|
|
@ -3,50 +3,51 @@ from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
import re
|
|
|
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
|
|
|
from .common import InfoExtractor
|
|
|
|
from ..utils import int_or_none
|
|
|
|
from ..utils import (
|
|
|
|
|
|
|
|
int_or_none,
|
|
|
|
|
|
|
|
qualities,
|
|
|
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class UbuIE(InfoExtractor):
|
|
|
|
class UbuIE(InfoExtractor):
|
|
|
|
_VALID_URL = r'http://(?:www\.)?ubu\.com/film/(?P<id>[\da-z_-]+)\.html'
|
|
|
|
_VALID_URL = r'http://(?:www\.)?ubu\.com/film/(?P<id>[\da-z_-]+)\.html'
|
|
|
|
_TEST = {
|
|
|
|
_TEST = {
|
|
|
|
'url': 'http://ubu.com/film/her_noise.html',
|
|
|
|
'url': 'http://ubu.com/film/her_noise.html',
|
|
|
|
'md5': '8edd46ee8aa6b265fb5ed6cf05c36bc9',
|
|
|
|
'md5': '138d5652618bf0f03878978db9bef1ee',
|
|
|
|
'info_dict': {
|
|
|
|
'info_dict': {
|
|
|
|
'id': 'her_noise',
|
|
|
|
'id': 'her_noise',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'ext': 'm4v',
|
|
|
|
'title': 'Her Noise - The Making Of (2007)',
|
|
|
|
'title': 'Her Noise - The Making Of (2007)',
|
|
|
|
'duration': 3600,
|
|
|
|
'duration': 3600,
|
|
|
|
},
|
|
|
|
},
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
def _real_extract(self, url):
|
|
|
|
mobj = re.match(self._VALID_URL, url)
|
|
|
|
video_id = self._match_id(url)
|
|
|
|
video_id = mobj.group('id')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
webpage = self._download_webpage(url, video_id)
|
|
|
|
webpage = self._download_webpage(url, video_id)
|
|
|
|
|
|
|
|
|
|
|
|
title = self._html_search_regex(
|
|
|
|
title = self._html_search_regex(
|
|
|
|
r'<title>.+?Film & Video: ([^<]+)</title>', webpage, 'title')
|
|
|
|
r'<title>.+?Film & Video: ([^<]+)</title>', webpage, 'title')
|
|
|
|
|
|
|
|
|
|
|
|
duration = int_or_none(self._html_search_regex(
|
|
|
|
duration = int_or_none(self._html_search_regex(
|
|
|
|
r'Duration: (\d+) minutes', webpage, 'duration', fatal=False, default=None))
|
|
|
|
r'Duration: (\d+) minutes', webpage, 'duration', fatal=False),
|
|
|
|
if duration:
|
|
|
|
invscale=60)
|
|
|
|
duration *= 60
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
formats = []
|
|
|
|
formats = []
|
|
|
|
|
|
|
|
|
|
|
|
FORMAT_REGEXES = [
|
|
|
|
FORMAT_REGEXES = [
|
|
|
|
['sq', r"'flashvars'\s*,\s*'file=([^']+)'"],
|
|
|
|
('sq', r"'flashvars'\s*,\s*'file=([^']+)'"),
|
|
|
|
['hq', r'href="(http://ubumexico\.centro\.org\.mx/video/[^"]+)"']
|
|
|
|
('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:
|
|
|
|
for format_id, format_regex in FORMAT_REGEXES:
|
|
|
|
m = re.search(format_regex, webpage)
|
|
|
|
m = re.search(format_regex, webpage)
|
|
|
|
if m:
|
|
|
|
if m:
|
|
|
|
formats.append({
|
|
|
|
formats.append({
|
|
|
|
'url': m.group(1),
|
|
|
|
'url': m.group(1),
|
|
|
|
'format_id': format_id,
|
|
|
|
'format_id': format_id,
|
|
|
|
|
|
|
|
'preference': preference(format_id),
|
|
|
|
})
|
|
|
|
})
|
|
|
|
|
|
|
|
self._sort_formats(formats)
|
|
|
|
|
|
|
|
|
|
|
|
return {
|
|
|
|
return {
|
|
|
|
'id': video_id,
|
|
|
|
'id': video_id,
|
|
|
|