diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2013-10-28 10:44:13 +0100 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2013-10-28 10:44:13 +0100 |
commit | ebc14f251c2968f4cb6cb18610b857ecb24348c8 (patch) | |
tree | d33050d96f576d2a9710ccea7fac729116358025 /youtube_dl/extractor/pornhub.py | |
parent | d41e6efc852c34da582790a54ecc4f5e9dbbedda (diff) | |
parent | 8ffa13e03e995f2009d8240cbdc6ba7aba9d3759 (diff) | |
download | youtube-dl-ebc14f251c2968f4cb6cb18610b857ecb24348c8.tar.xz |
Merge remote-tracking branch 'origin/master'
Diffstat (limited to 'youtube_dl/extractor/pornhub.py')
-rw-r--r-- | youtube_dl/extractor/pornhub.py | 69 |
1 files changed, 69 insertions, 0 deletions
diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py new file mode 100644 index 000000000..5e2454f1b --- /dev/null +++ b/youtube_dl/extractor/pornhub.py @@ -0,0 +1,69 @@ +import os +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse_urlparse, + compat_urllib_request, + compat_urllib_parse, + unescapeHTML, +) +from ..aes import ( + aes_decrypt_text +) + +class PornHubIE(InfoExtractor): + _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>pornhub\.com/view_video\.php\?viewkey=(?P<videoid>[0-9]+))' + _TEST = { + u'url': u'http://www.pornhub.com/view_video.php?viewkey=648719015', + u'file': u'648719015.mp4', + u'md5': u'882f488fa1f0026f023f33576004a2ed', + u'info_dict': { + u"uploader": u"BABES-COM", + u"title": u"Seductive Indian beauty strips down and fingers her pink pussy", + u"age_limit": 18 + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('videoid') + url = 'http://www.' + mobj.group('url') + + req = compat_urllib_request.Request(url) + req.add_header('Cookie', 'age_verified=1') + webpage = self._download_webpage(req, video_id) + + video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, u'title') + video_uploader = self._html_search_regex(r'<b>From: </b>(?:\s|<[^>]*>)*(.+?)<', webpage, u'uploader', fatal=False) + thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, u'thumbnail', fatal=False) + if thumbnail: + thumbnail = compat_urllib_parse.unquote(thumbnail) + + video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage))) + if webpage.find('"encrypted":true') != -1: + password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, u'password').replace('+', ' ') + video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls)) + + formats = [] + for video_url in video_urls: + path = compat_urllib_parse_urlparse( video_url ).path + extension = os.path.splitext( path )[1][1:] + format = path.split('/')[5].split('_')[:2] + format = "-".join( format ) + formats.append({ + 'url': video_url, + 'ext': extension, + 'format': format, + 'format_id': format, + }) + formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-')))) + + return { + 'id': video_id, + 'uploader': video_uploader, + 'title': video_title, + 'thumbnail': thumbnail, + 'formats': formats, + 'age_limit': 18, + } |