aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl')
-rw-r--r--youtube_dl/extractor/canvas.py32
1 files changed, 27 insertions, 5 deletions
diff --git a/youtube_dl/extractor/canvas.py b/youtube_dl/extractor/canvas.py
index ec6d24d96..ef0691dcd 100644
--- a/youtube_dl/extractor/canvas.py
+++ b/youtube_dl/extractor/canvas.py
@@ -1,11 +1,13 @@
from __future__ import unicode_literals
+import re
+
from .common import InfoExtractor
from ..utils import float_or_none
class CanvasIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?canvas\.be/video/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+ _VALID_URL = r'https?://(?:www\.)?(?P<site_id>canvas|een)\.be/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.canvas.be/video/de-afspraak/najaar-2015/de-afspraak-veilt-voor-de-warmste-week',
'md5': 'ea838375a547ac787d4064d8c7860a6c',
@@ -38,22 +40,42 @@ class CanvasIE(InfoExtractor):
'params': {
'skip_download': True,
}
+ }, {
+ 'url': 'https://www.een.be/sorry-voor-alles/herbekijk-sorry-voor-alles',
+ 'info_dict': {
+ 'id': 'mz-ast-11a587f8-b921-4266-82e2-0bce3e80d07f',
+ 'display_id': 'herbekijk-sorry-voor-alles',
+ 'ext': 'mp4',
+ 'title': 'Herbekijk Sorry voor alles',
+ 'description': 'md5:8bb2805df8164e5eb95d6a7a29dc0dd3',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 3788.06,
+ },
+ 'params': {
+ 'skip_download': True,
+ }
+ }, {
+ 'url': 'https://www.canvas.be/check-point/najaar-2016/de-politie-uw-vriend',
+ 'only_matching': True,
}]
def _real_extract(self, url):
- display_id = self._match_id(url)
+ mobj = re.match(self._VALID_URL, url)
+ site_id, display_id = mobj.group('site_id'), mobj.group('id')
webpage = self._download_webpage(url, display_id)
- title = self._search_regex(
+ title = (self._search_regex(
r'<h1[^>]+class="video__body__header__title"[^>]*>(.+?)</h1>',
- webpage, 'title', default=None) or self._og_search_title(webpage)
+ webpage, 'title', default=None) or self._og_search_title(
+ webpage)).strip()
video_id = self._html_search_regex(
r'data-video=(["\'])(?P<id>.+?)\1', webpage, 'video id', group='id')
data = self._download_json(
- 'https://mediazone.vrt.be/api/v1/canvas/assets/%s' % video_id, display_id)
+ 'https://mediazone.vrt.be/api/v1/%s/assets/%s'
+ % (site_id, video_id), display_id)
formats = []
for target in data['targetUrls']: