X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/e76f531201cd41dfc0ce00be28bcc5c575c7acc5..d037080638e8dbb0ebb2ac9cf23b9671518340f9:/youtube_dl/extractor/imgur.py?ds=sidebyside diff --git a/youtube_dl/extractor/imgur.py b/youtube_dl/extractor/imgur.py index 70c8ca6..a5ba03e 100644 --- a/youtube_dl/extractor/imgur.py +++ b/youtube_dl/extractor/imgur.py @@ -3,7 +3,6 @@ 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, @@ -13,7 +12,7 @@ from ..utils import ( class ImgurIE(InfoExtractor): - _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?!gallery)(?P[a-zA-Z0-9]+)' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?!(?:a|gallery|(?:t(?:opic)?|r)/[^/]+)/)(?P[a-zA-Z0-9]+)' _TESTS = [{ 'url': 'https://i.imgur.com/A61SaA1.gifv', @@ -21,29 +20,28 @@ class ImgurIE(InfoExtractor): 'id': 'A61SaA1', 'ext': 'mp4', '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': 're:Imgur GIF$|MRW gifv is up and running without any bugs$', - 'description': 're:The origin of the Internet\'s most viral images$|The Internet\'s visual storytelling community\. Explore, share, and discuss the best visual stories the Internet has to offer\.$', - }, + 'only_matching': True, + }, { + 'url': 'https://i.imgur.com/crGpqCV.mp4', + 'only_matching': True, + }, { + # no title + 'url': 'https://i.imgur.com/jxBXAMC.gifv', + 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage( - compat_urlparse.urljoin(url, video_id), video_id) + 'https://i.imgur.com/{id}.gifv'.format(id=video_id), video_id) - width = int_or_none(self._search_regex( - r'(.*?)', @@ -59,7 +57,6 @@ class ImgurIE(InfoExtractor): 'format_id': m.group('type').partition('/')[2], 'url': self._proto_relative_url(m.group('src')), 'ext': mimetype2ext(m.group('type')), - 'acodec': 'none', 'width': width, 'height': height, 'http_headers': { @@ -94,31 +91,64 @@ class ImgurIE(InfoExtractor): return { 'id': video_id, 'formats': formats, - 'description': self._og_search_description(webpage), - 'title': self._og_search_title(webpage), + 'title': self._og_search_title(webpage, default=video_id), } -class ImgurAlbumIE(InfoExtractor): - _VALID_URL = r'https?://(?:i\.)?imgur\.com/gallery/(?P[a-zA-Z0-9]+)' +class ImgurGalleryIE(InfoExtractor): + IE_NAME = 'imgur:gallery' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:gallery|(?:t(?:opic)?|r)/[^/]+)/(?P[a-zA-Z0-9]+)' - _TEST = { + _TESTS = [{ 'url': 'http://imgur.com/gallery/Q95ko', 'info_dict': { 'id': 'Q95ko', + 'title': 'Adding faces make every GIF better', }, 'playlist_count': 25, - } + }, { + 'url': 'http://imgur.com/topic/Aww/ll5Vk', + 'only_matching': True, + }, { + '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....', + } + }, { + 'url': 'http://imgur.com/topic/Funny/N8rOudd', + 'only_matching': True, + }, { + 'url': 'http://imgur.com/r/aww/VQcQPhM', + 'only_matching': True, + }] def _real_extract(self, url): - album_id = self._match_id(url) + gallery_id = self._match_id(url) + + data = self._download_json( + 'https://imgur.com/gallery/%s.json' % gallery_id, + gallery_id)['data']['image'] - album_images = self._download_json( - 'http://imgur.com/gallery/%s/album_images/hit.json?all=true' % album_id, - album_id)['data']['images'] + if data.get('is_album'): + entries = [ + self.url_result('http://imgur.com/%s' % image['hash'], ImgurIE.ie_key(), image['hash']) + for image in data['album_images']['images'] if image.get('hash')] + return self.playlist_result(entries, gallery_id, data.get('title'), data.get('description')) - entries = [ - self.url_result('http://imgur.com/%s' % image['hash']) - for image in album_images if image.get('hash')] + return self.url_result('http://imgur.com/%s' % gallery_id, ImgurIE.ie_key(), gallery_id) - return self.playlist_result(entries, album_id) + +class ImgurAlbumIE(ImgurGalleryIE): + IE_NAME = 'imgur:album' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/a/(?P[a-zA-Z0-9]+)' + + _TESTS = [{ + 'url': 'http://imgur.com/a/j6Orj', + 'info_dict': { + 'id': 'j6Orj', + 'title': 'A Literary Analysis of "Star Wars: The Force Awakens"', + }, + 'playlist_count': 12, + }]