fenix
/
ytdl-nightly
mirror of https://github.com/ytdl-org/ytdl-nightly.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[ninegag] Add support for p/ URLs

This commit is contained in:
Philipp Hagemeister 2014-04-11 01:25:24 +02:00
parent 5c802bac37
commit 4be9f8c814
2 changed files with 29 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
test/test_all_urls.py
View File

@ -172,5 +172,6 @@ class TestAllURLsMatching(unittest.TestCase):
'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html', 'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html',
['Yahoo']) ['Yahoo'])
if __name__ == '__main__': if __name__ == '__main__':
unittest.main() unittest.main()

34
youtube_dl/extractor/ninegag.py
View File

@ -7,9 +7,14 @@ from .common import InfoExtractor
class NineGagIE(InfoExtractor): class NineGagIE(InfoExtractor):
IE_NAME = '9gag' IE_NAME = '9gag'
_VALID_URL = r'^https?://(?:www\.)?9gag\.tv/v/(?P<id>[0-9]+)' _VALID_URL = r'''(?x)^https?://(?:www\.)?9gag\.tv/
(?:
v/(?P<numid>[0-9]+)|
p/(?P<id>[a-zA-Z0-9]+)/(?P<display_id>[^?#/]+)
)
'''
_TEST = { _TESTS = [{
"url": "http://9gag.tv/v/1912", "url": "http://9gag.tv/v/1912",
"info_dict": { "info_dict": {
"id": "1912", "id": "1912",
@ -20,17 +25,33 @@ class NineGagIE(InfoExtractor):
"thumbnail": "re:^https?://", "thumbnail": "re:^https?://",
}, },
'add_ie': ['Youtube'] 'add_ie': ['Youtube']
} },
{
'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",
},
}]
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('id') video_id = mobj.group('numid') or mobj.group('id')
display_id = mobj.group('display_id') or video_id
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, display_id)
youtube_id = self._html_search_regex( youtube_id = self._html_search_regex(
r'(?s)id="jsid-video-post-container".*?data-external-id="([^"]+)"', r'(?s)id="jsid-video-post-container".*?data-external-id="([^"]+)"',
webpage, 'video 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( description = self._html_search_regex(
r'(?s)<div class="video-caption">.*?<p>(.*?)</p>', webpage, r'(?s)<div class="video-caption">.*?<p>(.*?)</p>', webpage,
'description', fatal=False) 'description', fatal=False)
@ -46,7 +67,8 @@ class NineGagIE(InfoExtractor):
'url': youtube_id, 'url': youtube_id,
'ie_key': 'Youtube', 'ie_key': 'Youtube',
'id': video_id, 'id': video_id,
'title': self._og_search_title(webpage), 'display_id': display_id,
'title': title,
'description': description, 'description': description,
'view_count': view_count, 'view_count': view_count,
'thumbnail': self._og_search_thumbnail(webpage), 'thumbnail': self._og_search_thumbnail(webpage),