diff options
Diffstat (limited to 'youtube_dl/extractor/aol.py')
-rw-r--r-- | youtube_dl/extractor/aol.py | 41 |
1 files changed, 39 insertions, 2 deletions
diff --git a/youtube_dl/extractor/aol.py b/youtube_dl/extractor/aol.py index abc668912..a7bfe5a5c 100644 --- a/youtube_dl/extractor/aol.py +++ b/youtube_dl/extractor/aol.py @@ -8,7 +8,18 @@ from .fivemin import FiveMinIE 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) |