From 65314dccf8a61210b2261a648bc5beb9723e1a69 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 13 May 2014 10:14:05 +0200 Subject: [PATCH] [empflix] Simplify (#2903) --- youtube_dl/extractor/empflix.py | 50 +++++++++++++++++---------------- 1 file changed, 26 insertions(+), 24 deletions(-) diff --git a/youtube_dl/extractor/empflix.py b/youtube_dl/extractor/empflix.py index e7abbb5d6..eaeee5a51 100644 --- a/youtube_dl/extractor/empflix.py +++ b/youtube_dl/extractor/empflix.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -5,42 +7,42 @@ ExtractorError, ) + class EmpflixIE(InfoExtractor): - _VALID_URL = r'^https?://www\.empflix\.com/videos/(?P[^\.]+)\.html' + _VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P[0-9]+)\.html' _TEST = { - u'url': u'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html', - u'file': u'Amateur-Finger-Fuck-33051.flv', - u'md5': u'5e5cc160f38ca9857f318eb97146e13e', - u'info_dict': { - u"title": u"Amateur Finger Fuck", - u"age_limit": 18, + 'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html', + 'md5': '5e5cc160f38ca9857f318eb97146e13e', + 'info_dict': { + 'id': '33051', + 'ext': 'flv', + 'title': 'Amateur Finger Fuck', + 'age_limit': 18, } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') - video_id = mobj.group('videoid') - - # Get webpage content webpage = self._download_webpage(url, video_id) - age_limit = self._rta_search(webpage) - # Get the video title - video_title = self._html_search_regex(r'name="title" value="(?P[^"]*)"', - webpage, u'title').strip() + video_title = self._html_search_regex( + r'name="title" value="(?P<title>[^"]*)"', webpage, 'title') - cfg_url = self._html_search_regex(r'flashvars\.config = escape\("([^"]+)"', - webpage, u'flashvars.config').strip() + cfg_url = self._html_search_regex( + r'flashvars\.config = escape\("([^"]+)"', + webpage, 'flashvars.config') - cfg_xml = self._download_xml(cfg_url, video_id, note=u'Downloading metadata') + cfg_xml = self._download_xml( + cfg_url, video_id, note='Downloading metadata') video_url = cfg_xml.find('videoLink').text - info = {'id': video_id, - 'url': video_url, - 'title': video_title, - 'ext': 'flv', - 'age_limit': age_limit} - - return [info] + return { + 'id': video_id, + 'url': video_url, + 'ext': 'flv', + 'title': video_title, + 'age_limit': age_limit, + }