CriterionIE: simplify some parts and use _html_search_regex

This commit is contained in:
Jaime Marquínez Ferrándiz 2013-07-13 12:26:05 +02:00
parent 7fd930c0c8
commit b0e72bcf34

View file

@ -3,38 +3,38 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import determine_ext
class CriterionIE(InfoExtractor): class CriterionIE(InfoExtractor):
_VALID_URL = r'http://www.criterion.com/films/(.*)' _VALID_URL = r'https?://www\.criterion\.com/films/(\d*)-.+'
_TEST = { _TEST = {
u'url': u'http://www.criterion.com/films/184-le-samourai', u'url': u'http://www.criterion.com/films/184-le-samourai',
u'file': u'184.mp4', u'file': u'184.mp4',
u'md5': u'bc51beba55685509883a9a7830919ec3', u'md5': u'bc51beba55685509883a9a7830919ec3',
u'info_dict': { u'info_dict': {
u"title": u"Le Samouraï", u"title": u"Le Samouraï",
u"description" : u"In a career-defining performance, Alain Delon plays a contract killer with samurai instincts. A razor-sharp cocktail of 1940s American gangster cinema and 1960s French pop culture, maverick director Jean-Pierre Melville's masterpiece _Le Samouraï_ defines cool. " u"description" : u'md5:a2b4b116326558149bef81f76dcbb93f',
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1).split('-')[0] video_id = mobj.group(1)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
final_url = self._search_regex(r'so.addVariable\("videoURL", "(.+?)"\)\;', final_url = self._search_regex(r'so.addVariable\("videoURL", "(.+?)"\)\;',
webpage, 'video url') webpage, 'video url')
title = self._search_regex(r'<meta content="(.+?)" property="og:title" />', title = self._html_search_regex(r'<meta content="(.+?)" property="og:title" />',
webpage, 'video title') webpage, 'video title')
description = self._search_regex(r'<meta name="description" content="(.+?)" />', description = self._html_search_regex(r'<meta name="description" content="(.+?)" />',
webpage, 'video description') webpage, 'video description')
thumbnail = self._search_regex(r'so.addVariable\("thumbnailURL", "(.+?)"\)\;', thumbnail = self._search_regex(r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
webpage, 'thumbnail url') webpage, 'thumbnail url')
ext = final_url.split('.')[-1]
return {'id': video_id, return {'id': video_id,
'url' : final_url, 'url' : final_url,
'title': title, 'title': title,
'ext': ext, 'ext': determine_ext(final_url),
'description': description, 'description': description,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
} }