youtube-dl

commit b9d76a95717afdbfb63410d1753966b5596e8e32
parent 4eb5c65beec671e534ad4859c073adb362e537ec
Author: Sergey M․ <dstftw@gmail.com>
Date:   Mon, 27 Apr 2015 03:36:46 +0600

Merge branch 'fstirlitz-philharmoniedeparis'

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
1
+
A
youtube_dl/extractor/philharmoniedeparis.py
 | 
78
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

2 files changed, 79 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -377,6 +377,7 @@ from .orf import (
 from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
 from .pbs import PBSIE
+from .philharmoniedeparis import PhilharmonieDeParisIE
 from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
 from .planetaplay import PlanetaPlayIE
diff --git a/youtube_dl/extractor/philharmoniedeparis.py b/youtube_dl/extractor/philharmoniedeparis.py
@@ -0,0 +1,78 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    parse_iso8601,
+    xpath_text,
+)
+
+
+class PhilharmonieDeParisIE(InfoExtractor):
+    IE_DESC = 'Philharmonie de Paris'
+    _VALID_URL = r'http://live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://live.philharmoniedeparis.fr/concert/1032066.html',
+        'info_dict': {
+            'id': '1032066',
+            'ext': 'flv',
+            'title': 'md5:d1f5585d87d041d07ce9434804bc8425',
+            'timestamp': 1428179400,
+            'upload_date': '20150404',
+            'duration': 6592.278,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://live.philharmoniedeparis.fr/Concert/1030324.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=1030324&track=&lang=fr',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        concert = self._download_xml(
+            'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=%s' % video_id,
+            video_id).find('./concert')
+
+        formats = []
+        info_dict = {
+            'id': video_id,
+            'title': xpath_text(concert, './titre', 'title', fatal=True),
+            'formats': formats,
+        }
+
+        fichiers = concert.find('./fichiers')
+        stream = fichiers.attrib['serveurstream']
+        for fichier in fichiers.findall('./fichier'):
+            info_dict['duration'] = float_or_none(fichier.get('timecodefin'))
+            for quality, (format_id, suffix) in enumerate([('lq', ''), ('hq', '_hd')]):
+                format_url = fichier.get('url%s' % suffix)
+                if not format_url:
+                    continue
+                formats.append({
+                    'url': stream,
+                    'play_path': format_url,
+                    'ext': 'flv',
+                    'format_id': format_id,
+                    'width': int_or_none(concert.get('largeur%s' % suffix)),
+                    'height': int_or_none(concert.get('hauteur%s' % suffix)),
+                    'quality': quality,
+                })
+        self._sort_formats(formats)
+
+        date, hour = concert.get('date'), concert.get('heure')
+        if date and hour:
+            info_dict['timestamp'] = parse_iso8601(
+                '%s-%s-%sT%s:00' % (date[0:4], date[4:6], date[6:8], hour))
+        elif date:
+            info_dict['upload_date'] = date
+
+        return info_dict