[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)
This commit is contained in:
Yen Chi Hsuan 2016-04-15 03:48:23 +08:00
parent 74b47d00c3
commit b0cf2e7c1b
No known key found for this signature in database
GPG Key ID: 3FDDD575826C5C30
2 changed files with 0 additions and 58 deletions

View File

@ -833,7 +833,6 @@
TwitterIE,
TwitterAmplifyIE,
)
from .ubu import UbuIE
from .udemy import (
UdemyIE,
UdemyCourseIE

View File

@ -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<id>[\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'<title>.+?Film &amp; Video: ([^<]+)</title>', 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,
}