Imported Upstream version 2015.05.15

[youtubedl] / youtube_dl / extractor / rtlnl.py

diff --git a/youtube_dl/extractor/rtlnl.py b/youtube_dl/extractor/rtlnl.py
index 0ab1eb69c8c82ae0bc04ec135971cd919b17a155..cfce4550ada568cfe13fae859a2bb745671074b5 100644 (file)
--- a/youtube_dl/extractor/rtlnl.py
+++ b/youtube_dl/extractor/rtlnl.py
@@ -1,16 +1,25 @@
+# coding: utf-8

 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import re
-

 from .common import InfoExtractor
 from .common import InfoExtractor

-from ..utils import parse_duration
+from ..utils import (
+    int_or_none,
+    parse_duration,
+)

 
 
 
 

-class RtlXlIE(InfoExtractor):
-    IE_NAME = 'rtlxl.nl'
-    _VALID_URL = r'https?://www\.rtlxl\.nl/#!/[^/]+/(?P<uuid>[^/?]+)'
+class RtlNlIE(InfoExtractor):
+    IE_NAME = 'rtl.nl'
+    IE_DESC = 'rtl.nl and rtlxl.nl'
+    _VALID_URL = r'''(?x)
+        https?://(www\.)?
+        (?:
+            rtlxl\.nl/\#!/[^/]+/|
+            rtl\.nl/system/videoplayer/[^?#]+?/video_embed\.html\#uuid=
+        )
+        (?P<id>[0-9a-f-]+)'''

 
 

-    _TEST = {
+    _TESTS = [{

         'url': 'http://www.rtlxl.nl/#!/rtl-nieuws-132237/6e4203a6-0a5e-3596-8424-c599a59e0677',
         'md5': 'cc16baa36a6c169391f0764fa6b16654',
         'info_dict': {
         'url': 'http://www.rtlxl.nl/#!/rtl-nieuws-132237/6e4203a6-0a5e-3596-8424-c599a59e0677',
         'md5': 'cc16baa36a6c169391f0764fa6b16654',
         'info_dict': {


@@ -22,28 +31,38 @@ class RtlXlIE(InfoExtractor):
             'upload_date': '20140814',
             'duration': 576.880,
         },
             'upload_date': '20140814',
             'duration': 576.880,
         },

-    }
+    }, {
+        'url': 'http://www.rtl.nl/system/videoplayer/derden/rtlnieuws/video_embed.html#uuid=84ae5571-ac25-4225-ae0c-ef8d9efb2aed/autoplay=false',
+        'md5': 'dea7474214af1271d91ef332fb8be7ea',
+        'info_dict': {
+            'id': '84ae5571-ac25-4225-ae0c-ef8d9efb2aed',
+            'ext': 'mp4',
+            'timestamp': 1424039400,
+            'title': 'RTL Nieuws - Nieuwe beelden Kopenhagen: chaos direct na aanslag',
+            'thumbnail': 're:^https?://screenshots\.rtl\.nl/system/thumb/sz=[0-9]+x[0-9]+/uuid=84ae5571-ac25-4225-ae0c-ef8d9efb2aed$',
+            'upload_date': '20150215',
+            'description': 'Er zijn nieuwe beelden vrijgegeven die vlak na de aanslag in Kopenhagen zijn gemaakt. Op de video is goed te zien hoe omstanders zich bekommeren om één van de slachtoffers, terwijl de eerste agenten ter plaatse komen.',
+        }
+    }]

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

-        mobj = re.match(self._VALID_URL, url)
-        uuid = mobj.group('uuid')
-
+        uuid = self._match_id(url)

         info = self._download_json(
             'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=flash/' % uuid,
             uuid)
 
         material = info['material'][0]
         info = self._download_json(
             'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=flash/' % uuid,
             uuid)
 
         material = info['material'][0]

-        episode_info = info['episodes'][0]
-

         progname = info['abstracts'][0]['name']
         subtitle = material['title'] or info['episodes'][0]['name']
         progname = info['abstracts'][0]['name']
         subtitle = material['title'] or info['episodes'][0]['name']

+        description = material.get('synopsis') or info['episodes'][0]['synopsis']

 
 

-        videopath = material['videopath']
-        f4m_url = 'http://manifest.us.rtl.nl' + videopath
+        # Use unencrypted m3u8 streams (See https://github.com/rg3/youtube-dl/issues/4118)
+        videopath = material['videopath'].replace('.f4m', '.m3u8')
+        m3u8_url = 'http://manifest.us.rtl.nl' + videopath

 
 

-        formats = self._extract_f4m_formats(f4m_url, uuid)
+        formats = self._extract_m3u8_formats(m3u8_url, uuid, ext='mp4')

 
 

-        video_urlpart = videopath.split('/flash/')[1][:-4]
+        video_urlpart = videopath.split('/flash/')[1][:-5]

         PG_URL_TEMPLATE = 'http://pg.us.rtl.nl/rtlxl/network/%s/progressive/%s.mp4'
 
         formats.extend([
         PG_URL_TEMPLATE = 'http://pg.us.rtl.nl/rtlxl/network/%s/progressive/%s.mp4'
 
         formats.extend([


@@ -54,14 +73,32 @@ class RtlXlIE(InfoExtractor):
             {
                 'url': PG_URL_TEMPLATE % ('a3m', video_urlpart),
                 'format_id': 'pg-hd',
             {
                 'url': PG_URL_TEMPLATE % ('a3m', video_urlpart),
                 'format_id': 'pg-hd',

+                'quality': 0,

             }
         ])
             }
         ])

+        self._sort_formats(formats)
+
+        thumbnails = []
+        meta = info.get('meta', {})
+        for p in ('poster_base_url', '"thumb_base_url"'):
+            if not meta.get(p):
+                continue
+
+            thumbnails.append({
+                'url': self._proto_relative_url(meta[p] + uuid),
+                'width': int_or_none(self._search_regex(
+                    r'/sz=([0-9]+)', meta[p], 'thumbnail width', fatal=False)),
+                'height': int_or_none(self._search_regex(
+                    r'/sz=[0-9]+x([0-9]+)',
+                    meta[p], 'thumbnail height', fatal=False))
+            })

 
         return {
             'id': uuid,
             'title': '%s - %s' % (progname, subtitle),
             'formats': formats,
             'timestamp': material['original_date'],
 
         return {
             'id': uuid,
             'title': '%s - %s' % (progname, subtitle),
             'formats': formats,
             'timestamp': material['original_date'],

-            'description': episode_info['synopsis'],
+            'description': description,

             'duration': parse_duration(material.get('duration')),
             'duration': parse_duration(material.get('duration')),

+            'thumbnails': thumbnails,

         }
         }