projects
/
youtube-dl
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
|
inline
| side by side (from parent 1:
cc1237f
)
[ubu] Fix test and modernize
author
Philipp Hagemeister
<phihag@phihag.de>
Sun, 25 Jan 2015 04:23:21 +0000
(
05:23
+0100)
committer
Philipp Hagemeister
<phihag@phihag.de>
Sun, 25 Jan 2015 04:23:21 +0000
(
05:23
+0100)
youtube_dl/extractor/ubu.py
patch
|
blob
|
history
diff --git
a/youtube_dl/extractor/ubu.py
b/youtube_dl/extractor/ubu.py
index 0182d67ec2db7fee5aa0b6f7f5457f13cca0c305..d5023775857a8bd27ee0f19cffd8176a477be4fd 100644
(file)
--- 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
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<id>[\da-z_-]+)\.html'
_TEST = {
'url': 'http://ubu.com/film/her_noise.html',
class UbuIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?ubu\.com/film/(?P<id>[\da-z_-]+)\.html'
_TEST = {
'url': 'http://ubu.com/film/her_noise.html',
- 'md5': '
8edd46ee8aa6b265fb5ed6cf05c36bc9
',
+ 'md5': '
138d5652618bf0f03878978db9bef1ee
',
'info_dict': {
'id': 'her_noise',
'info_dict': {
'id': 'her_noise',
- 'ext': 'm
p4
',
+ 'ext': 'm
4v
',
'title': 'Her Noise - The Making Of (2007)',
'duration': 3600,
},
}
def _real_extract(self, url):
'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'<title>.+?Film & Video: ([^<]+)</title>', webpage, 'title')
duration = int_or_none(self._html_search_regex(
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'<title>.+?Film & Video: ([^<]+)</title>', 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 = []
formats = []
-
FORMAT_REGEXES = [
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,
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,
return {
'id': video_id,