From 567a5996cac5f3ba2d06748cbbfb295eab48074c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?D=C3=A9stin=20Reed?= Date: Sat, 1 Oct 2016 15:34:46 +0200 Subject: [PATCH] [pornoxo] Use JWPlatform to improve metadata extraction --- youtube_dl/extractor/pornoxo.py | 31 ++++++++++++------------------- 1 file changed, 12 insertions(+), 19 deletions(-) diff --git a/youtube_dl/extractor/pornoxo.py b/youtube_dl/extractor/pornoxo.py index 202f58673..3c9087f2d 100644 --- a/youtube_dl/extractor/pornoxo.py +++ b/youtube_dl/extractor/pornoxo.py @@ -2,13 +2,13 @@ import re -from .common import InfoExtractor +from .jwplatform import JWPlatformBaseIE from ..utils import ( str_to_int, ) -class PornoXOIE(InfoExtractor): +class PornoXOIE(JWPlatformBaseIE): _VALID_URL = r'https?://(?:www\.)?pornoxo\.com/videos/(?P\d+)/(?P[^/]+)\.html' _TEST = { 'url': 'http://www.pornoxo.com/videos/7564/striptease-from-sexy-secretary.html', @@ -17,7 +17,8 @@ class PornoXOIE(InfoExtractor): 'id': '7564', 'ext': 'flv', 'title': 'Striptease From Sexy Secretary!', - 'description': 'Striptease From Sexy Secretary!', + 'display_id': 'striptease-from-sexy-secretary', + 'description': 'md5:0ee35252b685b3883f4a1d38332f9980', 'categories': list, # NSFW 'thumbnail': 're:https?://.*\.jpg$', 'age_limit': 18, @@ -26,23 +27,14 @@ class PornoXOIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id, display_id = mobj.groups() webpage = self._download_webpage(url, video_id) - - video_url = self._html_search_regex( - r'\'file\'\s*:\s*"([^"]+)"', webpage, 'video_url') + video_data = self._extract_jwplayer_data(webpage, video_id, require_title=False) title = self._html_search_regex( r'([^<]+)\s*-\s*PornoXO', webpage, 'title') - description = self._html_search_regex( - r'<meta name="description" content="([^"]+)\s*featuring', - webpage, 'description', fatal=False) - - thumbnail = self._html_search_regex( - r'\'image\'\s*:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False) - view_count = str_to_int(self._html_search_regex( r'[vV]iews:\s*([0-9,]+)', webpage, 'view count', fatal=False)) @@ -53,13 +45,14 @@ def _real_extract(self, url): None if categories_str is None else categories_str.split(',')) - return { + video_data.update({ 'id': video_id, - 'url': video_url, 'title': title, - 'description': description, - 'thumbnail': thumbnail, + 'display_id': display_id, + 'description': self._html_search_meta('description', webpage), 'categories': categories, 'view_count': view_count, 'age_limit': 18, - } + }) + + return video_data