X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/63a6927374492ef47c8fd6de67d0760ace4dd0ed..e5a601f21d25b8806d04be9671c8772e331e3bda:/youtube_dl/extractor/pornhub.py diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index d9135c6..6d57e1d 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -1,47 +1,137 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import itertools import os import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( + compat_HTTPError, + compat_urllib_parse_unquote, + compat_urllib_parse_unquote_plus, compat_urllib_parse_urlparse, - compat_urllib_request, - compat_urllib_parse, +) +from ..utils import ( + ExtractorError, + int_or_none, + orderedSet, + 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': '1e19b41231a02eba417839222ac9d58e', + 'info_dict': { + 'id': '648719015', + 'ext': 'mp4', + 'title': 'Seductive Indian beauty strips down and fingers her pink pussy', + 'uploader': 'Babes', + 'duration': 361, + 'view_count': int, + 'like_count': int, + 'dislike_count': int, + 'comment_count': int, + 'age_limit': 18, + }, + }, { + # non-ASCII title + 'url': 'http://www.pornhub.com/view_video.php?viewkey=1331683002', + 'info_dict': { + 'id': '1331683002', + 'ext': 'mp4', + 'title': '重庆婷婷女王足交', + 'uploader': 'cj397186295', + 'duration': 1753, + 'view_count': int, + 'like_count': int, + 'dislike_count': int, + 'comment_count': int, + 'age_limit': 18, + }, + 'params': { + 'skip_download': True, + }, + }, { + '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) - if thumbnail: - thumbnail = compat_urllib_parse.unquote(thumbnail) + 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 from flashvars contains whitespace instead of non-ASCII (see + # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying + # on that anymore. + title = self._html_search_meta( + 'twitter:title', webpage, default=None) or self._search_regex( + (r']+class=["\']title["\'][^>]*>(?P[^<]+)', + r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1', + r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'), + webpage, 'title', group='title') + + flashvars = self._parse_json( + self._search_regex( + r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'), + video_id) + if flashvars: + thumbnail = flashvars.get('image_url') + duration = int_or_none(flashvars.get('video_duration')) + else: + title, thumbnail, duration = [None] * 3 - video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage))) + video_uploader = self._html_search_regex( + r'(?s)From: .+?<(?:a href="/users/|a href="/channels/|span class="username)[^>]+>(.+?)<', + webpage, 'uploader', fatal=False) + + view_count = self._extract_count( + r'<span class="count">([\d,\.]+)</span> views', webpage, 'view') + like_count = self._extract_count( + r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like') + dislike_count = self._extract_count( + r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike') + comment_count = self._extract_count( + r'All Comments\s*<span>\(([\d,.]+)\)', 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 = [] @@ -49,20 +139,108 @@ class PornHubIE(InfoExtractor): path = compat_urllib_parse_urlparse(video_url).path extension = os.path.splitext(path)[1][1:] format = path.split('/')[5].split('_')[:2] - format = "-".join(format) + format = '-'.join(format) + + m = re.match(r'^(?P<height>[0-9]+)[pP]-(?P<tbr>[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, + 'title': title, 'thumbnail': thumbnail, + 'duration': duration, + 'view_count': view_count, + 'like_count': like_count, + 'dislike_count': dislike_count, + 'comment_count': comment_count, 'formats': formats, 'age_limit': 18, } + + +class PornHubPlaylistBaseIE(InfoExtractor): + def _extract_entries(self, webpage): + return [ + self.url_result( + 'http://www.pornhub.com/%s' % video_url, + PornHubIE.ie_key(), video_title=title) + for video_url, title in orderedSet(re.findall( + r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"', + webpage)) + ] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + entries = self._extract_entries(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')) + + +class PornHubPlaylistIE(PornHubPlaylistBaseIE): + _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://www.pornhub.com/playlist/6201671', + 'info_dict': { + 'id': '6201671', + 'title': 'P0p4', + }, + 'playlist_mincount': 35, + }] + + +class PornHubUserVideosIE(PornHubPlaylistBaseIE): + _VALID_URL = r'https?://(?:www\.)?pornhub\.com/users/(?P<id>[^/]+)/videos' + _TESTS = [{ + 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public', + 'info_dict': { + 'id': 'zoe_ph', + }, + 'playlist_mincount': 171, + }, { + 'url': 'http://www.pornhub.com/users/rushandlia/videos', + 'only_matching': True, + }] + + def _real_extract(self, url): + user_id = self._match_id(url) + + entries = [] + for page_num in itertools.count(1): + try: + webpage = self._download_webpage( + url, user_id, 'Downloading page %d' % page_num, + query={'page': page_num}) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: + break + page_entries = self._extract_entries(webpage) + if not page_entries: + break + entries.extend(page_entries) + + return self.playlist_result(entries, user_id)