aboutsummaryrefslogtreecommitdiffhomepage
path: root/youtube_dl/extractor/cjsw.py
diff options
context:
space:
mode:
authorFilippo Valsorda <[email protected]>2018-01-07 15:03:28 +0100
committerGitHub <[email protected]>2018-01-07 15:03:28 +0100
commit97bc05116e15df3cf1b7b7216c60fad7ee0acc9f (patch)
tree453059413184d22a44241d251a82196c5d2461eb /youtube_dl/extractor/cjsw.py
parent7608a91ee7b40c74a35c30b44731606382702592 (diff)
parent0a5b1295b7c1aa6395b65ee137087c540b37b32b (diff)
downloadyoutube-dl-totalwebcasting.tar.gz
youtube-dl-totalwebcasting.zip
Merge branch 'master' into totalwebcastingtotalwebcasting
Diffstat (limited to 'youtube_dl/extractor/cjsw.py')
-rw-r--r--youtube_dl/extractor/cjsw.py72
1 files changed, 72 insertions, 0 deletions
diff --git a/youtube_dl/extractor/cjsw.py b/youtube_dl/extractor/cjsw.py
new file mode 100644
index 000000000..505bdbe16
--- /dev/null
+++ b/youtube_dl/extractor/cjsw.py
@@ -0,0 +1,72 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ determine_ext,
+ unescapeHTML,
+)
+
+
+class CJSWIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?cjsw\.com/program/(?P<program>[^/]+)/episode/(?P<id>\d+)'
+ _TESTS = [{
+ 'url': 'http://cjsw.com/program/freshly-squeezed/episode/20170620',
+ 'md5': 'cee14d40f1e9433632c56e3d14977120',
+ 'info_dict': {
+ 'id': '91d9f016-a2e7-46c5-8dcb-7cbcd7437c41',
+ 'ext': 'mp3',
+ 'title': 'Freshly Squeezed – Episode June 20, 2017',
+ 'description': 'md5:c967d63366c3898a80d0c7b0ff337202',
+ 'series': 'Freshly Squeezed',
+ 'episode_id': '20170620',
+ },
+ }, {
+ # no description
+ 'url': 'http://cjsw.com/program/road-pops/episode/20170707/',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ program, episode_id = mobj.group('program', 'id')
+ audio_id = '%s/%s' % (program, episode_id)
+
+ webpage = self._download_webpage(url, episode_id)
+
+ title = unescapeHTML(self._search_regex(
+ (r'<h1[^>]+class=["\']episode-header__title["\'][^>]*>(?P<title>[^<]+)',
+ r'data-audio-title=(["\'])(?P<title>(?:(?!\1).)+)\1'),
+ webpage, 'title', group='title'))
+
+ audio_url = self._search_regex(
+ r'<button[^>]+data-audio-src=(["\'])(?P<url>(?:(?!\1).)+)\1',
+ webpage, 'audio url', group='url')
+
+ audio_id = self._search_regex(
+ r'/([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})\.mp3',
+ audio_url, 'audio id', default=audio_id)
+
+ formats = [{
+ 'url': audio_url,
+ 'ext': determine_ext(audio_url, 'mp3'),
+ 'vcodec': 'none',
+ }]
+
+ description = self._html_search_regex(
+ r'<p>(?P<description>.+?)</p>', webpage, 'description',
+ default=None)
+ series = self._search_regex(
+ r'data-showname=(["\'])(?P<name>(?:(?!\1).)+)\1', webpage,
+ 'series', default=program, group='name')
+
+ return {
+ 'id': audio_id,
+ 'title': title,
+ 'description': description,
+ 'formats': formats,
+ 'series': series,
+ 'episode_id': episode_id,
+ }