From fdb4d278bf6c2481778e01ab0ff25c2050664f1c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 29 Sep 2014 20:11:51 +0700 Subject: [PATCH] [spankwire] Fix extraction and modernize --- youtube_dl/extractor/spankwire.py | 48 +++++++++++++++++++------------ 1 file changed, 29 insertions(+), 19 deletions(-) diff --git a/youtube_dl/extractor/spankwire.py b/youtube_dl/extractor/spankwire.py index 2007a0013..21491027a 100644 --- a/youtube_dl/extractor/spankwire.py +++ b/youtube_dl/extractor/spankwire.py @@ -9,7 +9,6 @@ from ..utils import ( compat_urllib_parse, unified_strdate, str_to_int, - int_or_none, ) from ..aes import aes_decrypt_text @@ -40,31 +39,42 @@ class SpankwireIE(InfoExtractor): req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) - title = self._html_search_regex(r'

([^<]+)', webpage, 'title') + title = self._html_search_regex( + r'

([^<]+)', webpage, 'title') description = self._html_search_regex( - r'([^<]+)<', webpage, 'description', fatal=False) + r'([^<]+)<', + webpage, 'description', fatal=False) thumbnail = self._html_search_regex( - r'flashvars\.image_url = "([^"]+)', webpage, 'thumbnail', fatal=False) + r'playerData\.screenShot\s*=\s*"([^"]+)"', + webpage, 'thumbnail', fatal=False) uploader = self._html_search_regex( - r'by:\s*]*>(.+?)', webpage, 'uploader', fatal=False) + r'by:\s*]*>(.+?)', + webpage, 'uploader', fatal=False) uploader_id = self._html_search_regex( - r'by:\s* on (.+?) at \d+:\d+', webpage, 'upload date', fatal=False) - if upload_date: - upload_date = unified_strdate(upload_date) - - view_count = self._html_search_regex( - r'
([^<]+) views
', webpage, 'view count', fatal=False) - if view_count: - view_count = str_to_int(view_count) - comment_count = int_or_none(self._html_search_regex( - r'\s*(\d+) Comments', webpage, 'comment count', fatal=False)) + r'by:\s*
on (.+?) at \d+:\d+', + webpage, 'upload date', fatal=False)) - video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'flashvars\.quality_[0-9]{3}p = "([^"]+)', webpage))) + view_count = str_to_int(self._html_search_regex( + r'
([\d,\.]+) views
', + webpage, 'view count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'Comments]+>\s*\(([\d,\.]+)\)', + webpage, 'comment count', fatal=False)) + + video_urls = list(map( + compat_urllib_parse.unquote, + re.findall(r'playerData\.cdnPath[0-9]{3,}\s*=\s*"([^"]+)', webpage))) if webpage.find('flashvars\.encrypted = "true"') != -1: - password = self._html_search_regex(r'flashvars\.video_title = "([^"]+)', webpage, 'password').replace('+', ' ') - video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls)) + password = self._html_search_regex( + r'flashvars\.video_title = "([^"]+)', + webpage, 'password').replace('+', ' ') + video_urls = list(map( + lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), + video_urls)) formats = [] for video_url in video_urls: