diff options
author | Sergey M․ <dstftw@gmail.com> | 2018-08-22 01:44:22 +0700 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2018-08-22 01:44:22 +0700 |
commit | db192b29329696547b422d904819321077efddfe (patch) | |
tree | 62c9582b252b7d2fffa462a3ae72cdc26d07d13b /youtube_dl/extractor | |
parent | 52007de8ca6fcc2b72cbfb3fe026ea63cda88f25 (diff) |
[yourporn] Add extractor (closes #17298)
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/extractors.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/yourporn.py | 41 |
2 files changed, 42 insertions, 0 deletions
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 23ad42da9..d8e86c277 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1424,6 +1424,7 @@ from .younow import ( YouNowMomentIE, ) from .youporn import YouPornIE +from .yourporn import YourPornIE from .yourupload import YourUploadIE from .youtube import ( YoutubeIE, diff --git a/youtube_dl/extractor/yourporn.py b/youtube_dl/extractor/yourporn.py new file mode 100644 index 000000000..6602f7c03 --- /dev/null +++ b/youtube_dl/extractor/yourporn.py @@ -0,0 +1,41 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import urljoin + + +class YourPornIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?yourporn\.sexy/post/(?P<id>[^/?#&.]+)' + _TEST = { + 'url': 'https://yourporn.sexy/post/57ffcb2e1179b.html', + 'md5': '6f8682b6464033d87acaa7a8ff0c092e', + 'info_dict': { + 'id': '57ffcb2e1179b', + 'ext': 'mp4', + 'title': 'md5:c9f43630bd968267672651ba905a7d35', + 'thumbnail': r're:^https?://.*\.jpg$', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + video_url = urljoin(url, self._parse_json( + self._search_regex( + r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info', + group='data'), + video_id)[video_id]) + + title = (self._search_regex( + r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title', + default=None) or self._og_search_description(webpage)).strip() + thumbnail = self._og_search_thumbnail(webpage) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + } |