aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/iprima.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/iprima.py')
-rw-r--r--youtube_dl/extractor/iprima.py22
1 files changed, 12 insertions, 10 deletions
diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py
index 8529bedfc..36baf3245 100644
--- a/youtube_dl/extractor/iprima.py
+++ b/youtube_dl/extractor/iprima.py
@@ -6,16 +6,15 @@ from random import random
from math import floor
from .common import InfoExtractor
-from ..compat import (
- compat_urllib_request,
-)
from ..utils import (
ExtractorError,
+ remove_end,
+ sanitized_Request,
)
class IPrimaIE(InfoExtractor):
- _VALID_URL = r'https?://play\.iprima\.cz/[^?#]+/(?P<id>[^?#]+)'
+ _VALID_URL = r'https?://play\.iprima\.cz/(?:[^/]+/)*(?P<id>[^?#]+)'
_TESTS = [{
'url': 'http://play.iprima.cz/particka/particka-92',
@@ -23,7 +22,7 @@ class IPrimaIE(InfoExtractor):
'id': '39152',
'ext': 'flv',
'title': 'Partička (92)',
- 'description': 'md5:3740fda51464da35a2d4d0670b8e4fd6',
+ 'description': 'md5:74e9617e51bca67c3ecfb2c6f9766f45',
'thumbnail': 'http://play.iprima.cz/sites/default/files/image_crops/image_620x349/3/491483_particka-92_image_620x349.jpg',
},
'params': {
@@ -35,13 +34,14 @@ class IPrimaIE(InfoExtractor):
'id': '9718337',
'ext': 'flv',
'title': 'Tchibo Partička - Jarní móda',
- 'description': 'md5:589f8f59f414220621ff8882eb3ce7be',
'thumbnail': 're:^http:.*\.jpg$',
},
'params': {
'skip_download': True, # requires rtmpdump
},
- 'skip': 'Do not have permission to access this page',
+ }, {
+ 'url': 'http://play.iprima.cz/zpravy-ftv-prima-2752015',
+ 'only_matching': True,
}]
def _real_extract(self, url):
@@ -59,7 +59,7 @@ class IPrimaIE(InfoExtractor):
(floor(random() * 1073741824), floor(random() * 1073741824))
)
- req = compat_urllib_request.Request(player_url)
+ req = sanitized_Request(player_url)
req.add_header('Referer', url)
playerpage = self._download_webpage(req, video_id)
@@ -102,8 +102,10 @@ class IPrimaIE(InfoExtractor):
return {
'id': real_id,
- 'title': self._og_search_title(webpage),
+ 'title': remove_end(self._og_search_title(webpage), ' | Prima PLAY'),
'thumbnail': self._og_search_thumbnail(webpage),
'formats': formats,
- 'description': self._og_search_description(webpage),
+ 'description': self._search_regex(
+ r'<p[^>]+itemprop="description"[^>]*>([^<]+)',
+ webpage, 'description', default=None),
}