X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/87a0165ca7e39af4dacb7ec637063b2cd35ae40b..ed1c1d2a80ce1ad325853e6c59a1fbaf2156adcc:/youtube_dl/extractor/abcnews.py diff --git a/youtube_dl/extractor/abcnews.py b/youtube_dl/extractor/abcnews.py index 6ae5d9a..f770fe9 100644 --- a/youtube_dl/extractor/abcnews.py +++ b/youtube_dl/extractor/abcnews.py @@ -7,12 +7,21 @@ import time from .amp import AMPIE from .common import InfoExtractor +from .youtube import YoutubeIE from ..compat import compat_urlparse class AbcNewsVideoIE(AMPIE): IE_NAME = 'abcnews:video' - _VALID_URL = r'https?://abcnews\.go\.com/[^/]+/video/(?P[0-9a-z-]+)-(?P\d+)' + _VALID_URL = r'''(?x) + https?:// + abcnews\.go\.com/ + (?: + [^/]+/video/(?P[0-9a-z-]+)-| + video/embed\?.*?\bid= + ) + (?P\d+) + ''' _TESTS = [{ 'url': 'http://abcnews.go.com/ThisWeek/video/week-exclusive-irans-foreign-minister-zarif-20411932', @@ -23,12 +32,15 @@ class AbcNewsVideoIE(AMPIE): 'title': '\'This Week\' Exclusive: Iran\'s Foreign Minister Zarif', 'description': 'George Stephanopoulos goes one-on-one with Iranian Foreign Minister Dr. Javad Zarif.', 'duration': 180, - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', }, 'params': { # m3u8 download 'skip_download': True, }, + }, { + 'url': 'http://abcnews.go.com/video/embed?id=46979033', + 'only_matching': True, }, { 'url': 'http://abcnews.go.com/2020/video/2020-husband-stands-teacher-jail-student-affairs-26119478', 'only_matching': True, @@ -59,7 +71,7 @@ class AbcNewsIE(InfoExtractor): 'display_id': 'dramatic-video-rare-death-job-america', 'title': 'Occupational Hazards', 'description': 'Nightline investigates the dangers that lurk at various jobs.', - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', 'upload_date': '20100428', 'timestamp': 1272412800, }, @@ -97,9 +109,7 @@ class AbcNewsIE(InfoExtractor): r'window\.abcnvideo\.url\s*=\s*"([^"]+)"', webpage, 'video URL') full_video_url = compat_urlparse.urljoin(url, video_url) - youtube_url = self._html_search_regex( - r']+src="(https://www\.youtube\.com/embed/[^"]+)"', - webpage, 'YouTube URL', default=None) + youtube_url = YoutubeIE._extract_url(webpage) timestamp = None date_str = self._html_search_regex( @@ -129,7 +139,7 @@ class AbcNewsIE(InfoExtractor): } if youtube_url: - entries = [entry, self.url_result(youtube_url, 'Youtube')] + entries = [entry, self.url_result(youtube_url, ie=YoutubeIE.ie_key())] return self.playlist_result(entries) return entry