github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

Allow non-ASCII characters in simplified titles(Closes #220)

Browse source
This commit is contained in:
Philipp Hagemeister 2011-11-21 21:50:39 +01:00
parent e092418d8b
commit af8e8d63f9
2 changed files with 9 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
test/test_div.py
View file

@ -16,13 +16,14 @@ def test_simplify_title():
assert u'/' not in youtube_dl._simplify_title(u'abc/de')
assert u'abc' in youtube_dl._simplify_title(u'abc/de')
assert u'de' in youtube_dl._simplify_title(u'abc/de')
assert u'/' not in youtube_dl._simplify_title(u'abc/de///')
assert u'\\' not in youtube_dl._simplify_title(u'abc\\de')
assert u'abc' in youtube_dl._simplify_title(u'abc\\de')
assert u'de' in youtube_dl._simplify_title(u'abc\\de')
# TODO: Fix #220
#assert youtube_dl._simplify_title(u'ä') == u'ä'
assert youtube_dl._simplify_title(u'ä') == u'ä'
assert youtube_dl._simplify_title(u'кириллица') == u'кириллица'
# Strip underlines
assert youtube_dl._simplify_title(u'\'a_') == u'a'

10
youtube_dl/__init__.py
View file

@ -278,7 +278,8 @@ def timeconvert(timestr):
return timestamp
def _simplify_title(title):
return re.sub(ur'[^\w\d_\-]+', u'_', title).strip(u'_')
expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE)
return expr.sub(u'_', title).strip(u'_')
class DownloadError(Exception):
"""Download Error exception.
@ -2937,6 +2938,7 @@ def _real_extract(self, url):
if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
basename = url.split('/')[-1]
title,ext = os.path.splitext(basename)
title = title.decode('UTF-8')
ext = ext.replace('.', '')
self.report_direct_download(title)
info = {
@ -3089,9 +3091,9 @@ def _real_extract(self, url):
if mobj.group('shortname'):
if mobj.group('shortname') in ('tds', 'thedailyshow'):
url = 'http://www.thedailyshow.com/full-episodes/'
url = u'http://www.thedailyshow.com/full-episodes/'
else:
url = 'http://www.colbertnation.com/full-episodes/'
url = u'http://www.colbertnation.com/full-episodes/'
mobj = re.match(self._VALID_URL, url)
assert mobj is not None
@ -3177,7 +3179,7 @@ def _real_extract(self, url):
self._downloader.increment_downloads()
effTitle = showId + '-' + epTitle
effTitle = showId + u'-' + epTitle
info = {
'id': shortMediaId,
'url': video_url,