w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[condenast] Use unicode_literals

Browse source
This commit is contained in:
Philipp Hagemeister 2014-01-17 03:32:02 +01:00
parent fbcd7b5f83
commit 6e249060cf
1 changed files with 25 additions and 23 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

48
youtube_dl/extractor/condenast.py
View file

@ -1,4 +1,5 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals
import re import re
import json import json
@ -20,30 +21,31 @@ 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 = {'wired': u'WIRED', _SITES = {
'gq': u'GQ', 'wired': 'WIRED',
'vogue': u'Vogue', 'gq': 'GQ',
'glamour': u'Glamour', 'vogue': 'Vogue',
'wmagazine': u'W Magazine', 'glamour': 'Glamour',
'vanityfair': u'Vanity Fair', 'wmagazine': 'W Magazine',
} 'vanityfair': 'Vanity Fair',
}
_VALID_URL = r'http://(video|www).(?P<site>%s).com/(?P<type>watch|series|video)/(?P<id>.+)' % '|'.join(_SITES.keys()) _VALID_URL = r'http://(video|www).(?P<site>%s).com/(?P<type>watch|series|video)/(?P<id>.+)' % '|'.join(_SITES.keys())
IE_DESC = u'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values())) IE_DESC = 'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values()))
_TEST = { _TEST = {
u'url': u'http://video.wired.com/watch/3d-printed-speakers-lit-with-led', 'url': 'http://video.wired.com/watch/3d-printed-speakers-lit-with-led',
u'file': u'5171b343c2b4c00dd0c1ccb3.mp4', 'file': '5171b343c2b4c00dd0c1ccb3.mp4',
u'md5': u'1921f713ed48aabd715691f774c451f7', 'md5': '1921f713ed48aabd715691f774c451f7',
u'info_dict': { 'info_dict': {
u'title': u'3D Printed Speakers Lit With LED', 'title': '3D Printed Speakers Lit With LED',
u'description': u'Check out these beautiful 3D printed LED speakers. You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.', 'description': 'Check out these beautiful 3D printed LED speakers. You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.',
} }
} }
def _extract_series(self, url, webpage): def _extract_series(self, url, webpage):
title = self._html_search_regex(r'<div class="cne-series-info">.*?<h1>(.+?)</h1>', title = self._html_search_regex(r'<div class="cne-series-info">.*?<h1>(.+?)</h1>',
webpage, u'series title', flags=re.DOTALL) webpage, 'series title', flags=re.DOTALL)
url_object = compat_urllib_parse_urlparse(url) url_object = compat_urllib_parse_urlparse(url)
base_url = '%s://%s' % (url_object.scheme, url_object.netloc) base_url = '%s://%s' % (url_object.scheme, url_object.netloc)
m_paths = re.finditer(r'<p class="cne-thumb-title">.*?<a href="(/watch/.+?)["\?]', m_paths = re.finditer(r'<p class="cne-thumb-title">.*?<a href="(/watch/.+?)["\?]',
@ -57,24 +59,24 @@ class CondeNastIE(InfoExtractor):
description = self._html_search_regex([r'<div class="cne-video-description">(.+?)</div>', description = self._html_search_regex([r'<div class="cne-video-description">(.+?)</div>',
r'<div class="video-post-content">(.+?)</div>', r'<div class="video-post-content">(.+?)</div>',
], ],
webpage, u'description', webpage, 'description',
fatal=False, flags=re.DOTALL) fatal=False, flags=re.DOTALL)
params = self._search_regex(r'var params = {(.+?)}[;,]', webpage, params = self._search_regex(r'var params = {(.+?)}[;,]', webpage,
u'player params', flags=re.DOTALL) 'player params', flags=re.DOTALL)
video_id = self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, u'video id') video_id = self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id')
player_id = self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, u'player id') player_id = self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, 'player id')
target = self._search_regex(r'target: [\'"](.+?)[\'"]', params, u'target') target = self._search_regex(r'target: [\'"](.+?)[\'"]', params, 'target')
data = compat_urllib_parse.urlencode({'videoId': video_id, data = compat_urllib_parse.urlencode({'videoId': video_id,
'playerId': player_id, 'playerId': player_id,
'target': target, 'target': target,
}) })
base_info_url = self._search_regex(r'url = [\'"](.+?)[\'"][,;]', base_info_url = self._search_regex(r'url = [\'"](.+?)[\'"][,;]',
webpage, u'base info url', webpage, 'base info url',
default='http://player.cnevids.com/player/loader.js?') default='http://player.cnevids.com/player/loader.js?')
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,
u'Downloading video info') 'Downloading video info')
video_info = self._search_regex(r'var video = ({.+?});', info_page, u'video info') video_info = self._search_regex(r'var video = ({.+?});', info_page, 'video info')
video_info = json.loads(video_info) video_info = json.loads(video_info)
def _formats_sort_key(f): def _formats_sort_key(f):