aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authordinesh <dsdiscoverdinesh@gmail.com>2014-10-26 13:35:00 +0530
committerdinesh <dsdiscoverdinesh@gmail.com>2014-10-26 13:35:00 +0530
commitb13ccb1b87199dcfd10b12ed5c3002ff6f951769 (patch)
treefee7b5f62cf94ad15564187fb0c44402351c8b66 /youtube_dl/extractor
parentf64f8a46623d4940e6f53c3bf4b23050b054b0f6 (diff)
[BelgianNational] New extractor added
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/belgiannational.py64
2 files changed, 65 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 691fef5ca..ec299b72f 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -27,6 +27,7 @@ from .bandcamp import BandcampIE, BandcampAlbumIE
from .bbccouk import BBCCoUkIE
from .beeg import BeegIE
from .behindkink import BehindKinkIE
+from .belgiannational import BelgianNationalIE
from .bild import BildIE
from .bilibili import BiliBiliIE
from .blinkx import BlinkxIE
diff --git a/youtube_dl/extractor/belgiannational.py b/youtube_dl/extractor/belgiannational.py
new file mode 100644
index 000000000..2367d1f2b
--- /dev/null
+++ b/youtube_dl/extractor/belgiannational.py
@@ -0,0 +1,64 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+class BelgianNationalIE(InfoExtractor):
+ _VALID_URL = r'http://(?:deredactie|sporza|cobra)\.be/cm/(.*)/(?P<video_id>[^\']+)'
+ _TESTS = [
+ # deredactie.be
+ {
+ 'url': 'http://deredactie.be/cm/vrtnieuws/videozone/programmas/journaal/EP_141025_JOL',
+ 'md5': '4cebde1eb60a53782d4f3992cbd46ec8',
+ 'info_dict': {
+ 'id': 'EP_141025_JOL',
+ 'title': 'Het journaal L - 25/10/14',
+ 'ext': 'mp4',
+ 'duration': 929,
+ }
+ },
+ # sporza.be
+ {
+ 'url': 'http://sporza.be/cm/sporza/videozone/programmas/extratime/EP_141020_Extra_time',
+ 'md5': '11f53088da9bf8e7cfc42456697953ff',
+ 'info_dict': {
+ 'id': 'EP_141020_Extra_time',
+ 'title': 'Bekijk Extra Time van 20 oktober',
+ 'ext': 'mp4',
+ 'duration': 3238,
+ }
+
+ },
+ # cobra.be
+ {
+ 'url': 'http://cobra.be/cm/cobra/videozone/rubriek/film-videozone/141022-mv-ellis-cafecorsari',
+ 'md5': '78a2b060a5083c4f055449a72477409d',
+ 'info_dict': {
+ 'id': '141022-mv-ellis-cafecorsari',
+ 'title': 'Bret Easton Ellis in Café Corsari',
+ 'ext': 'mp4',
+ 'duration': 661,
+ }
+ }
+ ]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('video_id')
+
+ webpage = self._download_webpage(url, video_id)
+ title = self._og_search_title(webpage)
+
+ video_url = self._search_regex(r'data-video-src="(.*?)"', webpage, 'Video url') + '/manifest.f4m'
+ duration = int_or_none(self._search_regex(r'data-video-sitestat-duration="(.*?)"', webpage, 'Duration'))
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'duration': duration,
+ } \ No newline at end of file