X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/509eeaaa67b2f901752c50fc6edf41954dbe3085..d018d3313032e12968a6add6800e51d412e2f602:/youtube_dl/extractor/nuvid.py?ds=sidebyside diff --git a/youtube_dl/extractor/nuvid.py b/youtube_dl/extractor/nuvid.py index 280328b..9fa7cef 100644 --- a/youtube_dl/extractor/nuvid.py +++ b/youtube_dl/extractor/nuvid.py @@ -5,13 +5,13 @@ import re from .common import InfoExtractor from ..utils import ( parse_duration, + sanitized_Request, unified_strdate, - compat_urllib_request, ) class NuvidIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www|m)\.nuvid\.com/video/(?P[0-9]+)' + _VALID_URL = r'https?://(?:www|m)\.nuvid\.com/video/(?P[0-9]+)' _TEST = { 'url': 'http://m.nuvid.com/video/1310741/', 'md5': 'eab207b7ac4fccfb4e23c86201f11277', @@ -26,19 +26,18 @@ class NuvidIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) formats = [] for dwnld_speed, format_id in [(0, '3gp'), (5, 'mp4')]: - request = compat_urllib_request.Request( + request = sanitized_Request( 'http://m.nuvid.com/play/%s' % video_id) request.add_header('Cookie', 'skip_download_page=1; dwnld_speed=%d; adv_show=1' % dwnld_speed) webpage = self._download_webpage( request, video_id, 'Downloading %s page' % format_id) video_url = self._html_search_regex( - r'Continue to watch video', webpage, '%s video URL' % format_id, fatal=False) + r'', webpage, '%s video URL' % format_id, fatal=False) if not video_url: continue formats.append({ @@ -49,21 +48,26 @@ class NuvidIE(InfoExtractor): webpage = self._download_webpage( 'http://m.nuvid.com/video/%s' % video_id, video_id, 'Downloading video page') title = self._html_search_regex( - r'
\s+]*>([^<]+)', webpage, 'title').strip() - thumbnail = self._html_search_regex( - r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"', - webpage, 'thumbnail URL', fatal=False) + [r'', + r'
\s*]*>([^<]+)'], webpage, 'title').strip() + thumbnails = [ + { + 'url': thumb_url, + } for thumb_url in re.findall(r'', webpage) + ] + thumbnail = thumbnails[0]['url'] if thumbnails else None duration = parse_duration(self._html_search_regex( - r'Length:\s*(\d{2}:\d{2})',webpage, 'duration', fatal=False)) + r'\s*(\d{2}:\d{2})', webpage, 'duration', fatal=False)) upload_date = unified_strdate(self._html_search_regex( - r'Added:\s*(\d{4}-\d{2}-\d{2})', webpage, 'upload date', fatal=False)) + r'\s*(\d{4}-\d{2}-\d{2})', webpage, 'upload date', fatal=False)) return { 'id': video_id, 'title': title, - 'thumbnail': 'http://m.nuvid.com%s' % thumbnail, + 'thumbnails': thumbnails, + 'thumbnail': thumbnail, 'duration': duration, 'upload_date': upload_date, 'age_limit': 18, 'formats': formats, - } \ No newline at end of file + }