diff --git a/test/test_utils.py b/test/test_utils.py index 3d14f61fbf..8d89979775 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -211,6 +211,9 @@ def test_parse_duration(self): self.assertEqual(parse_duration('00:01:01'), 61) self.assertEqual(parse_duration('x:y'), None) self.assertEqual(parse_duration('3h11m53s'), 11513) + self.assertEqual(parse_duration('3h 11m 53s'), 11513) + self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513) + self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513) self.assertEqual(parse_duration('62m45s'), 3765) self.assertEqual(parse_duration('6m59s'), 419) self.assertEqual(parse_duration('49s'), 49) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 1479d998a2..6d94984def 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -393,6 +393,7 @@ from .viki import VikiIE from .vk import VKIE from .vodlocker import VodlockerIE +from .vporn import VpornIE from .vube import VubeIE from .vuclip import VuClipIE from .vulture import VultureIE diff --git a/youtube_dl/extractor/vporn.py b/youtube_dl/extractor/vporn.py new file mode 100644 index 0000000000..426369c51b --- /dev/null +++ b/youtube_dl/extractor/vporn.py @@ -0,0 +1,99 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + str_to_int, +) + + +class VpornIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?vporn\.com/[^/]+/(?P[^/]+)/(?P\d+)' + _TEST = { + 'url': 'http://www.vporn.com/masturbation/violet-on-her-th-birthday/497944/', + 'md5': 'facf37c1b86546fa0208058546842c55', + 'info_dict': { + 'id': '497944', + 'display_id': 'violet-on-her-th-birthday', + 'ext': 'mp4', + 'title': 'Violet on her 19th birthday', + 'description': 'Violet dances in front of the camera which is sure to get you horny.', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'kileyGrope', + 'categories': ['Masturbation', 'Teen'], + 'duration': 393, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + title = self._html_search_regex( + r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip() + description = self._html_search_regex( + r'
(.*?)
', webpage, 'description', fatal=False) + thumbnail = self._html_search_regex( + r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description', fatal=False, default=None) + if thumbnail: + thumbnail = 'http://www.vporn.com' + thumbnail + + uploader = self._html_search_regex( + r'(?s)UPLOADED BY.*?([^<]+)', + webpage, 'uploader', fatal=False) + + categories = re.findall(r'([^<]+)', webpage) + + duration = parse_duration(self._search_regex( + r'duration (\d+ min \d+ sec)', webpage, 'duration', fatal=False)) + + view_count = str_to_int(self._html_search_regex( + r'([\d,\.]+) VIEWS', webpage, 'view count', fatal=False)) + like_count = str_to_int(self._html_search_regex( + r'([\d,\.]+)', webpage, 'like count', fatal=False)) + dislike_count = str_to_int(self._html_search_regex( + r'([\d,\.]+)', webpage, 'dislike count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'

Comments \(([\d,\.]+)\)

', webpage, 'comment count', fatal=False)) + + formats = [] + + for video in re.findall(r'flashvars\.videoUrl([^=]+?)\s*=\s*"([^"]+)"', webpage): + video_url = video[1] + fmt = { + 'url': video_url, + 'format_id': video[0], + } + m = re.search(r'_(?P\d+)x(?P\d+)_(?P\d+)k\.mp4$', video_url) + if m: + fmt.update({ + 'width': int(m.group('width')), + 'height': int(m.group('height')), + 'vbr': int(m.group('vbr')), + }) + formats.append(fmt) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'categories': categories, + 'duration': duration, + 'view_count': view_count, + 'like_count': like_count, + 'dislike_count': dislike_count, + 'comment_count': comment_count, + 'age_limit': 18, + 'formats': formats, + } diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 4f02108720..e077504348 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1332,8 +1332,10 @@ def parse_duration(s): if s is None: return None + s = s.strip() + m = re.match( - r'(?:(?:(?P[0-9]+)[:h])?(?P[0-9]+)[:m])?(?P[0-9]+)s?(?::[0-9]+)?(?P\.[0-9]+)?$', s) + r'(?:(?:(?P[0-9]+)\s*(?:[:h]|hours?)\s*)?(?P[0-9]+)\s*(?:[:m]|mins?|minutes?)\s*)?(?P[0-9]+)(?P\.[0-9]+)?\s*(?:s|secs?|seconds?)?$', s) if not m: return None res = int(m.group('secs'))