1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-05 09:01:21 +00:00
youtube-dl/youtube_dl/extractor/ninegag.py

69 lines
2.5 KiB
Python
Raw Normal View History

2014-01-28 17:55:06 +00:00
from __future__ import unicode_literals
2013-12-05 13:29:08 +00:00
import re
2014-04-15 12:49:38 +00:00
import json
2013-12-05 13:29:08 +00:00
from .common import InfoExtractor
2014-04-15 12:49:38 +00:00
from ..utils import str_to_int
2013-12-05 13:29:08 +00:00
class NineGagIE(InfoExtractor):
IE_NAME = '9gag'
2014-04-10 23:25:24 +00:00
_VALID_URL = r'''(?x)^https?://(?:www\.)?9gag\.tv/
(?:
v/(?P<numid>[0-9]+)|
p/(?P<id>[a-zA-Z0-9]+)/(?P<display_id>[^?#/]+)
)
'''
2013-12-05 13:29:08 +00:00
2014-04-10 23:25:24 +00:00
_TESTS = [{
2014-01-28 17:55:06 +00:00
"url": "http://9gag.tv/v/1912",
"info_dict": {
"id": "1912",
"ext": "mp4",
2014-01-28 17:55:06 +00:00
"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!)",
2014-03-13 15:40:53 +00:00
"title": "\"People Are Awesome 2013\" Is Absolutely Awesome",
"view_count": int,
"thumbnail": "re:^https?://",
2013-12-05 13:29:08 +00:00
},
2014-01-28 17:55:06 +00:00
'add_ie': ['Youtube']
2014-04-10 23:25:24 +00:00
},
{
'url': 'http://9gag.tv/p/KklwM/alternate-banned-opening-scene-of-gravity?ref=fsidebar',
'info_dict': {
'id': 'KklwM',
'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",
},
}]
2013-12-05 13:29:08 +00:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2014-04-10 23:25:24 +00:00
video_id = mobj.group('numid') or mobj.group('id')
display_id = mobj.group('display_id') or video_id
2013-12-05 13:29:08 +00:00
2014-04-10 23:25:24 +00:00
webpage = self._download_webpage(url, display_id)
2013-12-05 13:29:08 +00:00
2014-04-15 12:49:38 +00:00
post_view = json.loads(self._html_search_regex(
r'var postView = new app\.PostView\({ post: ({.+?}),', webpage, 'post view'))
youtube_id = post_view['videoExternalId']
title = post_view['title']
description = post_view['description']
view_count = str_to_int(post_view['externalView'])
thumbnail = post_view.get('thumbnail_700w') or post_view.get('ogImageUrl') or post_view.get('thumbnail_300w')
2013-12-05 13:29:08 +00:00
return {
'_type': 'url_transparent',
2014-03-13 15:40:53 +00:00
'url': youtube_id,
2013-12-05 13:29:08 +00:00
'ie_key': 'Youtube',
'id': video_id,
2014-04-10 23:25:24 +00:00
'display_id': display_id,
'title': title,
2014-03-13 15:40:53 +00:00
'description': description,
'view_count': view_count,
2014-04-15 12:49:38 +00:00
'thumbnail': thumbnail,
2013-12-05 13:29:08 +00:00
}