X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fimgur.py;h=85e9344aab18e22be204134ca846318367b54329;hb=9f0ee2a3883ec6f6fdccba90085cb925aaa2f617;hp=16488e0c4c7526fc1abd800a90eddbaa5985cb45;hpb=3bf5705316adb4e486ec76a9308198b499787947;p=youtube-dl diff --git a/youtube_dl/extractor/imgur.py b/youtube_dl/extractor/imgur.py index 16488e0c4..85e9344aa 100644 --- a/youtube_dl/extractor/imgur.py +++ b/youtube_dl/extractor/imgur.py @@ -3,29 +3,52 @@ 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, 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/(?:(?:gallery|topic/[^/]+)/)?(?P[a-zA-Z0-9]{6,})(?:[/?#&]+|\.[a-z]+)?$' _TESTS = [{ 'url': 'https://i.imgur.com/A61SaA1.gifv', 'info_dict': { 'id': 'A61SaA1', 'ext': 'mp4', - 'title': 'MRW gifv is up and running without any bugs', - 'description': 'The Internet\'s visual storytelling community. Explore, share, and discuss the best visual stories the Internet has to offer.', + 'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$', + 'description': 'Imgur: The most awesome images on the Internet.', }, + }, { + 'url': 'https://imgur.com/A61SaA1', + 'info_dict': { + 'id': 'A61SaA1', + 'ext': 'mp4', + 'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$', + 'description': 'Imgur: The most awesome images on the Internet.', + }, + }, { + 'url': 'https://imgur.com/gallery/YcAQlkx', + 'info_dict': { + 'id': 'YcAQlkx', + 'ext': 'mp4', + 'title': 'Classic Steve Carell gif...cracks me up everytime....damn the repost downvotes....', + 'description': 'Imgur: The most awesome images on the Internet.' + + } + }, { + 'url': 'http://imgur.com/topic/Funny/N8rOudd', + 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage( + compat_urlparse.urljoin(url, video_id), video_id) width = int_or_none(self._search_regex( r'(.*?)', - webpage, 'video elements') + webpage, 'video elements', default=None) + if not video_elements: + raise ExtractorError( + 'No sources found for video %s. Maybe an image?' % video_id, + expected=True) + formats = [] for m in re.finditer(r'[^"]+)"\s+type="(?P[^"]+)"', video_elements): formats.append({ @@ -82,3 +109,41 @@ class ImgurIE(InfoExtractor): 'description': self._og_search_description(webpage), 'title': self._og_search_title(webpage), } + + +class ImgurAlbumIE(InfoExtractor): + _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:a|gallery|topic/[^/]+)/)?(?P[a-zA-Z0-9]{5})(?:[/?#&]+)?$' + + _TESTS = [{ + 'url': 'http://imgur.com/gallery/Q95ko', + 'info_dict': { + 'id': 'Q95ko', + }, + 'playlist_count': 25, + }, { + 'url': 'http://imgur.com/a/j6Orj', + 'only_matching': True, + }, { + 'url': 'http://imgur.com/topic/Aww/ll5Vk', + 'only_matching': True, + }] + + 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, fatal=False) + + if album_images: + data = album_images.get('data') + if data and isinstance(data, dict): + images = data.get('images') + if images and isinstance(images, list): + entries = [ + self.url_result('http://imgur.com/%s' % image['hash']) + for image in images if image.get('hash')] + return self.playlist_result(entries, album_id) + + # Fallback to single video + return self.url_result('http://imgur.com/%s' % album_id, ImgurIE.ie_key())