X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fninegag.py;h=dc6a27d3643d335a69a75d494f7673ecf5b43a7d;hb=HEAD;hp=3352b833018315821d5964c8e3c907ceb362e21c;hpb=4be9f8c814c328213c8f60ecbb1e4d4e205b950e;p=youtube-dl diff --git a/youtube_dl/extractor/ninegag.py b/youtube_dl/extractor/ninegag.py index 3352b8330..dc6a27d36 100644 --- a/youtube_dl/extractor/ninegag.py +++ b/youtube_dl/extractor/ninegag.py @@ -3,73 +3,102 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import str_to_int class NineGagIE(InfoExtractor): IE_NAME = '9gag' - _VALID_URL = r'''(?x)^https?://(?:www\.)?9gag\.tv/ - (?: - v/(?P[0-9]+)| - p/(?P[a-zA-Z0-9]+)/(?P[^?#/]+) - ) - ''' + _VALID_URL = r'https?://(?:www\.)?9gag(?:\.com/tv|\.tv)/(?:p|embed)/(?P[a-zA-Z0-9]+)(?:/(?P[^?#/]+))?' _TESTS = [{ - "url": "http://9gag.tv/v/1912", - "info_dict": { - "id": "1912", - "ext": "mp4", - "description": "This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)", - "title": "\"People Are Awesome 2013\" Is Absolutely Awesome", - "view_count": int, - "thumbnail": "re:^https?://", + 'url': 'http://9gag.com/tv/p/Kk2X5/people-are-awesome-2013-is-absolutely-awesome', + 'info_dict': { + 'id': 'kXzwOKyGlSA', + 'ext': 'mp4', + 'description': 'This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)', + 'title': '\"People Are Awesome 2013\" Is Absolutely Awesome', + 'uploader_id': 'UCdEH6EjDKwtTe-sO2f0_1XA', + 'uploader': 'CompilationChannel', + 'upload_date': '20131110', + 'view_count': int, }, - 'add_ie': ['Youtube'] - }, - { - 'url': 'http://9gag.tv/p/KklwM/alternate-banned-opening-scene-of-gravity?ref=fsidebar', + 'add_ie': ['Youtube'], + }, { + 'url': 'http://9gag.com/tv/p/aKolP3', 'info_dict': { - 'id': 'KklwM', + 'id': 'aKolP3', 'ext': 'mp4', - 'display_id': 'alternate-banned-opening-scene-of-gravity', - "description": "While Gravity was a pretty awesome movie already, YouTuber Krishna Shenoi came up with a way to improve upon it, introducing a much better solution to Sandra Bullock's seemingly endless tumble in space. The ending is priceless.", - 'title': "Banned Opening Scene Of \"Gravity\" That Changes The Whole Movie", + 'title': 'This Guy Travelled 11 countries In 44 days Just To Make This Amazing Video', + 'description': "I just saw more in 1 minute than I've seen in 1 year. This guy's video is epic!!", + 'uploader_id': 'rickmereki', + 'uploader': 'Rick Mereki', + 'upload_date': '20110803', + 'view_count': int, }, + 'add_ie': ['Vimeo'], + }, { + 'url': 'http://9gag.com/tv/p/KklwM', + 'only_matching': True, + }, { + 'url': 'http://9gag.tv/p/Kk2X5', + 'only_matching': True, + }, { + 'url': 'http://9gag.com/tv/embed/a5Dmvl', + 'only_matching': True, }] + _EXTERNAL_VIDEO_PROVIDER = { + '1': { + 'url': '%s', + 'ie_key': 'Youtube', + }, + '2': { + 'url': 'http://player.vimeo.com/video/%s', + 'ie_key': 'Vimeo', + }, + '3': { + 'url': 'http://instagram.com/p/%s', + 'ie_key': 'Instagram', + }, + '4': { + 'url': 'http://vine.co/v/%s', + 'ie_key': 'Vine', + }, + } + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('numid') or mobj.group('id') + video_id = mobj.group('id') display_id = mobj.group('display_id') or video_id webpage = self._download_webpage(url, display_id) - youtube_id = self._html_search_regex( - r'(?s)id="jsid-video-post-container".*?data-external-id="([^"]+)"', - webpage, 'video ID') - title = self._html_search_regex( - r'(?s)id="jsid-video-post-container".*?data-title="([^"]+)"', - webpage, 'title', default=None) - if not title: - title = self._og_search_title(webpage) - description = self._html_search_regex( - r'(?s)
.*?

(.*?)

', webpage, - 'description', fatal=False) - view_count_str = self._html_search_regex( - r'

([0-9][0-9,]*) views

', webpage, 'view count', - fatal=False) - view_count = ( - None if view_count_str is None - else int(view_count_str.replace(',', ''))) + post_view = self._parse_json( + self._search_regex( + r'var\s+postView\s*=\s*new\s+app\.PostView\({\s*post:\s*({.+?})\s*,\s*posts:\s*prefetchedCurrentPost', + webpage, 'post view'), + display_id) + + ie_key = None + source_url = post_view.get('sourceUrl') + if not source_url: + external_video_id = post_view['videoExternalId'] + external_video_provider = post_view['videoExternalProvider'] + source_url = self._EXTERNAL_VIDEO_PROVIDER[external_video_provider]['url'] % external_video_id + ie_key = self._EXTERNAL_VIDEO_PROVIDER[external_video_provider]['ie_key'] + title = post_view['title'] + description = post_view.get('description') + view_count = str_to_int(post_view.get('externalView')) + thumbnail = post_view.get('thumbnail_700w') or post_view.get('ogImageUrl') or post_view.get('thumbnail_300w') return { '_type': 'url_transparent', - 'url': youtube_id, - 'ie_key': 'Youtube', + 'url': source_url, + 'ie_key': ie_key, 'id': video_id, 'display_id': display_id, 'title': title, 'description': description, 'view_count': view_count, - 'thumbnail': self._og_search_thumbnail(webpage), + 'thumbnail': thumbnail, }