|
@ -1,40 +1,35 @@ |
|
|
import json |
|
|
|
|
|
import re |
|
|
|
|
|
|
|
|
from __future__ import unicode_literals |
|
|
|
|
|
|
|
|
from .common import InfoExtractor |
|
|
from .common import InfoExtractor |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TvpIE(InfoExtractor): |
|
|
class TvpIE(InfoExtractor): |
|
|
IE_NAME = u'tvp.pl' |
|
|
|
|
|
|
|
|
IE_NAME = 'tvp.pl' |
|
|
_VALID_URL = r'https?://www\.tvp\.pl/.*?wideo/(?P<date>\d+)/(?P<id>\d+)' |
|
|
_VALID_URL = r'https?://www\.tvp\.pl/.*?wideo/(?P<date>\d+)/(?P<id>\d+)' |
|
|
|
|
|
|
|
|
_TEST = { |
|
|
_TEST = { |
|
|
u'url': u'http://www.tvp.pl/warszawa/magazyny/campusnews/wideo/31102013/12878238', |
|
|
|
|
|
u'md5': u'148408967a6a468953c0a75cbdaf0d7a', |
|
|
|
|
|
u'file': u'12878238.wmv', |
|
|
|
|
|
u'info_dict': { |
|
|
|
|
|
u'title': u'31.10.2013 - Odcinek 2', |
|
|
|
|
|
u'description': u'31.10.2013 - Odcinek 2', |
|
|
|
|
|
|
|
|
'url': 'http://www.tvp.pl/warszawa/magazyny/campusnews/wideo/31102013/12878238', |
|
|
|
|
|
'md5': '148408967a6a468953c0a75cbdaf0d7a', |
|
|
|
|
|
'info_dict': { |
|
|
|
|
|
'id': '12878238', |
|
|
|
|
|
'ext': 'wmv', |
|
|
|
|
|
'title': '31.10.2013 - Odcinek 2', |
|
|
|
|
|
'description': '31.10.2013 - Odcinek 2', |
|
|
}, |
|
|
}, |
|
|
u'skip': u'Download has to use same server IP as extraction. Therefore, a good (load-balancing) DNS resolver will make the download fail.' |
|
|
|
|
|
|
|
|
'skip': 'Download has to use same server IP as extraction. Therefore, a good (load-balancing) DNS resolver will make the download fail.' |
|
|
} |
|
|
} |
|
|
|
|
|
|
|
|
def _real_extract(self, url): |
|
|
def _real_extract(self, url): |
|
|
mobj = re.match(self._VALID_URL, url) |
|
|
|
|
|
video_id = mobj.group('id') |
|
|
|
|
|
|
|
|
video_id = self._match_id(url) |
|
|
webpage = self._download_webpage(url, video_id) |
|
|
webpage = self._download_webpage(url, video_id) |
|
|
json_url = 'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s' % video_id |
|
|
json_url = 'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s' % video_id |
|
|
json_params = self._download_webpage( |
|
|
|
|
|
json_url, video_id, u"Downloading video metadata") |
|
|
|
|
|
|
|
|
|
|
|
params = json.loads(json_params) |
|
|
|
|
|
self.report_extraction(video_id) |
|
|
|
|
|
|
|
|
params = self._download_json( |
|
|
|
|
|
json_url, video_id, "Downloading video metadata") |
|
|
video_url = params['video_url'] |
|
|
video_url = params['video_url'] |
|
|
|
|
|
|
|
|
title = self._og_search_title(webpage, fatal=True) |
|
|
|
|
|
return { |
|
|
return { |
|
|
'id': video_id, |
|
|
'id': video_id, |
|
|
'title': title, |
|
|
|
|
|
|
|
|
'title': self._og_search_title(webpage), |
|
|
'ext': 'wmv', |
|
|
'ext': 'wmv', |
|
|
'url': video_url, |
|
|
'url': video_url, |
|
|
'description': self._og_search_description(webpage), |
|
|
'description': self._og_search_description(webpage), |
|
|