Generic: use compat_urllib_parse_unquote to prevent utf8 mangling

[youtube-dl] / youtube_dl / compat.py

diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py
index b2bf149ef63ffb1c31bfb02f976f5cce2dbadad3..1f4ccf443214d322121938cca58150f9aaa8803f 100644 (file)
--- a/youtube_dl/compat.py
+++ b/youtube_dl/compat.py
@@ -9,6 +9,7 @@ import shutil
 import socket
 import subprocess
 import sys
+import itertools
 
 
 try:
@@ -46,11 +47,6 @@ try:
 except ImportError:  # Python 2
     import htmlentitydefs as compat_html_entities
 
-try:
-    import html.parser as compat_html_parser
-except ImportError:  # Python 2
-    import HTMLParser as compat_html_parser
-
 try:
     import http.client as compat_http_client
 except ImportError:  # Python 2
@@ -98,6 +94,8 @@ except ImportError:
             try:
                 if not item:
                     raise ValueError
+                if not re.match('[0-9a-fA-F][0-9a-fA-F]',item[:2]):
+                    raise ValueError
                 pct_sequence += item[:2].decode('hex')
                 rest = item[2:]
                 if not rest:
@@ -389,10 +387,19 @@ else:
                 stdout=subprocess.PIPE, stderr=subprocess.PIPE)
             out, err = sp.communicate()
             lines, columns = map(int, out.split())
-        except:
+        except Exception:
             pass
         return _terminal_size(columns, lines)
 
+try:
+    itertools.count(start=0, step=1)
+    compat_itertools_count = itertools.count
+except TypeError:  # Python 2.6
+    def compat_itertools_count(start=0, step=1):
+        n = start
+        while True:
+            yield n
+            n += step
 
 __all__ = [
     'compat_HTTPError',
@@ -404,9 +411,9 @@ __all__ = [
     'compat_getenv',
     'compat_getpass',
     'compat_html_entities',
-    'compat_html_parser',
     'compat_http_client',
     'compat_http_server',
+    'compat_itertools_count',
     'compat_kwargs',
     'compat_ord',
     'compat_parse_qs',