New extractor: live.philharmoniedeparis.fr

2 files changed, 78 insertions, 0 deletions

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index ab80fd5e0..641c45f43 100644
--- 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
new file mode 100644
index 000000000..7fc2f32ab
--- /dev/null
+++ b/youtube_dl/extractor/philharmoniedeparis.py
@@ -0,0 +1,77 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    parse_iso8601,
+    unified_strdate,
+)
+
+class PhilharmonieDeParisIE(InfoExtractor):
+    _VALID_URL = r'http://live\.philharmoniedeparis\.fr/concert/(?P<id>\d+)(?:/|\.html)'
+    _TESTS = [{
+        'url': 'http://live.philharmoniedeparis.fr/concert/1032066.html',
+        'info_dict': {
+            'id': '1032066',
+            'ext': 'mp4',
+            'title': "Week-end Bach. Passion selon saint Jean. Akademie für alte Musik Berlin, Rias Kammerchor, René Jacobs",
+            'upload_date': '20150404',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        fichier_nom = self._html_search_regex(r'\sflashvars\s*:\s*\{\s*fichier_nom\s*:\s*\'(.*?)\'\s*,', webpage, 'fichier_nom')
+
+        playlist = self._download_xml('http://live.philharmoniedeparis.fr' + fichier_nom, video_id)
+
+        concert = playlist.find('.//concert')
+
+        formats = []
+        info_dict = {
+            'id': video_id,
+            'title': concert.find('./titre').text,
+            'formats': formats,
+        }
+
+        if concert.attrib.get('heure'):
+            info_dict['timestamp'] = parse_iso8601(('%s-%s-%s%s') % (
+                concert.attrib['date'][0:4],
+                concert.attrib['date'][4:6],
+                concert.attrib['date'][6:8],
+                concert.attrib['heure']
+            ))
+        else:
+            info_dict['upload_date'] = concert.attrib['date']
+
+        fichiers = concert.find('./fichiers')
+        for fichier in fichiers.findall('./fichier'):
+            # Sometimes <ficher>s have no attributes at all. Skip them.
+            if 'url' not in fichier.attrib:
+                continue
+
+            formats.append({
+                'format_id': 'lq',
+                'url': fichiers.attrib['serveurstream'],
+                'ext': determine_ext(fichier.attrib['url']),
+                'play_path': fichier.attrib['url'],
+                'width': int_or_none(concert.attrib['largeur']),
+                'height': int_or_none(concert.attrib['hauteur']),
+                'quality': 1,
+            })
+
+            formats.append({
+                'format_id': 'hq',
+                'url': fichiers.attrib['serveurstream'],
+                'ext': determine_ext(fichier.attrib['url_hd']),
+                'play_path': fichier.attrib['url_hd'],
+                'width': int_or_none(concert.attrib['largeur_hd']),
+                'height': int_or_none(concert.attrib['hauteur_hd']),
+                'quality': 2,
+            })
+
+        return info_dict