From 85689a531f1ba418570ce2bcde6fe16a482a5685 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Fri, 3 Jan 2014 13:09:39 +0100 Subject: [PATCH] [macgamestore] Minor fixes (#2044) --- youtube_dl/extractor/macgamestore.py | 41 +++++++++++++++------------- 1 file changed, 22 insertions(+), 19 deletions(-) diff --git a/youtube_dl/extractor/macgamestore.py b/youtube_dl/extractor/macgamestore.py index 4541f6d66..b818cf50c 100644 --- a/youtube_dl/extractor/macgamestore.py +++ b/youtube_dl/extractor/macgamestore.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -5,36 +7,37 @@ from ..utils import ExtractorError class MacGameStoreIE(InfoExtractor): - IE_NAME = u'macgamestore' - IE_DESC = u'MacGameStore trailers' + IE_NAME = 'macgamestore' + IE_DESC = 'MacGameStore trailers' _VALID_URL = r'https?://www\.macgamestore\.com/mediaviewer\.php\?trailer=(?P\d+)' _TEST = { - u'url': u'http://www.macgamestore.com/mediaviewer.php?trailer=2450', - u'file': u'2450.m4v', - u'md5': u'8649b8ea684b6666b4c5be736ecddc61', - u'info_dict': { - u'title': u'Crow', + 'url': 'http://www.macgamestore.com/mediaviewer.php?trailer=2450', + 'file': '2450.m4v', + 'md5': '8649b8ea684b6666b4c5be736ecddc61', + 'info_dict': { + 'title': 'Crow', } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - - webpage = self._download_webpage(url, video_id, u'Downloading trailer page') - + + webpage = self._download_webpage(url, video_id, 'Downloading trailer page') + if re.search(r'>Missing Media<', webpage) is not None: - raise ExtractorError(u'Trailer %s does not exist' % video_id, expected=True) - - mobj = re.search(r'MacGameStore: (?P<title>.*?) Trailer', webpage) - video_title = mobj.group('title') - - mobj = re.search(r'(?s)[^"]+)"\s*>', webpage) - video_url = mobj.group('video') - + raise ExtractorError('Trailer %s does not exist' % video_id, expected=True) + + video_title = self._html_search_regex( + r'MacGameStore: (.*?) Trailer', webpage, 'title') + + video_url = self._html_search_regex( + r'(?s)', + webpage, 'video URL') + return { 'id': video_id, 'url': video_url, 'title': video_title - } \ No newline at end of file + }