X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvice.py;h=46c785ae183d72207ab12500618f3eb7b765373d;hb=6e359a1534e6a20acb53e1268ec77b6b92765e22;hp=04e2b0ba7849adee473a42e471d77ced7df0652c;hpb=d9a743d9178b0ed1e44168e42e8cec2d7dd8d63e;p=youtube-dl diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py index 04e2b0ba7..46c785ae1 100644 --- a/youtube_dl/extractor/vice.py +++ b/youtube_dl/extractor/vice.py @@ -1,4 +1,5 @@ from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -7,25 +8,34 @@ from ..utils import ExtractorError class ViceIE(InfoExtractor): - _VALID_URL = r'http://www\.vice\.com/.*?/(?P.+)' + _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?videos?/(?P[^/?#&]+)' - _TEST = { - 'url': 'http://www.vice.com/Fringes/cowboy-capitalists-part-1', + _TESTS = [{ + 'url': 'http://www.vice.com/video/cowboy-capitalists-part-1', 'info_dict': { 'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp', 'ext': 'mp4', 'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov', + 'duration': 725.983, }, 'params': { # Requires ffmpeg (m3u8 manifest) 'skip_download': True, }, - } + }, { + 'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab', + 'only_matching': True, + }, { + 'url': 'http://www.vice.com/ru/video/big-night-out-ibiza-clive-martin-229', + 'only_matching': True, + }, { + 'url': 'https://munchies.vice.com/en/videos/watch-the-trailer-for-our-new-series-the-pizza-show', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - name = mobj.group('name') - webpage = self._download_webpage(url, name) + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) try: embed_code = self._search_regex( r'embedCode=([^&\'"]+)', webpage, @@ -34,3 +44,35 @@ class ViceIE(InfoExtractor): except ExtractorError: raise ExtractorError('The page doesn\'t contain a video', expected=True) return self.url_result(ooyala_url, ie='Ooyala') + + +class ViceShowIE(InfoExtractor): + _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?show/(?P[^/?#&]+)' + + _TEST = { + 'url': 'https://munchies.vice.com/en/show/fuck-thats-delicious-2', + 'info_dict': { + 'id': 'fuck-thats-delicious-2', + 'title': "Fuck, That's Delicious", + 'description': 'Follow the culinary adventures of rapper Action Bronson during his ongoing world tour.', + }, + 'playlist_count': 17, + } + + def _real_extract(self, url): + show_id = self._match_id(url) + webpage = self._download_webpage(url, show_id) + + entries = [ + self.url_result(video_url, ViceIE.ie_key()) + for video_url, _ in re.findall( + r']+class="article-title"[^>]+data-id="\d+"[^>]*>\s*]+href="(%s.*?)"' + % ViceIE._VALID_URL, webpage)] + + title = self._search_regex( + r'(.+?)', webpage, 'title', default=None) + if title: + title = re.sub(r'(.+)\s*\|\s*.+$', r'\1', title).strip() + description = self._html_search_meta('description', webpage, 'description') + + return self.playlist_result(entries, show_id, title, description)