')
-        duration = parse_duration(media.get('length'))
-        uploader = media.get('author')
-        upload_date = unified_strdate(media.get('date'))
+        thumbnails = []
+        for image_type in ('image', 'image_medium', 'image_300'):
+            thumbnail_url = media.get(image_type)
+            if thumbnail_url:
+                thumbnails.append({
+                    'url': thumbnail_url,
+                })

 
 

+        subtitles = []

         formats = []
         formats = []

-
-        for format_id in ['wmv', 'm3u8', 'mediaUri', 'h264']:
-            media_url = media.get(format_id)
-            if not media_url:
-                continue
+        media_type = media['type']
+        if 'Audio' in media_type:

             formats.append({
             formats.append({

-                'url': media_url,
-                'format_id': format_id,
-                'ext': 'mp4',
+                'format_id': media.get('formatoAudio'),
+                'url': media['audioUrl'],
+                'ext': media.get('formatoAudio'),

             })
             })

+        elif 'Video' in media_type:
+            def fix_xml(xml):
+                return xml.replace(' tag elementi', '').replace('>/', '</')

 
 

-        if self._downloader.params.get('listsubtitles', False):
-            page = self._download_webpage(url, video_id)
-            self._list_available_subtitles(video_id, page)
-            return
+            relinker = self._download_xml(
+                media['mediaUri'] + '&output=43',
+                video_id, transform_source=fix_xml)

 
 

-        subtitles = {}
-        if self._have_to_download_any_subtitles:
-            page = self._download_webpage(url, video_id)
-            subtitles = self.extract_subtitles(video_id, page)
+            has_subtitle = False
+
+            for element in relinker.findall('element'):
+                media_url = xpath_text(element, 'url')
+                ext = determine_ext(media_url)
+                content_type = xpath_text(element, 'content-type')
+                if ext == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        media_url, video_id, 'mp4', 'm3u8_native',
+                        m3u8_id='hls', fatal=False))
+                elif ext == 'f4m':
+                    formats.extend(self._extract_f4m_formats(
+                        media_url + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44',
+                        video_id, f4m_id='hds', fatal=False))
+                elif ext == 'stl':
+                    has_subtitle = True
+                elif content_type.startswith('video/'):
+                    bitrate = int_or_none(xpath_text(element, 'bitrate'))
+                    formats.append({
+                        'url': media_url,
+                        'tbr': bitrate if bitrate > 0 else None,
+                        'format_id': 'http-%d' % bitrate if bitrate > 0 else 'http',
+                    })
+                elif content_type.startswith('image/'):
+                    thumbnails.append({
+                        'url': media_url,
+                    })
+
+            self._sort_formats(formats)
+
+            if has_subtitle:
+                webpage = self._download_webpage(url, video_id)
+                subtitles = self._get_subtitles(video_id, webpage)
+        else:
+            raise ExtractorError('not a media file')

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

-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'uploader': uploader,
-            'upload_date': upload_date,
-            'duration': duration,
+            'title': media['name'],
+            'description': media.get('desc'),
+            'thumbnails': thumbnails,
+            'uploader': media.get('author'),
+            'upload_date': unified_strdate(media.get('date')),
+            'duration': parse_duration(media.get('length')),

             'formats': formats,
             'subtitles': subtitles,
         }
 
             'formats': formats,
             'subtitles': subtitles,
         }
 

-    def _get_available_subtitles(self, video_id, webpage):
+    def _get_subtitles(self, video_id, webpage):

         subtitles = {}
         m = re.search(r'<meta name="closedcaption" content="(?P<captions>[^"]+)"', webpage)
         if m:
         subtitles = {}
         m = re.search(r'<meta name="closedcaption" content="(?P<captions>[^"]+)"', webpage)
         if m:


@@ -118,5 +167,41 @@ class RaiIE(SubtitlesInfoExtractor):
             SRT_EXT = '.srt'
             if captions.endswith(STL_EXT):
                 captions = captions[:-len(STL_EXT)] + SRT_EXT
             SRT_EXT = '.srt'
             if captions.endswith(STL_EXT):
                 captions = captions[:-len(STL_EXT)] + SRT_EXT

-            subtitles['it'] = 'http://www.rai.tv%s' % compat_urllib_parse.quote(captions)
-        return subtitles
\ No newline at end of file
+            subtitles['it'] = [{
+                'ext': 'srt',
+                'url': 'http://www.rai.tv%s' % compat_urllib_parse.quote(captions),
+            }]
+        return subtitles
+
+
+class RaiIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html'
+    _TESTS = [
+        {
+            'url': 'http://www.report.rai.it/dl/Report/puntata/ContentItem-0c7a664b-d0f4-4b2c-8835-3f82e46f433e.html',
+            'md5': 'e0e7a8a131e249d1aa0ebf270d1d8db7',
+            'info_dict': {
+                'id': '59d69d28-6bb6-409d-a4b5-ed44096560af',
+                'ext': 'flv',
+                'title': 'Il pacco',
+                'description': 'md5:4b1afae1364115ce5d78ed83cd2e5b3a',
+                'upload_date': '20141221',
+            },
+        }
+    ]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if RaiTVIE.suitable(url) else super(RaiIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        iframe_url = self._search_regex(
+            [r'<iframe[^>]+src="([^"]*/dl/[^"]+\?iframe\b[^"]*)"',
+             r'drawMediaRaiTV\(["\'](.+?)["\']'],
+            webpage, 'iframe')
+        if not iframe_url.startswith('http'):
+            iframe_url = compat_urlparse.urljoin(url, iframe_url)
+        return self.url_result(iframe_url)