From c58843b3a15393a46e74c8c1301b828dfcb5002c Mon Sep 17 00:00:00 2001 From: Will Glynn Date: Thu, 18 Dec 2014 22:28:13 -0600 Subject: [PATCH] [nerdcubed] Add new extractor nerdcubed.co.uk describes videos in a single a feed.json file, providing references to and metadata on >1300 YouTube videos spread across 3 main channels as well as guest appareances on other channels via a single HTTP request. NerdCubedFeedIE transforms this feed into a youtube-dl playlist, preserving information present in the upstream JSON (allowing zero-cost title/date matches) and ultimately referencing the embedded YouTube videos. --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/nerdcubed.py | 36 +++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) create mode 100644 youtube_dl/extractor/nerdcubed.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 79f6f6f13..76f13bf52 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -264,6 +264,7 @@ ) from .ndr import NDRIE from .ndtv import NDTVIE +from .nerdcubed import NerdCubedFeedIE from .newgrounds import NewgroundsIE from .newstube import NewstubeIE from .nfb import NFBIE diff --git a/youtube_dl/extractor/nerdcubed.py b/youtube_dl/extractor/nerdcubed.py new file mode 100644 index 000000000..9f2e678e0 --- /dev/null +++ b/youtube_dl/extractor/nerdcubed.py @@ -0,0 +1,36 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import datetime + +from .common import InfoExtractor + + +class NerdCubedFeedIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?nerdcubed\.co\.uk/feed\.json' + _TEST = { + 'url': 'http://www.nerdcubed.co.uk/feed.json', + 'info_dict': { + 'title': 'nerdcubed.co.uk feed', + }, + 'playlist_mincount': 1300, + } + + def _real_extract(self, url): + feed = self._download_json(url, url, "Downloading NerdCubed JSON feed") + + entries = [{ + '_type': 'url', + 'title': feed_entry['title'], + 'uploader': feed_entry['source']['name'] if feed_entry['source'] else None, + 'upload_date': datetime.datetime.strptime(feed_entry['date'], '%Y-%m-%d').strftime('%Y%m%d'), + 'url': "http://www.youtube.com/watch?v=" + feed_entry['youtube_id'], + } for feed_entry in feed] + + return { + '_type': 'playlist', + 'title': 'nerdcubed.co.uk feed', + 'id': 'nerdcubed-feed', + 'entries': entries, + } +