From ed8648a322f8ec55957db0d4a959868807c38ebb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 19 Feb 2016 21:42:46 +0600 Subject: [PATCH] [pornhub] Fix thumbnail and duration extraction (Closes #8604) --- youtube_dl/extractor/pornhub.py | 31 ++++++++++++++++++++++++------- 1 file changed, 24 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 55af13324..5a55c25e7 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -11,6 +11,7 @@ ) from ..utils import ( ExtractorError, + int_or_none, sanitized_Request, str_to_int, ) @@ -23,13 +24,18 @@ 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, } }, { 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d', @@ -67,13 +73,23 @@ def _real_extract(self, url): 'PornHub said: %s' % error_msg, expected=True, video_id=video_id) - video_title = self._html_search_regex(r'

]+>([^<]+)', webpage, 'title') + flashvars = self._parse_json( + self._search_regex( + r'var\s+flashv1ars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'), + video_id) + if flashvars: + video_title = flashvars.get('video_title') + thumbnail = flashvars.get('image_url') + duration = int_or_none(flashvars.get('video_duration')) + else: + video_title, thumbnail, duration = [None] * 3 + + if not video_title: + video_title = self._html_search_regex(r'

]+>([^<]+)', webpage, 'title') + 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'([\d,\.]+) views', webpage, 'view') @@ -120,6 +136,7 @@ def _real_extract(self, url): 'uploader': video_uploader, 'title': video_title, 'thumbnail': thumbnail, + 'duration': duration, 'view_count': view_count, 'like_count': like_count, 'dislike_count': dislike_count,