[condenast] fix extraction and add support for other sites

pull/6963/head
remitamine 2015-09-23 17:48:39 +01:00 committed by Sergey M․
parent 9b166fc1f8
commit 882fc9052e
1 changed files with 20 additions and 9 deletions

View File

@ -2,7 +2,6 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import json
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
@ -24,13 +23,25 @@ class CondeNastIE(InfoExtractor):
# The keys are the supported sites and the values are the name to be shown # The keys are the supported sites and the values are the name to be shown
# to the user and in the extractor description. # to the user and in the extractor description.
_SITES = { _SITES = {
'wired': 'WIRED', 'allure': 'Allure',
'gq': 'GQ', 'architecturaldigest': 'Architectural Digest',
'vogue': 'Vogue', 'arstechnica': 'Ars Technica',
'glamour': 'Glamour', 'bonappetit': 'Bon Appetit',
'wmagazine': 'W Magazine', 'brides': 'Brides',
'vanityfair': 'Vanity Fair',
'cnevids': 'Condé Nast', 'cnevids': 'Condé Nast',
'cntraveler': 'Condé Nast Traveler',
'details': 'Details',
'epicurious': 'Epicurious',
'glamour': 'Glamour',
'golfdigest': 'Golf Digest',
'gq': 'GQ',
'newyorker': 'The New Yorker',
'self': 'SELF',
'teenvogue': 'Teen Vogue',
'vanityfair': 'Vanity Fair',
'vogue': 'Vogue',
'wired': 'WIRED',
'wmagazine': 'W Magazine',
} }
_VALID_URL = r'http://(video|www|player)\.(?P<site>%s)\.com/(?P<type>watch|series|video|embed)/(?P<id>[^/?#]+)' % '|'.join(_SITES.keys()) _VALID_URL = r'http://(video|www|player)\.(?P<site>%s)\.com/(?P<type>watch|series|video|embed)/(?P<id>[^/?#]+)' % '|'.join(_SITES.keys())
@ -86,8 +97,8 @@ class CondeNastIE(InfoExtractor):
info_url = base_info_url + data info_url = base_info_url + data
info_page = self._download_webpage(info_url, video_id, info_page = self._download_webpage(info_url, video_id,
'Downloading video info') 'Downloading video info')
video_info = self._search_regex(r'var video = ({.+?});', info_page, 'video info') video_info = self._search_regex(r'var\s*video\s*=\s*({.+?});', info_page, 'video info')
video_info = json.loads(video_info) video_info = self._parse_json(video_info, video_id)
formats = [{ formats = [{
'format_id': '%s-%s' % (fdata['type'].split('/')[-1], fdata['quality']), 'format_id': '%s-%s' % (fdata['type'].split('/')[-1], fdata['quality']),