aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/tvnoe.py
diff options
context:
space:
mode:
authorMatěj Cepl <mcepl@cepl.eu>2016-09-01 17:31:08 +0200
committerMatěj Cepl <mcepl@cepl.eu>2016-09-04 19:06:40 +0200
commit78e762d23c48f85c61a8afcae29307912000a7dd (patch)
tree4fdc0d0ede1ad339ef017f9e0878d88d6b539224 /youtube_dl/extractor/tvnoe.py
parent48094901086534533ca89283067f2ab732857654 (diff)
Add new extractor for TV Noe (Czech Christian TV).
Fixes #10520
Diffstat (limited to 'youtube_dl/extractor/tvnoe.py')
-rw-r--r--youtube_dl/extractor/tvnoe.py44
1 files changed, 44 insertions, 0 deletions
diff --git a/youtube_dl/extractor/tvnoe.py b/youtube_dl/extractor/tvnoe.py
new file mode 100644
index 000000000..d50261ddd
--- /dev/null
+++ b/youtube_dl/extractor/tvnoe.py
@@ -0,0 +1,44 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .jwplatform import JWPlatformBaseIE
+from ..utils import clean_html, get_element_by_class, js_to_json
+
+
+class TVNoeIE(JWPlatformBaseIE):
+ _VALID_URL = r'https?://(www\.)?tvnoe\.cz/video/(?P<id>[0-9]+)'
+ _TEST = {
+ 'url': 'http://www.tvnoe.cz/video/10362',
+ 'md5': 'aee983f279aab96ec45ab6e2abb3c2ca',
+ 'info_dict': {
+ 'id': '10362',
+ 'ext': 'mp4',
+ 'series': 'Noční univerzita',
+ 'title': 'prof. Tomáš Halík, Th.D. - ' +
+ 'Návrat náboženství a střet civilizací',
+ 'description': 'md5:f337bae384e1a531a52c55ebc50fff41',
+ }
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+
+ iframe_url = self._search_regex(r'<iframe[^>]+src="([^"]+)"',
+ webpage, 'iframe src attribute')
+
+ ifs_page = self._download_webpage(iframe_url, video_id)
+ jwplayer_data = self._parse_json(self._find_jwplayer_data(ifs_page),
+ video_id, transform_source=js_to_json)
+ info_dict = self._parse_jwplayer_data(
+ jwplayer_data, video_id, require_title=False, base_url=iframe_url)
+
+ info_dict.update({
+ 'id': video_id,
+ 'title': clean_html(
+ get_element_by_class('field-name-field-podnazev', webpage)),
+ 'description': clean_html(get_element_by_class('field-name-body',
+ webpage)),
+ 'series': clean_html(get_element_by_class('title', webpage))
+ })
+ return info_dict