[utils] Encode hostnames before passing to urllib

[youtube-dl] / youtube_dl / utils.py

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index bad1c4ea87dd086a34d93f6872d9ce5d9f2209f9..03bb7782f492daa247c6ababba6c975d5548d75e 100644 (file)
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -1346,7 +1346,7 @@ def format_bytes(bytes):
 def lookup_unit_table(unit_table, s):
     units_re = '|'.join(re.escape(u) for u in unit_table)
     m = re.match(
-        r'(?P<num>[0-9]+(?:[,.][0-9]*)?)\s*(?P<unit>%s)$' % units_re, s)
+        r'(?P<num>[0-9]+(?:[,.][0-9]*)?)\s*(?P<unit>%s)\b' % units_re, s)
     if not m:
         return None
     num_str = m.group('num').replace(',', '.')
@@ -1746,6 +1746,7 @@ def escape_url(url):
     """Escape URL as suggested by RFC 3986"""
     url_parsed = compat_urllib_parse_urlparse(url)
     return url_parsed._replace(
+        netloc=url_parsed.netloc.encode('idna').decode('ascii'),
         path=escape_rfc3986(url_parsed.path),
         params=escape_rfc3986(url_parsed.params),
         query=escape_rfc3986(url_parsed.query),