From cb28e0338665c96b2d5b35d203b1d54a57f3feb1 Mon Sep 17 00:00:00 2001 From: nyuszika7h Date: Mon, 10 Aug 2015 19:27:16 +0200 Subject: [PATCH] [indavideo] Add new extractor Closes #2147. --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/indavideo.py | 79 +++++++++++++++++++++++++++++++ 2 files changed, 80 insertions(+) create mode 100644 youtube_dl/extractor/indavideo.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 9a6308723..3bcfa93bb 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -242,6 +242,7 @@ from .imdb import ( ) from .imgur import ImgurIE from .ina import InaIE +from .indavideo import IndavideoIE from .infoq import InfoQIE from .instagram import InstagramIE, InstagramUserIE from .internetvideoarchive import InternetVideoArchiveIE diff --git a/youtube_dl/extractor/indavideo.py b/youtube_dl/extractor/indavideo.py new file mode 100644 index 000000000..2a2cf2bd3 --- /dev/null +++ b/youtube_dl/extractor/indavideo.py @@ -0,0 +1,79 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .. import utils +from .common import InfoExtractor + + +class IndavideoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?indavideo\.hu/video/(?P.+)' + _TESTS = [ + { + 'url': 'http://indavideo.hu/video/Cicatanc', + 'md5': 'c8a507a1c7410685f83a06eaeeaafeab', + 'info_dict': { + 'id': '1837039', + 'title': 'Cicatánc', + 'ext': 'mp4', + 'display_id': 'Cicatanc', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': '', + 'uploader': 'cukiajanlo', + 'uploader_id': '83729', + 'duration': 72, + 'age_limit': 0, + 'tags': ['tánc', 'cica', 'cuki', 'cukiajanlo', 'newsroom'] + }, + }, + { + 'url': 'http://indavideo.hu/video/Vicces_cica_1', + 'md5': '8c82244ba85d2a2310275b318eb51eac', + 'info_dict': { + 'id': '1335611', + 'title': 'Vicces cica', + 'ext': 'mp4', + 'display_id': 'Vicces_cica_1', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'Játszik a tablettel. :D', + 'uploader': 'Jet_Pack', + 'uploader_id': '491217', + 'duration': 7, + 'age_limit': 0, + 'tags': ['vicces', 'macska', 'cica', 'ügyes', 'nevetés', 'játszik', 'Cukiság', 'Jet_Pack'], + }, + }, + ] + + def _real_extract(self, url): + video_disp_id = self._match_id(url) + webpage = self._download_webpage(url, video_disp_id) + + embed_url = self._html_search_regex(r'', webpage, 'embed_url') + video_hash = embed_url.split('/')[-1] + + payload = self._download_json('http://amfphp.indavideo.hu/SYm0json.php/player.playerHandler.getVideoData/' + video_hash, video_disp_id) + video_info = payload['data'] + + thumbnails = video_info.get('thumbnails') + if thumbnails: + thumbnails = [{'url': self._proto_relative_url(x)} for x in thumbnails] + + tags = video_info.get('tags') + if tags: + tags = [x['title'] for x in tags] + + return { + 'id': video_info.get('id'), + 'title': video_info['title'], + 'url': video_info['video_file'], + 'ext': 'mp4', + 'display_id': video_disp_id, + 'thumbnails': thumbnails, + 'description': video_info.get('description'), + 'uploader': video_info.get('user_name'), + # TODO: upload date (it's in CET/CEST) + 'uploader_id': video_info.get('user_id'), + 'duration': utils.int_or_none(video_info.get('length')), + 'age_limit': utils.int_or_none(video_info.get('age_limit')), + 'tags': tags, + }