diff options
Diffstat (limited to 'hypervideo_dl/extractor/youporn.py')
| -rw-r--r-- | hypervideo_dl/extractor/youporn.py | 39 |
1 files changed, 26 insertions, 13 deletions
diff --git a/hypervideo_dl/extractor/youporn.py b/hypervideo_dl/extractor/youporn.py index 5feb568..8f1b991 100644 --- a/hypervideo_dl/extractor/youporn.py +++ b/hypervideo_dl/extractor/youporn.py @@ -1,11 +1,10 @@ -from __future__ import unicode_literals - import re from .common import InfoExtractor from ..utils import ( extract_attributes, int_or_none, + merge_dicts, str_to_int, unified_strdate, url_or_none, @@ -14,6 +13,7 @@ from ..utils import ( class YouPornIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?' + _EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)'] _TESTS = [{ 'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/', 'md5': '3744d24c50438cf5b6f6d59feb5055c2', @@ -65,14 +65,26 @@ class YouPornIE(InfoExtractor): }, { 'url': 'https://www.youporn.com/watch/13922959/femdom-principal/', 'only_matching': True, + }, { + 'url': 'https://www.youporn.com/watch/16290308/tinderspecial-trailer1/', + 'info_dict': { + 'id': '16290308', + 'age_limit': 18, + 'categories': [], + 'description': 'md5:00ea70f642f431c379763c17c2f396bc', + 'display_id': 'tinderspecial-trailer1', + 'duration': 298.0, + 'ext': 'mp4', + 'upload_date': '20201123', + 'uploader': 'Ersties', + 'tags': [], + 'thumbnail': 'https://fi1.ypncdn.com/202011/23/16290308/original/8/tinderspecial-trailer1-8(m=eaAaaEPbaaaa).jpg', + 'timestamp': 1606089600, + 'title': 'Tinder In Real Life', + 'view_count': int, + } }] - @staticmethod - def _extract_urls(webpage): - return re.findall( - r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)', - webpage) - def _real_extract(self, url): mobj = self._match_valid_url(url) video_id = mobj.group('id') @@ -110,7 +122,6 @@ class YouPornIE(InfoExtractor): }) f['height'] = height formats.append(f) - self._sort_formats(formats) webpage = self._download_webpage( 'http://www.youporn.com/watch/%s' % video_id, display_id, @@ -137,9 +148,10 @@ class YouPornIE(InfoExtractor): r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>', webpage, 'uploader', fatal=False) upload_date = unified_strdate(self._html_search_regex( - [r'UPLOADED:\s*<span>([^<]+)', + (r'UPLOADED:\s*<span>([^<]+)', r'Date\s+[Aa]dded:\s*<span>([^<]+)', - r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>'], + r'''(?s)<div[^>]+class=["']videoInfo(?:Date|Time)\b[^>]*>(.+?)</div>''', + r'(?s)<label\b[^>]*>Uploaded[^<]*</label>\s*<span\b[^>]*>(.+?)</span>'), webpage, 'upload date', fatal=False)) age_limit = self._rta_search(webpage) @@ -166,7 +178,8 @@ class YouPornIE(InfoExtractor): r'(?s)Tags:.*?</div>\s*<div[^>]+class=["\']tagBoxContent["\'][^>]*>(.+?)</div>', 'tags') - return { + data = self._search_json_ld(webpage, video_id, expected_type='VideoObject', fatal=False) + return merge_dicts(data, { 'id': video_id, 'display_id': display_id, 'title': title, @@ -181,4 +194,4 @@ class YouPornIE(InfoExtractor): 'tags': tags, 'age_limit': age_limit, 'formats': formats, - } + }) |