1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-09 19:54:32 +01:00
youtube-dl/youtube_dl/extractor/srf.py

105 lines
4.2 KiB
Python
Raw Normal View History

2015-04-16 16:00:45 +02:00
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
parse_iso8601,
xpath_text,
)
class SrfIE(InfoExtractor):
2015-04-16 17:47:42 +02:00
_VALID_URL = r'https?://(?:www\.srf\.ch/play(?:er)?/tv/[^/]+/video/(?P<display_id>[^?]+)\?id=|tp\.srgssr\.ch/p/flash\?urn=urn:srf:ais:video:)(?P<id>[0-9a-f\-]{36})'
2015-04-16 16:00:45 +02:00
_TESTS = [{
'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
'md5': '4cd93523723beff51bb4bee974ee238d',
'info_dict': {
'id': '28e1a57d-5b76-4399-8ab3-9097f071e6c5',
'display_id': 'snowden-beantragt-asyl-in-russland',
'ext': 'm4v',
'upload_date': '20130701',
'title': 'Snowden beantragt Asyl in Russland',
'timestamp': 1372713995,
}
}, {
# No Speichern (Save) button
'url': 'http://www.srf.ch/play/tv/top-gear/video/jaguar-xk120-shadow-und-tornado-dampflokomotive?id=677f5829-e473-4823-ac83-a1087fe97faa',
2015-04-16 17:30:13 +02:00
'md5': 'd97e236e80d1d24729e5d0953d276a4f',
2015-04-16 16:00:45 +02:00
'info_dict': {
'id': '677f5829-e473-4823-ac83-a1087fe97faa',
'display_id': 'jaguar-xk120-shadow-und-tornado-dampflokomotive',
2015-04-16 17:30:13 +02:00
'ext': 'flv',
2015-04-16 16:00:45 +02:00
'upload_date': '20130710',
'title': 'Jaguar XK120, Shadow und Tornado-Dampflokomotive',
'timestamp': 1373493600,
},
}, {
'url': 'http://www.srf.ch/player/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
'only_matching': True,
2015-04-16 17:47:42 +02:00
}, {
'url': 'https://tp.srgssr.ch/p/flash?urn=urn:srf:ais:video:28e1a57d-5b76-4399-8ab3-9097f071e6c5',
'only_matching': True,
2015-04-16 16:00:45 +02:00
}]
def _real_extract(self, url):
video_id = self._match_id(url)
2015-04-16 17:48:22 +02:00
display_id = re.match(self._VALID_URL, url).group('display_id') or video_id
2015-04-16 16:00:45 +02:00
video_data = self._download_xml(
'http://il.srgssr.ch/integrationlayer/1.0/ue/srf/video/play/%s.xml' % video_id,
2015-04-16 17:48:22 +02:00
display_id)
2015-04-16 16:00:45 +02:00
title = xpath_text(
video_data, './AssetMetadatas/AssetMetadata/title', fatal=True)
thumbnails = [{
'url': s.text
} for s in video_data.findall('.//ImageRepresentation/url')]
timestamp = parse_iso8601(xpath_text(video_data, './createdDate'))
# The <duration> field in XML is different from the exact duration, skipping
formats = []
for item in video_data.findall('./Playlists/Playlist') + video_data.findall('./Downloads/Download'):
for url_node in item.findall('url'):
quality = url_node.attrib['quality']
full_url = url_node.text
original_ext = determine_ext(full_url)
format_id = '%s-%s' % (quality, item.attrib['protocol'])
if original_ext == 'f4m':
formats.extend(self._extract_f4m_formats(
2015-04-16 17:48:22 +02:00
full_url + '?hdcore=3.4.0', display_id, f4m_id=format_id))
elif original_ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
2015-04-16 17:48:22 +02:00
full_url, display_id, 'mp4', m3u8_id=format_id))
else:
formats.append({
'url': full_url,
2015-04-16 17:28:21 +02:00
'ext': original_ext,
'format_id': format_id,
'quality': 0 if 'HD' in quality else -1,
'preference': 1,
})
2015-04-16 16:00:45 +02:00
self._sort_formats(formats)
2015-04-16 16:48:17 +02:00
subtitles = {}
subtitles_data = video_data.find('Subtitles')
if subtitles_data is not None:
subtitles_list = [{
'url': sub.text,
'ext': determine_ext(sub.text),
} for sub in subtitles_data]
if subtitles_list:
subtitles['de'] = subtitles_list
2015-04-16 16:00:45 +02:00
return {
'id': video_id,
'display_id': display_id,
'formats': formats,
'title': title,
'thumbnails': thumbnails,
'timestamp': timestamp,
2015-04-16 16:48:17 +02:00
'subtitles': subtitles,
2015-04-16 16:00:45 +02:00
}