X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fpornhub.py;h=965940a4b07fc5d17fa61cf1208a029ce4794216;hb=5c2266df4b9aeb7881ed8c026a038e2a25e43734;hp=d9135c6b929765e87b13e58f6fd6af5567c55199;hpb=2a203a6cda7171d5417423a43b640c1d5ba7e7e0;p=youtube-dl diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index d9135c6b9..965940a4b 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -1,47 +1,93 @@ +from __future__ import unicode_literals + import os import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( + compat_urllib_parse_unquote, + compat_urllib_parse_unquote_plus, compat_urllib_parse_urlparse, - compat_urllib_request, - compat_urllib_parse, +) +from ..utils import ( + ExtractorError, + sanitized_Request, + str_to_int, ) from ..aes import ( aes_decrypt_text ) + class PornHubIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?Ppornhub\.com/view_video\.php\?viewkey=(?P[0-9a-f]+))' - _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 + _VALID_URL = r'https?://(?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)(?P[0-9a-z]+)' + _TESTS = [{ + 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015', + 'md5': '882f488fa1f0026f023f33576004a2ed', + 'info_dict': { + 'id': '648719015', + 'ext': 'mp4', + "uploader": "Babes", + "title": "Seductive Indian beauty strips down and fingers her pink pussy", + "age_limit": 18 } - } + }, { + 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d', + 'only_matching': True, + }, { + 'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862', + 'only_matching': True, + }] + + @classmethod + def _extract_url(cls, webpage): + mobj = re.search( + r']+?src=(["\'])(?P(?:https?:)?//(?:www\.)?pornhub\.com/embed/\d+)\1', webpage) + if mobj: + return mobj.group('url') + + def _extract_count(self, pattern, webpage, name): + return str_to_int(self._search_regex( + pattern, webpage, '%s count' % name, fatal=False)) def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') - url = 'http://www.' + mobj.group('url') + video_id = self._match_id(url) - req = compat_urllib_request.Request(url) + req = sanitized_Request( + 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id) req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) - video_title = self._html_search_regex(r'

]+>([^<]+)', webpage, u'title') - video_uploader = self._html_search_regex(r'From: (?:\s|<[^>]*>)*(.+?)<', webpage, u'uploader', fatal=False) - thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, u'thumbnail', fatal=False) + error_msg = self._html_search_regex( + r'(?s)
(.*?)
', + webpage, 'error message', default=None) + if error_msg: + error_msg = re.sub(r'\s+', ' ', error_msg) + raise ExtractorError( + 'PornHub said: %s' % error_msg, + expected=True, video_id=video_id) + + video_title = self._html_search_regex(r'

]+>([^<]+)', webpage, 'title') + video_uploader = self._html_search_regex( + r'(?s)From: .+?<(?:a href="/users/|a href="/channels/|span class="username)[^>]+>(.+?)<', + webpage, 'uploader', fatal=False) + thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False) if thumbnail: - thumbnail = compat_urllib_parse.unquote(thumbnail) + thumbnail = compat_urllib_parse_unquote(thumbnail) - video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage))) + view_count = self._extract_count( + r'([\d,\.]+) views', webpage, 'view') + like_count = self._extract_count( + r'([\d,\.]+)', webpage, 'like') + dislike_count = self._extract_count( + r'([\d,\.]+)', webpage, 'dislike') + comment_count = self._extract_count( + r'All Comments\s*\(([\d,.]+)\)', webpage, 'comment') + + video_urls = list(map(compat_urllib_parse_unquote, re.findall(r"player_quality_[0-9]{3}p\s*=\s*'([^']+)'", webpage))) if webpage.find('"encrypted":true') != -1: - password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, u'password').replace('+', ' ') + password = compat_urllib_parse_unquote_plus( + self._search_regex(r'"video_title":"([^"]+)', webpage, 'password')) video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls)) formats = [] @@ -50,19 +96,64 @@ class PornHubIE(InfoExtractor): extension = os.path.splitext(path)[1][1:] format = path.split('/')[5].split('_')[:2] format = "-".join(format) + + m = re.match(r'^(?P[0-9]+)[pP]-(?P[0-9]+)[kK]$', format) + if m is None: + height = None + tbr = None + else: + height = int(m.group('height')) + tbr = int(m.group('tbr')) + formats.append({ 'url': video_url, 'ext': extension, 'format': format, 'format_id': format, + 'tbr': tbr, + 'height': height, }) - formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-')))) + self._sort_formats(formats) return { 'id': video_id, 'uploader': video_uploader, 'title': video_title, 'thumbnail': thumbnail, + 'view_count': view_count, + 'like_count': like_count, + 'dislike_count': dislike_count, + 'comment_count': comment_count, 'formats': formats, 'age_limit': 18, } + + +class PornHubPlaylistIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P\d+)' + _TESTS = [{ + 'url': 'http://www.pornhub.com/playlist/6201671', + 'info_dict': { + 'id': '6201671', + 'title': 'P0p4', + }, + 'playlist_mincount': 35, + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + entries = [ + self.url_result('http://www.pornhub.com/%s' % video_url, 'PornHub') + for video_url in set(re.findall('href="/?(view_video\.php\?viewkey=\d+[^"]*)"', webpage)) + ] + + playlist = self._parse_json( + self._search_regex( + r'playlistObject\s*=\s*({.+?});', webpage, 'playlist'), + playlist_id) + + return self.playlist_result( + entries, playlist_id, playlist.get('title'), playlist.get('description'))