aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/europa.py60
2 files changed, 61 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index a73a1317e..495a18c17 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -158,6 +158,7 @@ from .eroprofile import EroProfileIE
from .escapist import EscapistIE
from .espn import ESPNIE
from .esri import EsriVideoIE
+from .europa import EuropaIE
from .everyonesmixtape import EveryonesMixtapeIE
from .exfm import ExfmIE
from .expotv import ExpoTVIE
diff --git a/youtube_dl/extractor/europa.py b/youtube_dl/extractor/europa.py
new file mode 100644
index 000000000..c437c4886
--- /dev/null
+++ b/youtube_dl/extractor/europa.py
@@ -0,0 +1,60 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urlparse,
+ xpath_text
+)
+
+
+class EuropaIE(InfoExtractor):
+ _VALID_URL = r'https?://ec\.europa\.eu/avservices/video/player\.cfm\?(?:[^&]|&(?!ref))*ref=(?P<id>[A-Za-z0-9]+)'
+ _TEST = {
+ 'url': 'http://ec.europa.eu/avservices/video/player.cfm?ref=I107758',
+ 'md5': '728cca2fd41d5aa7350cec1141fbe620',
+ 'info_dict': {
+ 'id': 'I107758',
+ 'ext': 'mp4',
+ 'title': 'TRADE - Wikileaks on TTIP',
+ 'description': 'NEW LIVE EC Midday press briefing of 11/08/2015',
+ 'thumbnail': 're:^http://defiris\.ec\.streamcloud\.be/findmedia/18/107758/THUMB_[0-9A-Z]+\.jpg$'
+ }
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+ lang = query.get('sitelang', ['en'])[0]
+
+ playlist = self._download_xml('http://ec.europa.eu/avservices/video/player/playlist.cfm?ID=' + video_id, video_id)
+ videos = {}
+ formats = []
+
+ for item in playlist.findall('info/title/item'):
+ videos[xpath_text(item, 'lg')] = {'title': xpath_text(item, 'label').strip()}
+
+ for item in playlist.findall('info/description/item'):
+ videos[xpath_text(item, 'lg')]['description'] = xpath_text(item, 'label').strip()
+
+ for item in playlist.findall('files/file'):
+ lg = xpath_text(item, 'lg')
+ vid = videos[lg]
+ vid['format_note'] = xpath_text(item, 'lglabel')
+ vid['url'] = xpath_text(item, 'url')
+
+ if lg == lang:
+ vid['language_preference'] = 10
+
+ formats.append(vid)
+
+ formats.reverse()
+ def_video = videos.get(lang, videos['int'])
+
+ return {
+ 'id': video_id,
+ 'title': def_video['title'],
+ 'description': def_video['description'],
+ 'thumbnail': xpath_text(playlist, 'info/thumburl', 'thumburl'),
+ 'formats': formats
+ }