aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorRemita Amine <remitamine@gmail.com>2016-07-14 23:59:12 +0100
committerRemita Amine <remitamine@gmail.com>2016-07-14 23:59:47 +0100
commit224db034abf7dff24898ae51cbe17fb1cc0d9e00 (patch)
tree616a75a4bfc53a29971ccf091b0091a59e05f5dc /youtube_dl/extractor
parentad27649be307a55b04fa497d244ccca33b4260b0 (diff)
[syfy] fix extraction(closes #9087)(closes #3820)(closes #2388)
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/syfy.py78
1 files changed, 44 insertions, 34 deletions
diff --git a/youtube_dl/extractor/syfy.py b/youtube_dl/extractor/syfy.py
index 5ca079f88..53723b66e 100644
--- a/youtube_dl/extractor/syfy.py
+++ b/youtube_dl/extractor/syfy.py
@@ -1,46 +1,56 @@
from __future__ import unicode_literals
-import re
+from .theplatform import ThePlatformIE
+from ..utils import (
+ update_url_query,
+ smuggle_url,
+)
-from .common import InfoExtractor
-
-
-class SyfyIE(InfoExtractor):
- _VALID_URL = r'https?://www\.syfy\.com/(?:videos/.+?vid:(?P<id>[0-9]+)|(?!videos)(?P<video_name>[^/]+)(?:$|[?#]))'
+class SyfyIE(ThePlatformIE):
+ _VALID_URL = r'https?://www\.syfy\.com/(?:[^/]+/)?videos/(?P<id>[^/?#]+)'
_TESTS = [{
- 'url': 'http://www.syfy.com/videos/Robot%20Combat%20League/Behind%20the%20Scenes/vid:2631458',
+ 'url': 'http://www.syfy.com/theinternetruinedmylife/videos/the-internet-ruined-my-life-season-1-trailer',
'info_dict': {
- 'id': 'NmqMrGnXvmO1',
- 'ext': 'flv',
- 'title': 'George Lucas has Advice for his Daughter',
- 'description': 'Listen to what insights George Lucas give his daughter Amanda.',
+ 'id': '2968097',
+ 'ext': 'mp4',
+ 'title': 'The Internet Ruined My Life: Season 1 Trailer',
+ 'description': 'One tweet, one post, one click, can destroy everything.',
+ 'uploader': 'NBCU-MPAT',
+ 'upload_date': '20170113',
+ 'timestamp': 1484345640,
},
- 'add_ie': ['ThePlatform'],
- }, {
- 'url': 'http://www.syfy.com/wilwheaton',
- 'md5': '94dfa54ee3ccb63295b276da08c415f6',
- 'info_dict': {
- 'id': '4yoffOOXC767',
- 'ext': 'flv',
- 'title': 'The Wil Wheaton Project - Premiering May 27th at 10/9c.',
- 'description': 'The Wil Wheaton Project premieres May 27th at 10/9c. Don\'t miss it.',
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
},
'add_ie': ['ThePlatform'],
- 'skip': 'Blocked outside the US',
}]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_name = mobj.group('video_name')
- if video_name:
- generic_webpage = self._download_webpage(url, video_name)
- video_id = self._search_regex(
- r'<iframe.*?class="video_iframe_page"\s+src="/_utils/video/thP_video_controller.php.*?_vid([0-9]+)">',
- generic_webpage, 'video ID')
- url = 'http://www.syfy.com/videos/%s/%s/vid:%s' % (
- video_name, video_name, video_id)
- else:
- video_id = mobj.group('id')
- webpage = self._download_webpage(url, video_id)
- return self.url_result(self._og_search_video_url(webpage))
+ display_id = self._match_id(url)
+ webpage = self._download_webpage(url, display_id)
+ syfy_mpx = list(self._parse_json(self._search_regex(
+ r'jQuery\.extend\([^,]+,\s*({.+})\);', webpage, 'drupal settings'),
+ display_id)['syfy']['syfy_mpx'].values())[0]
+ video_id = syfy_mpx['mpxGUID']
+ title = syfy_mpx['episodeTitle']
+ query = {
+ 'mbr': 'true',
+ 'manifest': 'm3u',
+ }
+ if syfy_mpx.get('entitlement') == 'auth':
+ resource = '<rss version="2.0" xmlns:media="http://search.yahoo.com/mrss/"><channel><title>syfy</title><item><title><![CDATA[%s]]></title><guid>%s</guid><media:rating scheme="urn:v-chip">%s</media:rating></item></channel></rss>' % (title, video_id, syfy_mpx.get('mpxRating', 'TV-14'))
+ query['auth'] = self._extract_mvpd_auth(
+ url, video_id, 'syfy', resource)
+
+ return {
+ '_type': 'url_transparent',
+ 'ie_key': 'ThePlatform',
+ 'url': smuggle_url(update_url_query(
+ self._proto_relative_url(syfy_mpx['releaseURL']), query),
+ {'force_smil_url': True}),
+ 'title': title,
+ 'id': video_id,
+ 'display_id': display_id,
+ }