X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Fextractor%2Fpornhub.py;h=6d57e1d35eb567b26f65dea8cc74c653f955c08f;hb=427cd050a3b64319c19e4596d8885378604e388e;hp=405dbf0063b56c967403e2214a9ab699a9963084;hpb=40e146aa1e1a8fd57d3f84b0a541174f56fa5dba;p=youtube-dl diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 405dbf006..6d57e1d35 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -1,16 +1,21 @@ +# coding: utf-8 from __future__ import unicode_literals +import itertools 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, ) from ..utils import ( ExtractorError, + int_or_none, + orderedSet, sanitized_Request, str_to_int, ) @@ -23,14 +28,37 @@ class PornHubIE(InfoExtractor): _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', + 'md5': '1e19b41231a02eba417839222ac9d58e', 'info_dict': { 'id': '648719015', 'ext': 'mp4', - 'uploader': 'Babes', 'title': 'Seductive Indian beauty strips down and fingers her pink pussy', - 'age_limit': 18 - } + '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, @@ -67,13 +95,29 @@ class PornHubIE(InfoExtractor): 'PornHub said: %s' % error_msg, expected=True, video_id=video_id) - video_title = self._html_search_regex(r'

]+>([^<]+)', webpage, 'title') + # 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_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) view_count = self._extract_count( r'<span class="count">([\d,\.]+)</span> views', webpage, 'view') @@ -118,8 +162,9 @@ class PornHubIE(InfoExtractor): 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, @@ -132,9 +177,12 @@ class PornHubIE(InfoExtractor): class PornHubPlaylistBaseIE(InfoExtractor): def _extract_entries(self, webpage): return [ - self.url_result('http://www.pornhub.com/%s' % video_url, 'PornHub') - for video_url in set(re.findall( - r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"', webpage)) + 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): @@ -168,16 +216,31 @@ class PornHubPlaylistIE(PornHubPlaylistBaseIE): class PornHubUserVideosIE(PornHubPlaylistBaseIE): _VALID_URL = r'https?://(?:www\.)?pornhub\.com/users/(?P<id>[^/]+)/videos' _TESTS = [{ - 'url': 'http://www.pornhub.com/users/rushandlia/videos', + 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public', 'info_dict': { - 'id': 'rushandlia', + 'id': 'zoe_ph', }, - 'playlist_mincount': 13, + '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) - webpage = self._download_webpage(url, user_id) - - return self.playlist_result(self._extract_entries(webpage), user_id) + 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)