From b0cf2e7c1b844e533c447572b6979ae64f7e2870 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Fri, 15 Apr 2016 03:48:23 +0800 Subject: [PATCH] [ubu] Remove extractor 1. Videos on ubu.com are now hosted on Vimeo 2. The duration is far from correct, and may not exist on other videos (For example http://ubu.com/film/hammons_king.html) --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/ubu.py | 57 ------------------------------ 2 files changed, 58 deletions(-) delete mode 100644 youtube_dl/extractor/ubu.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 0a75a56c5f..d9193349d7 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -833,7 +833,6 @@ TwitterIE, TwitterAmplifyIE, ) -from .ubu import UbuIE from .udemy import ( UdemyIE, UdemyCourseIE diff --git a/youtube_dl/extractor/ubu.py b/youtube_dl/extractor/ubu.py deleted file mode 100644 index 1d52cbc98e..0000000000 --- a/youtube_dl/extractor/ubu.py +++ /dev/null @@ -1,57 +0,0 @@ -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ( - int_or_none, - qualities, -) - - -class UbuIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?ubu\.com/film/(?P[\da-z_-]+)\.html' - _TEST = { - 'url': 'http://ubu.com/film/her_noise.html', - 'md5': '138d5652618bf0f03878978db9bef1ee', - 'info_dict': { - 'id': 'her_noise', - 'ext': 'm4v', - 'title': 'Her Noise - The Making Of (2007)', - 'duration': 3600, - }, - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - title = self._html_search_regex( - r'.+?Film & Video: ([^<]+)', webpage, 'title') - - duration = int_or_none(self._html_search_regex( - r'Duration: (\d+) minutes', webpage, 'duration', fatal=False), - invscale=60) - - formats = [] - FORMAT_REGEXES = [ - ('sq', r"'flashvars'\s*,\s*'file=([^']+)'"), - ('hq', r'href="(http://ubumexico\.centro\.org\.mx/video/[^"]+)"'), - ] - preference = qualities([fid for fid, _ in FORMAT_REGEXES]) - for format_id, format_regex in FORMAT_REGEXES: - m = re.search(format_regex, webpage) - if m: - formats.append({ - 'url': m.group(1), - 'format_id': format_id, - 'preference': preference(format_id), - }) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'duration': duration, - 'formats': formats, - }