X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ffoxnews.py;h=dc0662f74ce5a84d59aa94333ee14d56a592cda2;hb=4c76aa06665621c7689938afd7bbdbc797b5c7ea;hp=5c7acd79592bef94775dfeb7eab1be4e7dd33d03;hpb=95843da5297965bb535262002c92a4d0afcb7e12;p=youtube-dl diff --git a/youtube_dl/extractor/foxnews.py b/youtube_dl/extractor/foxnews.py index 5c7acd795..dc0662f74 100644 --- a/youtube_dl/extractor/foxnews.py +++ b/youtube_dl/extractor/foxnews.py @@ -7,6 +7,7 @@ from .common import InfoExtractor class FoxNewsIE(AMPIE): + IE_NAME = 'foxnews' IE_DESC = 'Fox News and Fox Business Video' _VALID_URL = r'https?://(?Pvideo\.(?:insider\.)?fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P\d+)' _TESTS = [ @@ -21,7 +22,7 @@ class FoxNewsIE(AMPIE): 'duration': 265, 'timestamp': 1304411491, 'upload_date': '20110503', - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', }, }, { @@ -35,7 +36,7 @@ class FoxNewsIE(AMPIE): 'duration': 292, 'timestamp': 1417662047, 'upload_date': '20141204', - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', }, 'params': { # m3u8 download @@ -66,6 +67,35 @@ class FoxNewsIE(AMPIE): return info +class FoxNewsArticleIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?foxnews\.com/(?!v)([^/]+/)+(?P[a-z-]+)' + IE_NAME = 'foxnews:article' + + _TEST = { + 'url': 'http://www.foxnews.com/politics/2016/09/08/buzz-about-bud-clinton-camp-denies-claims-wore-earpiece-at-forum.html', + 'md5': '62aa5a781b308fdee212ebb6f33ae7ef', + 'info_dict': { + 'id': '5116295019001', + 'ext': 'mp4', + 'title': 'Trump and Clinton asked to defend positions on Iraq War', + 'description': 'Veterans react on \'The Kelly File\'', + 'timestamp': 1473299755, + 'upload_date': '20160908', + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + video_id = self._html_search_regex( + r'data-video-id=([\'"])(?P[^\'"]+)\1', + webpage, 'video ID', group='id') + return self.url_result( + 'http://video.foxnews.com/v/' + video_id, + FoxNewsIE.ie_key()) + + class FoxNewsInsiderIE(InfoExtractor): _VALID_URL = r'https?://insider\.foxnews\.com/([^/]+/)+(?P[a-z-]+)' IE_NAME = 'foxnews:insider' @@ -81,7 +111,11 @@ class FoxNewsInsiderIE(InfoExtractor): 'description': 'Is campus censorship getting out of control?', 'timestamp': 1472168725, 'upload_date': '20160825', - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', + }, + 'params': { + # m3u8 download + 'skip_download': True, }, 'add_ie': [FoxNewsIE.ie_key()], }