youtube-dl

commit fa37c26c4d350d89017de500a76bb57edcbca280
parent 479bf783d2d90c303e6b152e5e697265832747d2
Author: Sergey M <dstftw@gmail.com>
Date:   Thu, 13 Aug 2015 00:57:00 +0600

Merge pull request #6537 from ngld/rtvnhnl

[rtvnhnl] Added new extractor
Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
1
+
A
youtube_dl/extractor/rtvnh.py
 | 
36
++++++++++++++++++++++++++++++++++++

2 files changed, 37 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -491,6 +491,7 @@ from .rtl2 import RTL2IE
 from .rtp import RTPIE
 from .rts import RTSIE
 from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE
+from .rtvnh import RTVNHIE
 from .ruhd import RUHDIE
 from .rutube import (
     RutubeIE,
diff --git a/youtube_dl/extractor/rtvnh.py b/youtube_dl/extractor/rtvnh.py
@@ -0,0 +1,36 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class RTVNHIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?rtvnh\.nl/video/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.rtvnh.nl/video/131946',
+        'md5': '6e1d0ab079e2a00b6161442d3ceacfc1',
+        'info_dict': {
+            'id': '131946',
+            'ext': 'mp4',
+            'title': 'Grote zoektocht in zee bij Zandvoort naar vermiste vrouw',
+            'thumbnail': 're:^https?:.*\.jpg$'
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        meta = self._parse_json(self._download_webpage('http://www.rtvnh.nl/video/json?m=' + video_id, video_id), video_id)
+        formats = self._extract_smil_formats('http://www.rtvnh.nl/video/smil?m=' + video_id, video_id)
+
+        for item in meta['source']['fb']:
+            if item.get('type') == 'hls':
+                formats.extend(self._extract_m3u8_formats(item['file'], video_id, ext='mp4', entry_protocol='m3u8_native'))
+            elif item.get('type') == '':
+                formats.append({'url': item['file']})
+        
+        return {
+            'id': video_id,
+            'title': meta['title'].strip(),
+            'thumbnail': meta['image'],
+            'formats': formats
+        }