yt-dlp/youtube_dl/extractor/ndr.py

91 lines
3.0 KiB
Python
Raw Normal View History

# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import ExtractorError
class NDRIE(InfoExtractor):
IE_NAME = 'ndr'
IE_DESC = 'NDR.de - Mediathek'
_VALID_URL = r'https?://www\.ndr\.de/.+?(?P<id>\d+)\.html'
_TESTS = [
{
2014-02-11 14:21:05 +00:00
'url': 'http://www.ndr.de/fernsehen/sendungen/markt/markt7959.html',
'md5': 'e7a6079ca39d3568f4996cb858dd6708',
'note': 'Video file',
'info_dict': {
2014-02-11 14:21:05 +00:00
'id': '7959',
'ext': 'mp4',
2014-02-11 14:21:05 +00:00
'title': 'Markt - die ganze Sendung',
'description': 'md5:af9179cf07f67c5c12dc6d9997e05725',
'duration': 2655,
},
},
{
2014-02-14 16:12:15 +00:00
'url': 'http://www.ndr.de/info/audio51535.html',
'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
2014-02-11 14:21:05 +00:00
'note': 'Audio file',
'info_dict': {
2014-02-14 16:12:15 +00:00
'id': '51535',
'ext': 'mp3',
2014-02-14 16:12:15 +00:00
'title': 'La Valette entgeht der Hinrichtung',
'description': 'md5:22f9541913a40fe50091d5cdd7c9f536',
'duration': 884,
}
}
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
page = self._download_webpage(url, video_id, 'Downloading page')
title = self._og_search_title(page)
description = self._og_search_description(page)
mobj = re.search(
r'<div class="duration"><span class="min">(?P<minutes>\d+)</span>:<span class="sec">(?P<seconds>\d+)</span></div>',
page)
duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
formats = []
mp3_url = re.search(r'''{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
if mp3_url:
formats.append({
'url': mp3_url.group('audio'),
'format_id': 'mp3',
})
thumbnail = None
video_url = re.search(r'''3: {src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
if video_url:
2014-05-17 10:58:37 +00:00
thumbnails = re.findall(r'''\d+: {src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page)
if thumbnails:
QUALITIES = ['xs', 's', 'm', 'l', 'xl']
thumbnails.sort(key=lambda thumb: QUALITIES.index(thumb[1]))
thumbnail = 'http://www.ndr.de' + thumbnails[-1][0]
for format_id in ['lo', 'hi', 'hq']:
formats.append({
'url': '%s.%s.mp4' % (video_url.group('video'), format_id),
'format_id': format_id,
})
if not formats:
raise ExtractorError('No media links available for %s' % video_id)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
}