X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/1270059fa7cf720bc0533c2cdfe6370923ae4e20..291f6705b350d9f813b12efb37b7963555758994:/youtube_dl/extractor/pornhub.py?ds=sidebyside diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 9ce513a..19eaf38 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -4,28 +4,22 @@ from __future__ import unicode_literals import functools import itertools import operator -# import os import re from .common import InfoExtractor from ..compat import ( compat_HTTPError, - # compat_urllib_parse_unquote, - # compat_urllib_parse_unquote_plus, - # compat_urllib_parse_urlparse, + compat_str, ) from ..utils import ( ExtractorError, int_or_none, js_to_json, orderedSet, - # sanitized_Request, remove_quotes, str_to_int, + url_or_none, ) -# from ..aes import ( -# aes_decrypt_text -# ) class PornHubIE(InfoExtractor): @@ -33,7 +27,7 @@ class PornHubIE(InfoExtractor): _VALID_URL = r'''(?x) https?:// (?: - (?:[a-z]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| + (?:[^/]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| (?:www\.)?thumbzilla\.com/video/ ) (?P[\da-z]+) @@ -46,6 +40,7 @@ class PornHubIE(InfoExtractor): 'ext': 'mp4', 'title': 'Seductive Indian beauty strips down and fingers her pink pussy', 'uploader': 'Babes', + 'upload_date': '20130628', 'duration': 361, 'view_count': int, 'like_count': int, @@ -62,7 +57,8 @@ class PornHubIE(InfoExtractor): 'id': '1331683002', 'ext': 'mp4', 'title': '重庆婷婷女王足交', - 'uploader': 'cj397186295', + 'uploader': 'Unknown', + 'upload_date': '20150213', 'duration': 1753, 'view_count': int, 'like_count': int, @@ -75,6 +71,31 @@ class PornHubIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + # subtitles + 'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7', + 'info_dict': { + 'id': 'ph5af5fef7c2aa7', + 'ext': 'mp4', + 'title': 'BFFS - Cute Teen Girls Share Cock On the Floor', + 'uploader': 'BFFs', + 'duration': 622, + 'view_count': int, + 'like_count': int, + 'dislike_count': int, + 'comment_count': int, + 'age_limit': 18, + 'tags': list, + 'categories': list, + 'subtitles': { + 'en': [{ + "ext": 'srt' + }] + }, + }, + 'params': { + 'skip_download': True, + }, }, { 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d', 'only_matching': True, @@ -121,7 +142,7 @@ class PornHubIE(InfoExtractor): self._set_cookie('pornhub.com', 'platform', platform) return self._download_webpage( 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id, - video_id) + video_id, 'Downloading %s webpage' % platform) webpage = dl_webpage('pc') @@ -134,60 +155,114 @@ class PornHubIE(InfoExtractor): 'PornHub said: %s' % error_msg, expected=True, video_id=video_id) - tv_webpage = dl_webpage('tv') - - assignments = self._search_regex( - r'(var.+?mediastring.+?)', tv_webpage, - 'encoded url').split(';') - - js_vars = {} - - def parse_js_value(inp): - inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp) - if '+' in inp: - inps = inp.split('+') - return functools.reduce( - operator.concat, map(parse_js_value, inps)) - inp = inp.strip() - if inp in js_vars: - return js_vars[inp] - return remove_quotes(inp) - - for assn in assignments: - assn = assn.strip() - if not assn: - continue - assn = re.sub(r'var\s+', '', assn) - vname, value = assn.split('=', 1) - js_vars[vname] = parse_js_value(value) - - video_url = js_vars['mediastring'] - - title = self._search_regex( - r'

([^>]+)

', tv_webpage, 'title', default=None) - # 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 = title or self._html_search_meta( + 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') + video_urls = [] + video_urls_set = set() + subtitles = {} + flashvars = self._parse_json( self._search_regex( r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'), video_id) if flashvars: + subtitle_url = url_or_none(flashvars.get('closedCaptionsFile')) + if subtitle_url: + subtitles.setdefault('en', []).append({ + 'url': subtitle_url, + 'ext': 'srt', + }) thumbnail = flashvars.get('image_url') duration = int_or_none(flashvars.get('video_duration')) + media_definitions = flashvars.get('mediaDefinitions') + if isinstance(media_definitions, list): + for definition in media_definitions: + if not isinstance(definition, dict): + continue + video_url = definition.get('videoUrl') + if not video_url or not isinstance(video_url, compat_str): + continue + if video_url in video_urls_set: + continue + video_urls_set.add(video_url) + video_urls.append( + (video_url, int_or_none(definition.get('quality')))) else: - title, thumbnail, duration = [None] * 3 + thumbnail, duration = [None] * 2 + + if not video_urls: + tv_webpage = dl_webpage('tv') + + assignments = self._search_regex( + r'(var.+?mediastring.+?)</script>', tv_webpage, + 'encoded url').split(';') + + js_vars = {} + + def parse_js_value(inp): + inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp) + if '+' in inp: + inps = inp.split('+') + return functools.reduce( + operator.concat, map(parse_js_value, inps)) + inp = inp.strip() + if inp in js_vars: + return js_vars[inp] + return remove_quotes(inp) + + for assn in assignments: + assn = assn.strip() + if not assn: + continue + assn = re.sub(r'var\s+', '', assn) + vname, value = assn.split('=', 1) + js_vars[vname] = parse_js_value(value) + + video_url = js_vars['mediastring'] + if video_url not in video_urls_set: + video_urls.append((video_url, None)) + video_urls_set.add(video_url) + + for mobj in re.finditer( + r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1', + webpage): + video_url = mobj.group('url') + if video_url not in video_urls_set: + video_urls.append((video_url, None)) + video_urls_set.add(video_url) + + upload_date = None + formats = [] + for video_url, height in video_urls: + if not upload_date: + upload_date = self._search_regex( + r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None) + if upload_date: + upload_date = upload_date.replace('/', '') + tbr = None + mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url) + if mobj: + if not height: + height = int(mobj.group('height')) + tbr = int(mobj.group('tbr')) + formats.append({ + 'url': video_url, + 'format_id': '%dp' % height if height else None, + 'height': height, + 'tbr': tbr, + }) + self._sort_formats(formats) video_uploader = self._html_search_regex( - r'(?s)From: .+?<(?:a\b[^>]+\bhref=["\']/(?:user|channel)s/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<', + r'(?s)From: .+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<', webpage, 'uploader', fatal=False) view_count = self._extract_count( @@ -210,8 +285,8 @@ class PornHubIE(InfoExtractor): return { 'id': video_id, - 'url': video_url, 'uploader': video_uploader, + 'upload_date': upload_date, 'title': title, 'thumbnail': thumbnail, 'duration': duration, @@ -219,10 +294,11 @@ class PornHubIE(InfoExtractor): 'like_count': like_count, 'dislike_count': dislike_count, 'comment_count': comment_count, - # 'formats': formats, + 'formats': formats, 'age_limit': 18, 'tags': tags, 'categories': categories, + 'subtitles': subtitles, } @@ -264,7 +340,7 @@ class PornHubPlaylistBaseIE(InfoExtractor): class PornHubPlaylistIE(PornHubPlaylistBaseIE): - _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)' + _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/playlist/(?P<id>\d+)' _TESTS = [{ 'url': 'http://www.pornhub.com/playlist/4667351', 'info_dict': { @@ -272,11 +348,14 @@ class PornHubPlaylistIE(PornHubPlaylistBaseIE): 'title': 'Nataly Hot', }, 'playlist_mincount': 2, + }, { + 'url': 'https://de.pornhub.com/playlist/4667351', + 'only_matching': True, }] class PornHubUserVideosIE(PornHubPlaylistBaseIE): - _VALID_URL = r'https?://(?:www\.)?pornhub\.com/(?:user|channel)s/(?P<id>[^/]+)/videos' + _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos' _TESTS = [{ 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public', 'info_dict': { @@ -305,6 +384,15 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE): # Most Viewed Videos 'url': 'https://www.pornhub.com/channels/povd/videos?o=vi', 'only_matching': True, + }, { + 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public', + 'only_matching': True, + }, { + 'url': 'https://www.pornhub.com/model/jayndrea/videos/upload', + 'only_matching': True, + }, { + 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload', + 'only_matching': True, }] def _real_extract(self, url):