|
|
@ -4,7 +4,11 @@ from __future__ import unicode_literals |
|
|
|
import re |
|
|
|
|
|
|
|
from .common import InfoExtractor |
|
|
|
from ..utils import ExtractorError |
|
|
|
from ..utils import ( |
|
|
|
ExtractorError, |
|
|
|
int_or_none, |
|
|
|
unified_strdate, |
|
|
|
) |
|
|
|
|
|
|
|
|
|
|
|
class NRKIE(InfoExtractor): |
|
|
@ -64,4 +68,78 @@ class NRKIE(InfoExtractor): |
|
|
|
'title': data['title'], |
|
|
|
'description': data['description'], |
|
|
|
'thumbnail': thumbnail, |
|
|
|
} |
|
|
|
|
|
|
|
|
|
|
|
class NRKTVIE(InfoExtractor): |
|
|
|
_VALID_URL = r'http://tv\.nrk\.no/(?:serie/[^/]+|program)/(?P<id>[a-z]{4}\d{8})' |
|
|
|
|
|
|
|
_TESTS = [ |
|
|
|
{ |
|
|
|
'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/muhh48000314/23-05-2014', |
|
|
|
'md5': '7b96112fbae1faf09a6f9ae1aff6cb84', |
|
|
|
'info_dict': { |
|
|
|
'id': 'muhh48000314', |
|
|
|
'ext': 'flv', |
|
|
|
'title': '20 spørsmål', |
|
|
|
'description': 'md5:bdea103bc35494c143c6a9acdd84887a', |
|
|
|
'upload_date': '20140523', |
|
|
|
'duration': 1741.52, |
|
|
|
} |
|
|
|
}, |
|
|
|
{ |
|
|
|
'url': 'http://tv.nrk.no/program/mdfp15000514', |
|
|
|
'md5': '383650ece2b25ecec996ad7b5bb2a384', |
|
|
|
'info_dict': { |
|
|
|
'id': 'mdfp15000514', |
|
|
|
'ext': 'flv', |
|
|
|
'title': 'Kunnskapskanalen: Grunnlovsjubiléet - Stor ståhei for ingenting', |
|
|
|
'description': 'md5:654c12511f035aed1e42bdf5db3b206a', |
|
|
|
'upload_date': '20140524', |
|
|
|
'duration': 4605.0, |
|
|
|
} |
|
|
|
}, |
|
|
|
] |
|
|
|
|
|
|
|
def _real_extract(self, url): |
|
|
|
mobj = re.match(self._VALID_URL, url) |
|
|
|
video_id = mobj.group('id') |
|
|
|
|
|
|
|
page = self._download_webpage(url, video_id) |
|
|
|
|
|
|
|
title = self._html_search_meta('title', page, 'title') |
|
|
|
description = self._html_search_meta('description', page, 'description') |
|
|
|
thumbnail = self._html_search_regex(r'data-posterimage="([^"]+)"', page, 'thumbnail', fatal=False) |
|
|
|
upload_date = unified_strdate(self._html_search_meta('rightsfrom', page, 'upload date', fatal=False)) |
|
|
|
duration = self._html_search_regex(r'data-duration="([^"]+)"', page, 'duration', fatal=False) |
|
|
|
if duration: |
|
|
|
duration = float(duration) |
|
|
|
|
|
|
|
formats = [] |
|
|
|
|
|
|
|
f4m_url = re.search(r'data-media="([^"]+)"', page) |
|
|
|
if f4m_url: |
|
|
|
formats.append({ |
|
|
|
'url': f4m_url.group(1) + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', |
|
|
|
'format_id': 'f4m', |
|
|
|
'ext': 'flv', |
|
|
|
}) |
|
|
|
|
|
|
|
m3u8_url = re.search(r'data-hls-media="([^"]+)"', page) |
|
|
|
if m3u8_url: |
|
|
|
formats.append({ |
|
|
|
'url': m3u8_url.group(1), |
|
|
|
'format_id': 'm3u8', |
|
|
|
}) |
|
|
|
|
|
|
|
self._sort_formats(formats) |
|
|
|
|
|
|
|
return { |
|
|
|
'id': video_id, |
|
|
|
'title': title, |
|
|
|
'description': description, |
|
|
|
'thumbnail': thumbnail, |
|
|
|
'upload_date': upload_date, |
|
|
|
'duration': duration, |
|
|
|
'formats': formats, |
|
|
|
} |