[aol] Add support for playlists (Fixes #2730)

This commit is contained in:
Philipp Hagemeister 2014-04-13 03:19:56 +02:00
parent 2fb3deeca1
commit de906ef543
3 changed files with 50 additions and 3 deletions

View file

@ -176,6 +176,5 @@ def test_yahoo_https(self):
'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html',
['Yahoo'])
if __name__ == '__main__':
unittest.main()

View file

@ -43,6 +43,7 @@
XTubeUserIE,
InstagramUserIE,
CSpanIE,
AolIE,
)
@ -327,6 +328,16 @@ def test_CSpan_playlist(self):
whole_duration = sum(e['duration'] for e in result['entries'])
self.assertEqual(whole_duration, 14855)
def test_aol_playlist(self):
dl = FakeYDL()
ie = AolIE(dl)
result = ie.extract(
'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], '152147')
self.assertEqual(
result['title'], 'Brace Yourself - Today\'s Weirdest News')
self.assertTrue(len(result['entries']) >= 10)
if __name__ == '__main__':
unittest.main()

View file

@ -8,7 +8,18 @@
class AolIE(InfoExtractor):
IE_NAME = 'on.aol.com'
_VALID_URL = r'http://on\.aol\.com/video/.*-(?P<id>\d+)($|\?)'
_VALID_URL = r'''(?x)
(?:
aol-video:|
http://on\.aol\.com/
(?:
video/.*-|
playlist/(?P<playlist_display_id>[^/?#]+?)-(?P<playlist_id>[0-9]+)[?#].*_videoid=
)
)
(?P<id>[0-9]+)
(?:$|\?)
'''
_TEST = {
'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
@ -24,5 +35,31 @@ class AolIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
self.to_screen('Downloading 5min.com video %s' % video_id)
playlist_id = mobj.group('playlist_id')
if playlist_id and not self._downloader.params.get('noplaylist'):
self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
webpage = self._download_webpage(url, playlist_id)
title = self._html_search_regex(
r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title')
playlist_html = self._search_regex(
r"(?s)<ul\s+class='video-related[^']*'>(.*?)</ul>", webpage,
'playlist HTML')
entries = [{
'_type': 'url',
'url': 'aol-video:%s' % m.group('id'),
'ie_key': 'Aol',
} for m in re.finditer(
r"<a\s+href='.*videoid=(?P<id>[0-9]+)'\s+class='video-thumb'>",
playlist_html)]
return {
'_type': 'playlist',
'id': playlist_id,
'display_id': mobj.group('playlist_display_id'),
'title': title,
'entries': entries,
}
return FiveMinIE._build_result(video_id)