From 8604e882a8f99fcd632efbb94e449477d860218d Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sun, 25 Jan 2015 05:23:21 +0100 Subject: [PATCH] [ubu] Fix test and modernize --- youtube_dl/extractor/ubu.py | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/youtube_dl/extractor/ubu.py b/youtube_dl/extractor/ubu.py index 0182d67ec..d50237758 100644 --- a/youtube_dl/extractor/ubu.py +++ b/youtube_dl/extractor/ubu.py @@ -3,50 +3,51 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + qualities, +) class UbuIE(InfoExtractor): _VALID_URL = r'http://(?:www\.)?ubu\.com/film/(?P[\da-z_-]+)\.html' _TEST = { 'url': 'http://ubu.com/film/her_noise.html', - 'md5': '8edd46ee8aa6b265fb5ed6cf05c36bc9', + 'md5': '138d5652618bf0f03878978db9bef1ee', 'info_dict': { 'id': 'her_noise', - 'ext': 'mp4', + 'ext': 'm4v', 'title': 'Her Noise - The Making Of (2007)', 'duration': 3600, }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + 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, default=None)) - if duration: - duration *= 60 + 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/[^"]+)"'] + ('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,