X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fimgur.py;h=d692ea79ab493174038c9649445e6a592a86687c;hb=1de5cd3ba51ce67d9a1cd3b40157058e78e46692;hp=7937a5c819bf7be8eeda523dfcafc1b51f02e987;hpb=b74d50557757df97c1b2d7a776aa496e623a116c;p=youtube-dl diff --git a/youtube_dl/extractor/imgur.py b/youtube_dl/extractor/imgur.py index 7937a5c81..d692ea79a 100644 --- a/youtube_dl/extractor/imgur.py +++ b/youtube_dl/extractor/imgur.py @@ -3,38 +3,40 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_urlparse from ..utils import ( int_or_none, - str_or_none, js_to_json, mimetype2ext, ExtractorError, ) + class ImgurIE(InfoExtractor): - _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?P[a-zA-Z0-9]+)(?:\.mp4|\.gifv)?' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?P[a-zA-Z0-9]+)' _TESTS = [{ 'url': 'https://i.imgur.com/A61SaA1.gifv', 'info_dict': { 'id': 'A61SaA1', 'ext': 'mp4', - 'title': 'MRW gifv is up and running without any bugs', - 'description': 'The Internet\'s visual storytelling community. Explore, share, and discuss the best visual stories the Internet has to offer.', + 'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$', + 'description': 're:The origin of the Internet\'s most viral images$|The Internet\'s visual storytelling community\. Explore, share, and discuss the best visual stories the Internet has to offer\.$', }, }, { 'url': 'https://imgur.com/A61SaA1', 'info_dict': { 'id': 'A61SaA1', 'ext': 'mp4', - 'title': 'MRW gifv is up and running without any bugs', - 'description': 'The Internet\'s visual storytelling community. Explore, share, and discuss the best visual stories the Internet has to offer.', + 'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$', + 'description': 're:The origin of the Internet\'s most viral images$|The Internet\'s visual storytelling community\. Explore, share, and discuss the best visual stories the Internet has to offer\.$', }, }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage( + compat_urlparse.urljoin(url, video_id), video_id) width = int_or_none(self._search_regex( r'(.*?)', - webpage, 'video elements', fatal=False)) + webpage, 'video elements', default=None) if not video_elements: raise ExtractorError( - 'No sources found for video %s' % video_id, expected=True) + 'No sources found for video %s. Maybe an image?' % video_id, + expected=True) formats = [] for m in re.finditer(r'[^"]+)"\s+type="(?P[^"]+)"', video_elements):