youtube-dl/youtube_dl/extractor/dreisat.py

82 lines
3.0 KiB
Python
Raw Normal View History

2014-06-08 17:45:12 +02:00
from __future__ import unicode_literals
2013-07-08 01:13:55 +02:00
import re
from .common import InfoExtractor
2015-04-04 19:28:47 +02:00
from ..utils import (
ExtractorError,
unified_strdate,
)
2013-07-08 01:13:55 +02:00
class DreiSatIE(InfoExtractor):
IE_NAME = '3sat'
_VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
2013-07-08 01:13:55 +02:00
_TEST = {
2015-04-04 19:30:38 +02:00
'url': 'http://www.3sat.de/mediathek/index.php?mode=play&obj=45918',
'md5': 'be37228896d30a88f315b638900a026e',
2014-06-08 17:45:12 +02:00
'info_dict': {
2015-04-04 19:30:38 +02:00
'id': '45918',
2014-06-08 17:45:12 +02:00
'ext': 'mp4',
2015-04-04 19:30:38 +02:00
'title': 'Waidmannsheil',
'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
2014-06-08 17:45:12 +02:00
'uploader': '3sat',
2015-04-04 19:30:38 +02:00
'upload_date': '20140913'
2013-07-08 01:13:55 +02:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
2014-06-08 17:45:12 +02:00
details_doc = self._download_xml(details_url, video_id, 'Downloading video details')
2013-07-08 01:13:55 +02:00
2015-04-04 19:28:47 +02:00
status_code = details_doc.find('./status/statuscode')
if status_code is not None and status_code.text != 'ok':
code = status_code.text
if code == 'notVisibleAnymore':
message = 'Video %s is not available' % video_id
else:
message = '%s returned error: %s' % (self.IE_NAME, code)
raise ExtractorError(message, expected=True)
2013-07-08 01:13:55 +02:00
thumbnail_els = details_doc.findall('.//teaserimage')
thumbnails = [{
'width': int(te.attrib['key'].partition('x')[0]),
'height': int(te.attrib['key'].partition('x')[2]),
2013-07-08 01:13:55 +02:00
'url': te.text,
} for te in thumbnail_els]
information_el = details_doc.find('.//information')
video_title = information_el.find('./title').text
video_description = information_el.find('./detail').text
details_el = details_doc.find('.//details')
video_uploader = details_el.find('./channel').text
upload_date = unified_strdate(details_el.find('./airtime').text)
format_els = details_doc.findall('.//formitaet')
formats = [{
'format_id': fe.attrib['basetype'],
'width': int(fe.find('./width').text),
'height': int(fe.find('./height').text),
'url': fe.find('./url').text,
'filesize': int(fe.find('./filesize').text),
'video_bitrate': int(fe.find('./videoBitrate').text),
} for fe in format_els
if not fe.find('./url').text.startswith('http://www.metafilegenerator.de/')]
self._sort_formats(formats)
2013-07-08 01:13:55 +02:00
return {
'_type': 'video',
2013-07-08 01:13:55 +02:00
'id': video_id,
'title': video_title,
'formats': formats,
'description': video_description,
'thumbnails': thumbnails,
'thumbnail': thumbnails[-1]['url'],
'uploader': video_uploader,
'upload_date': upload_date,
}