Imported Upstream version 2015.07.21

[youtubedl] / youtube_dl / extractor / rai.py

diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py
index ba3dd707f8b5d38363dacce62e9fe684265c6a96..1631faf29f61c9cc15bca99394966c1917ca1a08 100644 (file)
--- a/youtube_dl/extractor/rai.py
+++ b/youtube_dl/extractor/rai.py
@@ -2,16 +2,18 @@ from __future__ import unicode_literals
 
 import re
 
 
 import re
 

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

 from ..utils import (
     parse_duration,
     unified_strdate,
 from ..utils import (
     parse_duration,
     unified_strdate,

-    compat_urllib_parse,

 )
 
 
 )
 
 

-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 RaiIE(InfoExtractor):
+    _VALID_URL = r'(?P<url>(?P<host>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)'

     _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',


@@ -60,42 +62,78 @@ class RaiIE(SubtitlesInfoExtractor):
                 'description': 'Edizione delle ore 20:30 ',
             }
         },
                 'description': 'Edizione delle ore 20:30 ',
             }
         },

+        {
+            'url': 'http://www.ilcandidato.rai.it/dl/ray/media/Il-Candidato---Primo-episodio-Le-Primarie-28e5525a-b495-45e8-a7c3-bc48ba45d2b6.html',
+            'md5': '02b64456f7cc09f96ff14e7dd489017e',
+            'info_dict': {
+                'id': '28e5525a-b495-45e8-a7c3-bc48ba45d2b6',
+                'ext': 'flv',
+                'title': 'Il Candidato - Primo episodio: "Le Primarie"',
+                'description': 'Primo appuntamento con "Il candidato" con Filippo Timi, alias Piero Zucca presidente!',
+                'uploader': 'RaiTre',
+            }
+        }

     ]
 
     ]
 

+    def _extract_relinker_url(self, webpage):
+        return self._proto_relative_url(self._search_regex(
+            [r'name="videourl" content="([^"]+)"', r'var\s+videoURL(?:_MP4)?\s*=\s*"([^"]+)"'],
+            webpage, 'relinker url', default=None))
+

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

+        host = mobj.group('host')
+
+        webpage = self._download_webpage(url, video_id)

 
 

-        media = self._download_json('%s?json' % mobj.group('url'), video_id, 'Downloading video JSON')
+        relinker_url = self._extract_relinker_url(webpage)

 
 

-        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'))
+        if not relinker_url:
+            iframe_path = self._search_regex(
+                r'<iframe[^>]+src="/?(dl/[^"]+\?iframe\b[^"]*)"',
+                webpage, 'iframe')
+            webpage = self._download_webpage(
+                '%s/%s' % (host, iframe_path), video_id)
+            relinker_url = self._extract_relinker_url(webpage)

 
 

-        formats = []
+        relinker = self._download_json(
+            '%s&output=47' % relinker_url, video_id)

 
 

-        for format_id in ['wmv', 'm3u8', 'mediaUri', 'h264']:
-            media_url = media.get(format_id)
-            if not media_url:
-                continue
-            formats.append({
+        media_url = relinker['video'][0]
+        ct = relinker.get('ct')
+        if ct == 'f4m':
+            formats = self._extract_f4m_formats(
+                media_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id)
+        else:
+            formats = [{

                 'url': media_url,
                 'url': media_url,

-                'format_id': format_id,
-                'ext': 'mp4',
-            })
+                'format_id': ct,
+            }]

 
 

-        if self._downloader.params.get('listsubtitles', False):
-            page = self._download_webpage(url, video_id)
-            self._list_available_subtitles(video_id, page)
-            return
+        json_link = self._html_search_meta(
+            'jsonlink', webpage, 'JSON link', default=None)
+        if json_link:
+            media = self._download_json(
+                host + json_link, 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'))
+        else:
+            title = (self._search_regex(
+                r'var\s+videoTitolo\s*=\s*"(.+?)";',
+                webpage, 'title', default=None) or self._og_search_title(webpage)).replace('\\"', '"')
+            description = self._og_search_description(webpage)
+            thumbnail = self._og_search_thumbnail(webpage)
+            duration = None
+            uploader = self._html_search_meta('Editore', webpage, 'uploader')
+            upload_date = unified_strdate(self._html_search_meta(
+                'item-date', webpage, 'upload date', default=None))

 
 

-        subtitles = {}
-        if self._have_to_download_any_subtitles:
-            page = self._download_webpage(url, video_id)
-            subtitles = self.extract_subtitles(video_id, page)
+        subtitles = self.extract_subtitles(video_id, webpage)

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


@@ -109,7 +147,7 @@ class RaiIE(SubtitlesInfoExtractor):
             'subtitles': subtitles,
         }
 
             '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 +156,8 @@ 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