youtube-dl

commit 121c09c7be1ac2944f3432122104c1952bfd1f04
parent 76bfaf6daf73ac74f7a9068c51d14ab0a5ec5e52
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Sat, 10 Jan 2015 17:51:52 +0100

Merge remote-tracking branch 'Dineshs91/f4m-2.0'

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
1
+
M
youtube_dl/extractor/common.py
 | 
6
++++++
A
youtube_dl/extractor/rte.py
 | 
59
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

3 files changed, 66 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -340,6 +340,7 @@ from .ro220 import Ro220IE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
 from .rtbf import RTBFIE
+from .rte import RteIE
 from .rtlnl import RtlXlIE
 from .rtlnow import RTLnowIE
 from .rtp import RTPIE
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
@@ -742,8 +742,14 @@ class InfoExtractor(object):
             'Unable to download f4m manifest')
 
         formats = []
+        manifest_version = '1.0'
         media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media')
+        if not media_nodes:
+            manifest_version = '2.0'
+            media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')
         for i, media_el in enumerate(media_nodes):
+            if manifest_version == '2.0':
+                manifest_url = '/'.join(manifest_url.split('/')[:-1]) + '/' + media_el.attrib.get('href')
             tbr = int_or_none(media_el.attrib.get('bitrate'))
             format_id = 'f4m-%d' % (i if tbr is None else tbr)
             formats.append({
diff --git a/youtube_dl/extractor/rte.py b/youtube_dl/extractor/rte.py
@@ -0,0 +1,58 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+from ..utils import (
+    float_or_none,
+)
+
+
+class RteIE(InfoExtractor):
+    _VALID_URL = r'http?://(?:www\.)?rte\.ie/player/in/show/(?P<id>[0-9]+)/'
+    _TEST = {
+        'url': 'http://www.rte.ie/player/in/show/10336191/',
+        'info_dict': {
+            'id': '10336191',
+            'ext': 'mp4',
+            'title': 'Nine News',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'description': 'The One O\'Clock News followed by Weather.',
+            'duration': 1622.963,
+        }
+    }
+    
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        title = self._og_search_title(webpage)
+        
+        description = self._search_regex(r'<meta name="description" content="(.*?)" />', webpage, 'description')
+        duration = float_or_none(self._html_search_meta('duration', webpage, 'duration'), 1000)
+        
+        thumbnail_id = self._search_regex(r'<meta name="thumbnail" content="uri:irus:(.*?)" />', webpage, 'thumbnail')
+        thumbnail = 'http://img.rasset.ie/' + thumbnail_id + '.jpg' 
+        
+        feeds_url = self._html_search_meta("feeds-prefix", webpage, 'feeds url') + video_id
+        json_string = self._download_json(feeds_url, video_id)
+        
+        # f4m_url = server + relative_url
+        f4m_url = json_string['shows'][0]['media:group'][0]['rte:server'] + json_string['shows'][0]['media:group'][0]['url']
+        f4m_formats = self._extract_f4m_formats(f4m_url, video_id)
+        f4m_formats = [{
+            'format_id': f['format_id'],
+            'url': f['url'],
+            'ext': 'mp4',
+            'width': f['width'],
+            'height': f['height'],
+        } for f in f4m_formats ]
+        
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': f4m_formats,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+        }+
\ No newline at end of file