[peertube] Fix issues and improve extraction (closes #23657)

This commit is contained in:
Sergey M․ 2020-03-03 03:01:23 +07:00
parent ac379fa236
commit 1e1c1960aa
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 34 additions and 22 deletions

View File

@ -416,6 +416,7 @@ class PeerTubeIE(InfoExtractor):
peertube\.cpy\.re peertube\.cpy\.re
)''' )'''
_UUID_RE = r'[\da-fA-F]{8}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{12}' _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'''(?x) _VALID_URL = r'''(?x)
(?: (?:
peertube:(?P<host>[^:]+):| peertube:(?P<host>[^:]+):|
@ -430,7 +431,7 @@ class PeerTubeIE(InfoExtractor):
'id': '9c9de5e8-0a1e-484a-b099-e80766180a6d', 'id': '9c9de5e8-0a1e-484a-b099-e80766180a6d',
'ext': 'mp4', 'ext': 'mp4',
'title': 'What is PeerTube?', 'title': 'What is PeerTube?',
'description': '**[Want to help to translate this video?](https://weblate.framasoft.org/projects/what-is-peertube-video/)**\r\n\r\n**Take back the control of your videos! [#JoinPeertube](https://joinpeertube.org)**\r\n*A decentralized video hosting network, based on free/libre software!*\r\n\r\n**Animation Produced by:** [LILA](https://libreart.info) - [ZeMarmot Team](https://film.zemarmot.net)\r\n*Directed by* Aryeom\r\n*Assistant* Jehan\r\n**Licence**: [CC-By-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/)\r\n\r\n**Sponsored by** [Framasoft](https://framasoft.org)\r\n\r\n**Music**: [Red Step Forward](http://play.dogmazic.net/song.php?song_id=52491) - CC-By Ken Bushima\r\n\r\n**Movie Clip**: [Caminades 3: Llamigos](http://www.caminandes.com/) CC-By Blender Institute\r\n\r\n**Video sources**: https://gitlab.gnome.org/Jehan/what-is-peertube/', 'description': 'md5:3fefb8dde2b189186ce0719fda6f7b10',
'thumbnail': r're:https?://.*\.(?:jpg|png)', 'thumbnail': r're:https?://.*\.(?:jpg|png)',
'timestamp': 1538391166, 'timestamp': 1538391166,
'upload_date': '20181001', 'upload_date': '20181001',
@ -489,19 +490,27 @@ class PeerTubeIE(InfoExtractor):
entries = [peertube_url] entries = [peertube_url]
return entries return entries
def _get_subtitles(self, host, video_id): def _call_api(self, host, video_id, path, note=None, errnote=None, fatal=True):
video_captions = self._download_json( return self._download_json(
'https://%s/api/v1/videos/%s/captions' % (host, video_id), video_id, fatal=False) self._API_BASE % (host, video_id, path), video_id,
if not isinstance(video_captions, dict): note=note, errnote=errnote, fatal=fatal)
return None
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 = {} subtitles = {}
for entry in video_captions.get('data'): for e in data:
language_id = try_get(entry, lambda x: x['language']['id'], compat_str) language_id = try_get(e, lambda x: x['language']['id'], compat_str)
caption_path = str_or_none(entry.get('captionPath')) caption_url = urljoin('https://%s' % host, e.get('captionPath'))
if language_id and caption_path: if not caption_url:
caption_url = urljoin('https://%s' % host, entry.get('captionPath')) continue
subtitles.setdefault(language_id, []).append({ subtitles.setdefault(language_id or 'en', []).append({
'url': caption_url, 'url': caption_url,
}) })
return subtitles return subtitles
@ -511,8 +520,8 @@ class PeerTubeIE(InfoExtractor):
host = mobj.group('host') or mobj.group('host_2') host = mobj.group('host') or mobj.group('host_2')
video_id = mobj.group('id') video_id = mobj.group('id')
video = self._download_json( video = self._call_api(
'https://%s/api/v1/videos/%s' % (host, video_id), video_id) host, video_id, '', note='Downloading video JSON')
title = video['name'] title = video['name']
@ -535,12 +544,15 @@ class PeerTubeIE(InfoExtractor):
formats.append(f) formats.append(f)
self._sort_formats(formats) self._sort_formats(formats)
video_description = self._download_json( full_description = self._call_api(
'https://%s/api/v1/videos/%s/description' % (host, video_id), video_id, fatal=False) host, video_id, 'description', note='Downloading description JSON',
fatal=False)
description = None description = None
if isinstance(video_description, dict): if isinstance(full_description, dict):
description = str_or_none(video_description.get('description')) description = str_or_none(full_description.get('description'))
if not description:
description = video.get('description')
subtitles = self.extract_subtitles(host, video_id) subtitles = self.extract_subtitles(host, video_id)
@ -569,10 +581,10 @@ class PeerTubeIE(InfoExtractor):
'thumbnail': urljoin(url, video.get('thumbnailPath')), 'thumbnail': urljoin(url, video.get('thumbnailPath')),
'timestamp': unified_timestamp(video.get('publishedAt')), 'timestamp': unified_timestamp(video.get('publishedAt')),
'uploader': account_data('displayName', compat_str), 'uploader': account_data('displayName', compat_str),
'uploader_id': str(account_data('id', int)), 'uploader_id': str_or_none(account_data('id', int)),
'uploader_url': url_or_none(account_data('url', compat_str)), 'uploader_url': url_or_none(account_data('url', compat_str)),
'channel': channel_data('displayName', compat_str), 'channel': channel_data('displayName', compat_str),
'channel_id': str(channel_data('id', int)), 'channel_id': str_or_none(channel_data('id', int)),
'channel_url': url_or_none(channel_data('url', compat_str)), 'channel_url': url_or_none(channel_data('url', compat_str)),
'language': data('language', 'id', compat_str), 'language': data('language', 'id', compat_str),
'license': data('licence', 'label', compat_str), 'license': data('licence', 'label', compat_str),