[ninegag] fix _VALID_URL regex and handle the use of other external providers

This commit is contained in:
remitamine 2015-09-21 14:01:12 +01:00 committed by Sergey M․
parent d0fed4ac02
commit de3fc356e1
1 changed files with 29 additions and 14 deletions

View File

@ -9,17 +9,12 @@ from ..utils import str_to_int
class NineGagIE(InfoExtractor): class NineGagIE(InfoExtractor):
IE_NAME = '9gag' IE_NAME = '9gag'
_VALID_URL = r'''(?x)^https?://(?:www\.)?9gag\.tv/ _VALID_URL = r'https?://(?:www\.)?9gag\.com/tv/p/(?P<id>[a-zA-Z0-9]+)/(?P<display_id>[^?#/]+)'
(?:
v/(?P<numid>[0-9]+)|
p/(?P<id>[a-zA-Z0-9]+)/(?P<display_id>[^?#/]+)
)
'''
_TESTS = [{ _TESTS = [{
"url": "http://9gag.tv/v/1912", "url": "http://9gag.com/tv/p/Kk2X5/people-are-awesome-2013-is-absolutely-awesome",
"info_dict": { "info_dict": {
"id": "1912", "id": "Kk2X5",
"ext": "mp4", "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!)", "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", "title": "\"People Are Awesome 2013\" Is Absolutely Awesome",
@ -31,7 +26,7 @@ class NineGagIE(InfoExtractor):
}, },
'add_ie': ['Youtube'] 'add_ie': ['Youtube']
}, { }, {
'url': 'http://9gag.tv/p/KklwM/alternate-banned-opening-scene-of-gravity?ref=fsidebar', 'url': 'http://9gag.com/tv/p/KklwM/alternate-banned-opening-scene-of-gravity?ref=fsidebar',
'info_dict': { 'info_dict': {
'id': 'KklwM', 'id': 'KklwM',
'ext': 'mp4', 'ext': 'mp4',
@ -42,19 +37,39 @@ class NineGagIE(InfoExtractor):
'upload_date': '20140401', 'upload_date': '20140401',
'uploader_id': 'krishnashenoi93', 'uploader_id': 'krishnashenoi93',
}, },
'add_ie': ['Youtube']
}] }]
_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): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, 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 display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
post_view = json.loads(self._html_search_regex( post_view = json.loads(self._html_search_regex(
r'var postView = new app\.PostView\({\s*post:\s*({.+?}),\s*posts:\s*prefetchedCurrentPost', webpage, 'post view')) r'var postView = new app\.PostView\({\s*post:\s*({.+?}),\s*posts:\s*prefetchedCurrentPost', webpage, 'post view'))
youtube_id = post_view['videoExternalId'] external_video_id = post_view['videoExternalId']
external_video_provider = post_view['videoExternalProvider']
title = post_view['title'] title = post_view['title']
description = post_view['description'] description = post_view['description']
view_count = str_to_int(post_view['externalView']) view_count = str_to_int(post_view['externalView'])
@ -62,8 +77,8 @@ class NineGagIE(InfoExtractor):
return { return {
'_type': 'url_transparent', '_type': 'url_transparent',
'url': youtube_id, 'url': self._EXTERNAL_VIDEO_PROVIDER[external_video_provider]['url'] % external_video_id,
'ie_key': 'Youtube', 'ie_key': self._EXTERNAL_VIDEO_PROVIDER[external_video_provider]['ie_key'],
'id': video_id, 'id': video_id,
'display_id': display_id, 'display_id': display_id,
'title': title, 'title': title,