From 892b47ab6c9147e785c562229e6dab305fffba61 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Mon, 27 Feb 2017 21:34:33 +0800 Subject: [PATCH] [scivee] Remove extractor (#9315) The Wikipedia page is changed from active to down: https://en.wikipedia.org/w/index.php?title=SciVee&diff=prev&oldid=723161154 Some other interesting bits: $ nslookup www.scivee.tv Server: 8.8.8.8 Address: 8.8.8.8#53 Non-authoritative answer: www.scivee.tv canonical name = scivee.rcsb.org. Name: scivee.rcsb.org Address: 132.249.231.211 $ nslookup rcsb.org Server: 8.8.8.8 Address: 8.8.8.8#53 Non-authoritative answer: Name: rcsb.org Address: 132.249.231.77 Both IPs are from UCSD. I guess it's maintained by a lab and they don't maintain it anymore. --- ChangeLog | 1 + youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/scivee.py | 57 ------------------------------ 3 files changed, 1 insertion(+), 58 deletions(-) delete mode 100644 youtube_dl/extractor/scivee.py diff --git a/ChangeLog b/ChangeLog index 4009acf370..4ed9cb4e0b 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,6 +1,7 @@ version Extractors +- [scivee] Remove extractor (#9315) + [MDR] Recognize more URL patterns (#12169) * [vevo] Fix extraction for videos with the new streams/streamsV3 format (#11719) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 58139ee4e0..d09104096e 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -838,7 +838,6 @@ from .safari import ( from .sapo import SapoIE from .savefrom import SaveFromIE from .sbs import SBSIE -from .scivee import SciVeeIE from .screencast import ScreencastIE from .screencastomatic import ScreencastOMaticIE from .scrippsnetworks import ScrippsNetworksWatchIE diff --git a/youtube_dl/extractor/scivee.py b/youtube_dl/extractor/scivee.py deleted file mode 100644 index b1ca12fdee..0000000000 --- a/youtube_dl/extractor/scivee.py +++ /dev/null @@ -1,57 +0,0 @@ -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import int_or_none - - -class SciVeeIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?scivee\.tv/node/(?P\d+)' - - _TEST = { - 'url': 'http://www.scivee.tv/node/62352', - 'md5': 'b16699b74c9e6a120f6772a44960304f', - 'info_dict': { - 'id': '62352', - 'ext': 'mp4', - 'title': 'Adam Arkin at the 2014 DOE JGI Genomics of Energy & Environment Meeting', - 'description': 'md5:81f1710638e11a481358fab1b11059d7', - }, - 'skip': 'Not accessible from Travis CI server', - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - # annotations XML is malformed - annotations = self._download_webpage( - 'http://www.scivee.tv/assets/annotations/%s' % video_id, video_id, 'Downloading annotations') - - title = self._html_search_regex(r'([^<]+)', annotations, 'title') - description = self._html_search_regex(r'([^<]+)', annotations, 'abstract', fatal=False) - filesize = int_or_none(self._html_search_regex( - r'([^<]+)', annotations, 'filesize', fatal=False)) - - formats = [ - { - 'url': 'http://www.scivee.tv/assets/audio/%s' % video_id, - 'ext': 'mp3', - 'format_id': 'audio', - }, - { - 'url': 'http://www.scivee.tv/assets/video/%s' % video_id, - 'ext': 'mp4', - 'format_id': 'video', - 'filesize': filesize, - }, - ] - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnail': 'http://www.scivee.tv/assets/videothumb/%s' % video_id, - 'formats': formats, - }