From 9933b574302ebd364d4e53f9d537024e0099d72a Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 7 Jan 2014 10:25:34 +0100 Subject: [PATCH] [pornhub] Use centralized sorting --- youtube_dl/extractor/common.py | 1 + youtube_dl/extractor/pornhub.py | 38 ++++++++++++++++++++++----------- 2 files changed, 27 insertions(+), 12 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 0ec365eaa..ce3d16903 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -501,6 +501,7 @@ def _formats_key(f): f.get('height') if f.get('height') is not None else -1, f.get('width') if f.get('width') is not None else -1, ext_preference, + f.get('tbr') if f.get('tbr') is not None else -1, f.get('vbr') if f.get('vbr') is not None else -1, f.get('abr') if f.get('abr') is not None else -1, audio_ext_preference, diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index d9135c6b9..fdda69f33 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import os import re @@ -11,16 +13,17 @@ 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 + 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015', + 'file': '648719015.mp4', + 'md5': '882f488fa1f0026f023f33576004a2ed', + 'info_dict': { + "uploader": "BABES-COM", + "title": "Seductive Indian beauty strips down and fingers her pink pussy", + "age_limit": 18 } } @@ -33,15 +36,15 @@ def _real_extract(self, url): 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) + video_title = self._html_search_regex(r'

]+>([^<]+)', webpage, 'title') + video_uploader = self._html_search_regex(r'From: (?:\s|<[^>]*>)*(.+?)<', webpage, 'uploader', fatal=False) + thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, '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('+', ' ') + password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, 'password').replace('+', ' ') video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls)) formats = [] @@ -50,13 +53,24 @@ def _real_extract(self, url): extension = os.path.splitext(path)[1][1:] format = path.split('/')[5].split('_')[:2] format = "-".join(format) + + m = re.match(r'^(?P[0-9]+)P-(?P[0-9]+)K$', 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,