From 6bd499e8ca769cf69c4b24fa2d7a751d7869b679 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 26 May 2018 00:28:30 +0700 Subject: [PATCH] [peertube] Add support for generic embeds --- youtube_dl/extractor/generic.py | 15 +++++++++++++++ youtube_dl/extractor/peertube.py | 23 +++++++++++++++++------ 2 files changed, 32 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 76852f9dc..47ac139c9 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -108,6 +108,7 @@ from .vice import ViceIE from .xfileshare import XFileShareIE from .cloudflarestream import CloudflareStreamIE +from .peertube import PeerTubeIE class GenericIE(InfoExtractor): @@ -2012,6 +2013,15 @@ class GenericIE(InfoExtractor): 'skip_download': True, }, }, + { + # PeerTube embed + 'url': 'https://joinpeertube.org/fr/home/', + 'info_dict': { + 'id': 'home', + 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube', + }, + 'playlist_count': 2, + }, { 'url': 'http://share-videos.se/auto/video/83645793?uid=13', 'md5': 'b68d276de422ab07ee1d49388103f457', @@ -3029,6 +3039,11 @@ def _real_extract(self, url): return self.playlist_from_matches( cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key()) + peertube_urls = PeerTubeIE._extract_urls(webpage) + if peertube_urls: + return self.playlist_from_matches( + peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key()) + sharevideos_urls = [mobj.group('url') for mobj in re.finditer( r']+?\bsrc\s*=\s*(["\'])(?P(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1', webpage)] diff --git a/youtube_dl/extractor/peertube.py b/youtube_dl/extractor/peertube.py index 61c41add0..a481b3151 100644 --- a/youtube_dl/extractor/peertube.py +++ b/youtube_dl/extractor/peertube.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..compat import compat_str from ..utils import ( @@ -13,9 +15,7 @@ class PeerTubeIE(InfoExtractor): - _VALID_URL = r'''(?x) - https?:// - (?: + _INSTANCES_RE = r'''(?: # Taken from https://instances.joinpeertube.org/instances tube\.openalgeria\.org| peertube\.pointsecu\.fr| @@ -115,10 +115,13 @@ class PeerTubeIE(InfoExtractor): peertube2\.cpy\.re| videos\.tcit\.fr| peertube\.cpy\.re - ) + )''' + _VALID_URL = r'''(?x) + https?:// + %s /(?:videos/(?:watch|embed)|api/v\d/videos)/ - (?P[^/?#&]+) - ''' + (?P[^/?\#&]+) + ''' % _INSTANCES_RE _TESTS = [{ 'url': 'https://peertube.moe/videos/watch/2790feb0-8120-4e63-9af3-c943c69f5e6c', 'md5': '80f24ff364cc9d333529506a263e7feb', @@ -156,6 +159,14 @@ class PeerTubeIE(InfoExtractor): 'only_matching': True, }] + @staticmethod + def _extract_urls(webpage): + return [ + mobj.group('url') + for mobj in re.finditer( + r'''(?x)]+\bsrc=(["\'])(?P(?:https?:)?//%s/videos/embed/[^/?\#&]+)\1''' + % PeerTubeIE._INSTANCES_RE, webpage)] + def _real_extract(self, url): video_id = self._match_id(url)