192 lines
7.2 KiB
Python
192 lines
7.2 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
from .common import SelfhostedInfoExtractor
|
|
from ..compat import compat_str
|
|
from ..utils import (
|
|
int_or_none,
|
|
parse_resolution,
|
|
str_or_none,
|
|
try_get,
|
|
unified_timestamp,
|
|
url_or_none,
|
|
urljoin,
|
|
)
|
|
|
|
|
|
class PeerTubeSHIE(SelfhostedInfoExtractor):
|
|
_UUID_RE = r'[\da-fA-F]{8}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{12}'
|
|
_API_BASE = 'https://%s/api/v1/videos/%s/%s'
|
|
_VALID_URL = r'peertube:(?P<host>[^:]+):(?P<id>%s)' % (_UUID_RE)
|
|
_SH_VALID_URL = r'https?://(?P<host>[^/]+)/(?:videos/(?:watch|embed)|api/v\d/videos)/(?P<id>%s)' % _UUID_RE
|
|
_SH_VALID_CONTENT_STRINGS = (
|
|
'<title>PeerTube<',
|
|
'There will be other non JS-based clients to access PeerTube',
|
|
'>We are sorry but it seems that PeerTube is not compatible with your web browser.<',
|
|
)
|
|
|
|
_TESTS = [{
|
|
'url': 'https://framatube.org/videos/watch/9c9de5e8-0a1e-484a-b099-e80766180a6d',
|
|
'md5': '9bed8c0137913e17b86334e5885aacff',
|
|
'info_dict': {
|
|
'id': '9c9de5e8-0a1e-484a-b099-e80766180a6d',
|
|
'ext': 'mp4',
|
|
'title': 'What is PeerTube?',
|
|
'description': 'md5:3fefb8dde2b189186ce0719fda6f7b10',
|
|
'thumbnail': r're:https?://.*\.(?:jpg|png)',
|
|
'timestamp': 1538391166,
|
|
'upload_date': '20181001',
|
|
'uploader': 'Framasoft',
|
|
'uploader_id': '3',
|
|
'uploader_url': 'https://framatube.org/accounts/framasoft',
|
|
'channel': 'Les vidéos de Framasoft',
|
|
'channel_id': '2',
|
|
'channel_url': 'https://framatube.org/video-channels/bf54d359-cfad-4935-9d45-9d6be93f63e8',
|
|
'language': 'en',
|
|
'license': 'Attribution - Share Alike',
|
|
'duration': 113,
|
|
'view_count': int,
|
|
'like_count': int,
|
|
'dislike_count': int,
|
|
'tags': ['framasoft', 'peertube'],
|
|
'categories': ['Science & Technology'],
|
|
}
|
|
}, {
|
|
'url': 'https://peertube.tamanoir.foucry.net/videos/watch/0b04f13d-1e18-4f1d-814e-4979aa7c9c44',
|
|
'only_matching': True,
|
|
}, {
|
|
# nsfw
|
|
'url': 'https://tube.22decembre.eu/videos/watch/9bb88cd3-9959-46d9-9ab9-33d2bb704c39',
|
|
'only_matching': True,
|
|
}, {
|
|
'url': 'https://tube.22decembre.eu/videos/embed/fed67262-6edb-4d1c-833b-daa9085c71d7',
|
|
'only_matching': True,
|
|
}, {
|
|
'url': 'https://tube.openalgeria.org/api/v1/videos/c1875674-97d0-4c94-a058-3f7e64c962e8',
|
|
'only_matching': True,
|
|
}, {
|
|
'url': 'peertube:video.blender.org:b37a5b9f-e6b5-415c-b700-04a5cd6ec205',
|
|
'only_matching': True,
|
|
}]
|
|
|
|
@staticmethod
|
|
def _extract_urls(webpage, **kwargs):
|
|
entries = re.finditer(
|
|
r'''(?x)<iframe[^>]+\bsrc=["\'](?:https?:)?//(?P<host>[^/]+)/videos/embed/(?P<video_id>%s)'''
|
|
% (PeerTubeSHIE._UUID_RE), webpage)
|
|
return ['peertube:%s:%s' % (mobj.group('host'), mobj.group('video_id'))
|
|
for mobj in entries]
|
|
|
|
def _call_api(self, host, video_id, path, note=None, errnote=None, fatal=True):
|
|
return self._download_json(
|
|
self._API_BASE % (host, video_id, path), video_id,
|
|
note=note, errnote=errnote, fatal=fatal)
|
|
|
|
def _get_subtitles(self, host, video_id):
|
|
captions = self._call_api(
|
|
host, video_id, 'captions', note='Downloading captions JSON',
|
|
fatal=False)
|
|
if not isinstance(captions, dict):
|
|
return
|
|
data = captions.get('data')
|
|
if not isinstance(data, list):
|
|
return
|
|
subtitles = {}
|
|
for e in data:
|
|
language_id = try_get(e, lambda x: x['language']['id'], compat_str)
|
|
caption_url = urljoin('https://%s' % host, e.get('captionPath'))
|
|
if not caption_url:
|
|
continue
|
|
subtitles.setdefault(language_id or 'en', []).append({
|
|
'url': caption_url,
|
|
})
|
|
return subtitles
|
|
|
|
def _selfhosted_extract(self, url, webpage=None):
|
|
mobj = re.match(self._VALID_URL, url)
|
|
if not mobj:
|
|
mobj = re.match(self._SH_VALID_URL, url)
|
|
host = mobj.group('host')
|
|
video_id = mobj.group('id')
|
|
|
|
video = self._call_api(
|
|
host, video_id, '', note='Downloading video JSON')
|
|
|
|
title = video['name']
|
|
|
|
formats = []
|
|
for file_ in video['files']:
|
|
if not isinstance(file_, dict):
|
|
continue
|
|
file_url = url_or_none(file_.get('fileUrl'))
|
|
if not file_url:
|
|
continue
|
|
file_size = int_or_none(file_.get('size'))
|
|
format_id = try_get(
|
|
file_, lambda x: x['resolution']['label'], compat_str)
|
|
f = parse_resolution(format_id)
|
|
f.update({
|
|
'url': file_url,
|
|
'format_id': format_id,
|
|
'filesize': file_size,
|
|
})
|
|
formats.append(f)
|
|
self._sort_formats(formats)
|
|
|
|
full_description = self._call_api(
|
|
host, video_id, 'description', note='Downloading description JSON',
|
|
fatal=False)
|
|
|
|
description = None
|
|
if isinstance(full_description, dict):
|
|
description = str_or_none(full_description.get('description'))
|
|
if not description:
|
|
description = video.get('description')
|
|
|
|
subtitles = self.extract_subtitles(host, video_id)
|
|
|
|
def data(section, field, type_):
|
|
return try_get(video, lambda x: x[section][field], type_)
|
|
|
|
def account_data(field, type_):
|
|
return data('account', field, type_)
|
|
|
|
def channel_data(field, type_):
|
|
return data('channel', field, type_)
|
|
|
|
category = data('category', 'label', compat_str)
|
|
categories = [category] if category else None
|
|
|
|
nsfw = video.get('nsfw')
|
|
if nsfw is bool:
|
|
age_limit = 18 if nsfw else 0
|
|
else:
|
|
age_limit = None
|
|
|
|
return {
|
|
'id': video_id,
|
|
'title': title,
|
|
'description': description,
|
|
'thumbnail': urljoin(url, video.get('thumbnailPath')),
|
|
'timestamp': unified_timestamp(video.get('publishedAt')),
|
|
'uploader': account_data('displayName', compat_str),
|
|
'uploader_id': str_or_none(account_data('id', int)),
|
|
'uploader_url': url_or_none(account_data('url', compat_str)),
|
|
'channel': channel_data('displayName', compat_str),
|
|
'channel_id': str_or_none(channel_data('id', int)),
|
|
'channel_url': url_or_none(channel_data('url', compat_str)),
|
|
'language': data('language', 'id', compat_str),
|
|
'license': data('licence', 'label', compat_str),
|
|
'duration': int_or_none(video.get('duration')),
|
|
'view_count': int_or_none(video.get('views')),
|
|
'like_count': int_or_none(video.get('likes')),
|
|
'dislike_count': int_or_none(video.get('dislikes')),
|
|
'age_limit': age_limit,
|
|
'tags': try_get(video, lambda x: x['tags'], list),
|
|
'categories': categories,
|
|
'formats': formats,
|
|
'subtitles': subtitles
|
|
}
|