X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fimgur.py;h=70c8ca64e6346d86ef5ecea02722597829db1316;hb=33a513faf716e5d4a170da50d6fde541817dca09;hp=38c9617731cf1b1a708939e46009b0bdba88774d;hpb=d236b37ac94cd36657c881e18b8d9187483afa80;p=youtube-dl diff --git a/youtube_dl/extractor/imgur.py b/youtube_dl/extractor/imgur.py index 38c961773..70c8ca64e 100644 --- a/youtube_dl/extractor/imgur.py +++ b/youtube_dl/extractor/imgur.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_urlparse from ..utils import ( int_or_none, js_to_json, @@ -10,35 +11,32 @@ from ..utils import ( 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/(?!gallery)(?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) - - sources = re.findall(r'(.*?)', - webpage, 'video elements') + webpage, 'video elements', default=None) + if not video_elements: + raise ExtractorError( + '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): formats.append({ @@ -95,3 +97,28 @@ class ImgurIE(InfoExtractor): 'description': self._og_search_description(webpage), 'title': self._og_search_title(webpage), } + + +class ImgurAlbumIE(InfoExtractor): + _VALID_URL = r'https?://(?:i\.)?imgur\.com/gallery/(?P[a-zA-Z0-9]+)' + + _TEST = { + 'url': 'http://imgur.com/gallery/Q95ko', + 'info_dict': { + 'id': 'Q95ko', + }, + 'playlist_count': 25, + } + + def _real_extract(self, url): + album_id = self._match_id(url) + + album_images = self._download_json( + 'http://imgur.com/gallery/%s/album_images/hit.json?all=true' % album_id, + album_id)['data']['images'] + + entries = [ + self.url_result('http://imgur.com/%s' % image['hash']) + for image in album_images if image.get('hash')] + + return self.playlist_result(entries, album_id)