From c2a30b250cdea5a8c73225e6a14707a669640de0 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Fri, 23 Jan 2015 00:32:35 +0100 Subject: [PATCH] [testtube] Add new extractor (Fixes #4759) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/testtube.py | 60 ++++++++++++++++++++++++++++++++ 2 files changed, 61 insertions(+) create mode 100644 youtube_dl/extractor/testtube.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index a983fff76..9ab90ac62 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -432,6 +432,7 @@ from .telemb import TeleMBIE from .teletask import TeleTaskIE from .tenplay import TenPlayIE from .testurl import TestURLIE +from .testtube import TestTubeIE from .tf1 import TF1IE from .theonion import TheOnionIE from .theplatform import ThePlatformIE diff --git a/youtube_dl/extractor/testtube.py b/youtube_dl/extractor/testtube.py new file mode 100644 index 000000000..fd47e71a2 --- /dev/null +++ b/youtube_dl/extractor/testtube.py @@ -0,0 +1,60 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import int_or_none + + +class TestTubeIE(InfoExtractor): + _VALID_URL = r'https?://testtube\.com/[^/?#]+/(?P[^/?#]+)' + _TESTS = [{ + 'url': 'https://testtube.com/dnews/5-weird-ways-plants-can-eat-animals?utm_source=FB&utm_medium=DNews&utm_campaign=DNewsSocial', + 'info_dict': { + 'id': '60163', + 'display_id': '5-weird-ways-plants-can-eat-animals', + 'duration': 275, + 'ext': 'mp4', + 'title': '5 Weird Ways Plants Can Eat Animals', + 'description': 'Why have some plants evolved to eat meat?', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'DNews', + 'uploader_id': 'dnews', + }, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + video_id = self._search_regex( + r"player\.loadRevision3Item\('video_id',\s*([0-9]+)\);", + webpage, 'video ID') + + all_info = self._download_json( + 'https://testtube.com/api/getPlaylist.json?api_key=ba9c741bce1b9d8e3defcc22193f3651b8867e62&codecs=h264,vp8,theora&video_id=%s' % video_id, + video_id) + info = all_info['items'][0] + + formats = [] + for vcodec, fdatas in info['media'].items(): + for name, fdata in fdatas.items(): + formats.append({ + 'format_id': '%s-%s' % (vcodec, name), + 'url': fdata['url'], + 'vcodec': vcodec, + 'tbr': fdata.get('bitrate'), + }) + self._sort_formats(formats) + + duration = int_or_none(info.get('duration')) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': info['title'], + 'description': info.get('summary'), + 'thumbnail': info.get('images', {}).get('large'), + 'uploader': info.get('show', {}).get('name'), + 'uploader_id': info.get('show', {}).get('slug'), + 'duration': duration, + 'formats': formats, + }