depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-29 05:32:00 +00:00
Code Issues Releases Wiki Activity

[videofy.me] Fixing extractor to work after site redesign

Browse source
This commit is contained in:
Petar Kukolj 2018-10-02 18:28:46 +02:00
parent 05e7c184da
commit a6246c1f5b
1 changed files with 46 additions and 26 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

72
youtube_dl/extractor/videofyme.py
View file

@ -1,9 +1,16 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import json
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
parse_iso8601, parse_iso8601,
unescapeHTML,
sanitize_url,
clean_html,
get_element_by_attribute,
js_to_json,
) )
@ -11,42 +18,55 @@ class VideofyMeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.videofy\.me/.+?|p\.videofy\.me/v)/(?P<id>\d+)(&|#|$)' _VALID_URL = r'https?://(?:www\.videofy\.me/.+?|p\.videofy\.me/v)/(?P<id>\d+)(&|#|$)'
IE_NAME = 'videofy.me' IE_NAME = 'videofy.me'
_TEST = { _TESTS = [{
'url': 'http://www.videofy.me/thisisvideofyme/1100701', 'url': 'https://www.videofy.me/v/24582',
'md5': 'c77d700bdc16ae2e9f3c26019bd96143', 'md5': '1e46140bacdae8959827903cecd054d9',
'info_dict': { 'info_dict': {
'id': '1100701', 'id': '24582',
'ext': 'mp4', 'ext': 'mp4',
'title': 'This is VideofyMe', 'title': 'The VideofyMe app demo!',
'description': '', 'description': 'This is VideofyMe.',
'upload_date': '20130326', 'upload_date': '20120607',
'timestamp': 1364288959, 'timestamp': 1339070671,
'uploader': 'VideofyMe', 'uploader': 'oskarglauser',
'uploader_id': 'thisisvideofyme', 'uploader_id': 7010,
'view_count': int, 'view_count': int,
'likes': int,
'comment_count': int,
}, },
} }, {
'url': 'https://www.videofy.me/v/2975905',
'md5': '79ad4498ab14dec72e815a8f85c7641c',
'info_dict': {
'id': '2975905',
'ext': 'mp4',
'title': 'But',
'description': '',
'upload_date': '20180126',
'timestamp': 1516931131,
'uploader': 'iamatlien',
'uploader_id': 1798214,
'view_count': int,
},
},]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
config = self._download_json('http://vf-player-info-loader.herokuapp.com/%s.json' % video_id, video_id)['videoinfo'] page = self._download_webpage(url, video_id)
video = config.get('video') video_info = json.loads(get_element_by_attribute('type', 'application/ld+json', page))
blog = config.get('blog', {})
meta = self._download_json('https://www.videofy.me/wp-json/wp/v2/posts/%s' % video_id, video_id)
uploader_id = meta.get('author')
uploader_name = self._download_json('https://www.videofy.me/wp-json/wp/v2/users/%s' % uploader_id, uploader_id, fatal=False).get('name')
return { return {
'id': video_id, 'id': video_id,
'title': video['title'], 'title': video_info['name'],
'url': video['sources']['source']['url'], 'url': video_info['contentUrl'],
'thumbnail': video.get('thumb'), 'thumbnail': video_info.get('thumbnailUrl'),
'description': video.get('description'), 'description': clean_html(video_info.get('description')),
'timestamp': parse_iso8601(video.get('date')), 'timestamp': parse_iso8601(video_info.get('uploadDate')),
'uploader': blog.get('name'), 'uploader_id': uploader_id,
'uploader_id': blog.get('identifier'), 'uploader': uploader_name,
'view_count': int_or_none(self._search_regex(r'([0-9]+)', video.get('views'), 'view count', fatal=False)), 'view_count': int_or_none(video_info.get('interactionCount')),
'likes': int_or_none(video.get('likes')),
'comment_count': int_or_none(video.get('nrOfComments')),
} }