yt-dlp/youtube_dl/extractor/ard.py

91 lines
3.2 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
)
class ARDIE(InfoExtractor):
_VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?'
2013-06-27 18:46:46 +00:00
_TEST = {
'url': 'http://www.ardmediathek.de/das-erste/guenther-jauch/edward-snowden-im-interview-held-oder-verraeter?documentId=19288786',
'file': '19288786.mp4',
'md5': '515bf47ce209fb3f5a61b7aad364634c',
'info_dict': {
'title': 'Edward Snowden im Interview - Held oder Verräter?',
'description': 'Edward Snowden hat alles aufs Spiel gesetzt, um die weltweite \xdcberwachung durch die Geheimdienste zu enttarnen. Nun stellt sich der ehemalige NSA-Mitarbeiter erstmals weltweit in einem TV-Interview den Fragen eines NDR-Journalisten. Die Sendung vom Sonntagabend.',
'thumbnail': 'http://www.ardmediathek.de/ard/servlet/contentblob/19/28/87/90/19288790/bild/2250037',
2013-06-27 18:46:46 +00:00
},
'skip': 'Blocked outside of Germany',
2013-06-27 18:46:46 +00:00
}
def _real_extract(self, url):
# determine video id from url
m = re.match(self._VALID_URL, url)
numid = re.search(r'documentId=([0-9]+)', url)
if numid:
video_id = numid.group(1)
else:
video_id = m.group('video_id')
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
2014-05-30 02:59:18 +00:00
[r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
r'<meta name="dcterms.title" content="(.*?)"/>',
2014-05-30 02:59:18 +00:00
r'<h4 class="headline">(.*?)</h4>'],
webpage, 'title')
description = self._html_search_meta(
'dcterms.abstract', webpage, 'description')
thumbnail = self._og_search_thumbnail(webpage)
media_info = self._download_json(
'http://www.ardmediathek.de/play/media/%s' % video_id, video_id)
# The second element of the _mediaArray contains the standard http urls
streams = media_info['_mediaArray'][1]['_mediaStreamArray']
if not streams:
if '"fsk"' in webpage:
raise ExtractorError('This video is only available after 20:00')
formats = []
for s in streams:
if type(s['_stream']) == list:
reverse = s['_stream'][::-1]
for i in reverse:
quality = s['_quality'] + reverse.index(i)
formats.append({
'quality': quality,
'url': i,
'format_id': '%s-%s' % (determine_ext(i), quality)
})
continue
format = {
'quality': s['_quality'],
'url': s['_stream'],
}
format['format_id'] = '%s-%s' % (
determine_ext(format['url']), format['quality'])
formats.append(format)
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'formats': formats,
'thumbnail': thumbnail,
}