From 850837b67ada7cf0a139117a7335aa40990cd0d7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 18 Aug 2016 23:52:41 +0700 Subject: [PATCH] [porncom] Add extractor (Closes #2251, closes #10251) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/porncom.py | 89 ++++++++++++++++++++++++++++++ 2 files changed, 90 insertions(+) create mode 100644 youtube_dl/extractor/porncom.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index e61bb11c3..6c5d46015 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -642,6 +642,7 @@ from .podomatic import PodomaticIE from .pokemon import PokemonIE from .polskieradio import PolskieRadioIE from .porn91 import Porn91IE +from .porncom import PornComIE from .pornhd import PornHdIE from .pornhub import ( PornHubIE, diff --git a/youtube_dl/extractor/porncom.py b/youtube_dl/extractor/porncom.py new file mode 100644 index 000000000..4baf79688 --- /dev/null +++ b/youtube_dl/extractor/porncom.py @@ -0,0 +1,89 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_urlparse +from ..utils import ( + int_or_none, + js_to_json, + parse_filesize, + str_to_int, +) + + +class PornComIE(InfoExtractor): + _VALID_URL = r'https?://(?:[a-zA-Z]+\.)?porn\.com/videos/(?:(?P[^/]+)-)?(?P\d+)' + _TESTS = [{ + 'url': 'http://www.porn.com/videos/teen-grabs-a-dildo-and-fucks-her-pussy-live-on-1hottie-i-rec-2603339', + 'md5': '3f30ce76267533cd12ba999263156de7', + 'info_dict': { + 'id': '2603339', + 'display_id': 'teen-grabs-a-dildo-and-fucks-her-pussy-live-on-1hottie-i-rec', + 'ext': 'mp4', + 'title': 'Teen grabs a dildo and fucks her pussy live on 1hottie, I rec', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 551, + 'view_count': int, + 'age_limit': 18, + }, + }, { + 'url': 'http://se.porn.com/videos/marsha-may-rides-seth-on-top-of-his-thick-cock-2658067', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') or video_id + + webpage = self._download_webpage(url, display_id) + + config = self._parse_json( + self._search_regex( + r'=\s*({.+?})\s*,\s*[\da-zA-Z_]+\s*=', + webpage, 'config', default='{}'), + display_id, transform_source=js_to_json, fatal=False) + + if config: + title = config['title'] + formats = [{ + 'url': stream['url'], + 'format_id': stream.get('id'), + 'height': int_or_none(self._search_regex( + r'^(\d+)[pP]', stream.get('id') or '', 'height', default=None)) + } for stream in config['streams'] if stream.get('url')] + thumbnail = (compat_urlparse.urljoin( + config['thumbCDN'], config['poster']) + if config.get('thumbCDN') and config.get('poster') else None) + duration = int_or_none(config.get('length')) + else: + title = self._search_regex( + (r'([^<]+)', r']*>([^<]+)'), + webpage, 'title') + formats = [{ + 'url': compat_urlparse.urljoin(url, format_url), + 'format_id': '%sp' % height, + 'height': int(height), + 'filesize_approx': parse_filesize(filesize), + } for format_url, height, filesize in re.findall( + r']+href="(/download/[^"]+)">MPEG4 (\d+)p]*>(\d+\s+[a-zA-Z]+)<', + webpage)] + thumbnail = None + duration = None + + self._sort_formats(formats) + + view_count = str_to_int(self._search_regex( + r'class=["\']views["\'][^>]*>

([\d,.]+)', webpage, 'view count')) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + 'view_count': view_count, + 'formats': formats, + 'age_limit': 18, + }