From 7a5e7b303c6186f01e475789de7ef8cc3f9eea94 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 2 Aug 2014 17:56:01 +0700 Subject: [PATCH] [ubu] Add extractor (Close #3418) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/ubu.py | 56 ++++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+) create mode 100644 youtube_dl/extractor/ubu.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index f6c0ee795..e73bea881 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -327,6 +327,7 @@ from .tutv import TutvIE from .tvigle import TvigleIE from .tvp import TvpIE from .tvplay import TVPlayIE +from.ubu import UbuIE from .udemy import ( UdemyIE, UdemyCourseIE diff --git a/youtube_dl/extractor/ubu.py b/youtube_dl/extractor/ubu.py new file mode 100644 index 000000000..0182d67ec --- /dev/null +++ b/youtube_dl/extractor/ubu.py @@ -0,0 +1,56 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import int_or_none + + +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', + 'info_dict': { + 'id': 'her_noise', + 'ext': 'mp4', + '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') + + 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 + + formats = [] + + FORMAT_REGEXES = [ + ['sq', r"'flashvars'\s*,\s*'file=([^']+)'"], + ['hq', r'href="(http://ubumexico\.centro\.org\.mx/video/[^"]+)"'] + ] + + 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, + }) + + return { + 'id': video_id, + 'title': title, + 'duration': duration, + 'formats': formats, + }