From 54fdf7cc519cac42399215bb4b5474198079d767 Mon Sep 17 00:00:00 2001 From: v-delta Date: Thu, 29 Aug 2019 15:25:04 +0200 Subject: [PATCH 1/2] [sxyprn] Add new extractor --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/sxyprn.py | 56 ++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+) create mode 100644 youtube_dl/extractor/sxyprn.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 06de556b7..bcf3b9992 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1096,6 +1096,7 @@ from .svt import ( SVTSeriesIE, ) from .swrmediathek import SWRMediathekIE +from .sxyprn import SxyPrnIE from .syfy import SyfyIE from .sztvhu import SztvHuIE from .tagesschau import ( diff --git a/youtube_dl/extractor/sxyprn.py b/youtube_dl/extractor/sxyprn.py new file mode 100644 index 000000000..bc5dc71e8 --- /dev/null +++ b/youtube_dl/extractor/sxyprn.py @@ -0,0 +1,56 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + parse_duration, +) + + +class SxyPrnIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?sxyprn\.com/post/(?P[^/?#&.]+)' + _TEST = { + 'url': 'https://sxyprn.com/post/57ffcb2e1179b.html', + 'md5': '6f8682b6464033d87acaa7a8ff0c092e', + 'info_dict': { + 'id': '57ffcb2e1179b', + 'ext': 'mp4', + 'title': 'md5:c9f43630bd968267672651ba905a7d35', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 165, + 'age_limit': 18, + }, + 'params': { + 'skip_download': True, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + url_parts = self._parse_json(self._search_regex( + r'data-vnfo=(["\'])(?P{.+?})\1', webpage, 'data info', group='data'), video_id)[video_id].split("/") + + aid = self._search_regex(r'data-aid=\'(.*?)\'', webpage, 'aid') + + video_url = 'https://' + url_parts[2] + '.trafficdeposit.com/video/' + url_parts[3] + '/' + url_parts[ + 4] + '/' + url_parts[5] + '/' + aid + '/' + video_id + '.mp4' + + title = (self._search_regex( + r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title', + default=None) or self._og_search_description(webpage)).strip() + thumbnail = self._og_search_thumbnail(webpage) + duration = parse_duration(self._search_regex( + r'duration\s*:\s*<[^>]+>([\d:]+)', webpage, 'duration', + default=None)) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + 'age_limit': 18, + } From 12113ad2491ecb7ad136e1d1db21beaa4c49dc70 Mon Sep 17 00:00:00 2001 From: v-delta Date: Thu, 29 Aug 2019 16:02:15 +0200 Subject: [PATCH 2/2] [sxyprn] Make YourPornIE not match URLs from https://sxyprn.com --- youtube_dl/extractor/yourporn.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/yourporn.py b/youtube_dl/extractor/yourporn.py index 8a2d5f63b..efa31036b 100644 --- a/youtube_dl/extractor/yourporn.py +++ b/youtube_dl/extractor/yourporn.py @@ -8,7 +8,7 @@ from ..utils import ( class YourPornIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:yourporn\.sexy|sxyprn\.com)/post/(?P[^/?#&.]+)' + _VALID_URL = r'https?://(?:www\.)?yourporn\.sexy/post/(?P[^/?#&.]+)' _TESTS = [{ 'url': 'https://yourporn.sexy/post/57ffcb2e1179b.html', 'md5': '6f8682b6464033d87acaa7a8ff0c092e',