Merge branch 'lecture2go' of https://github.com/nichdu/youtube-dl into nichdu-lecture2go

[youtube-dl] / youtube_dl / compat.py

diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py
index 54ccf1d28773dcc975ed43e8dd3704da77e4d4b4..0c57c7aebf6bd45a8f9edfc7e1d585f1bbf2f23a 100644 (file)
--- a/youtube_dl/compat.py
+++ b/youtube_dl/compat.py
@@ -77,8 +77,12 @@ except ImportError:
 try:
     from urllib.parse import unquote_to_bytes as compat_urllib_parse_unquote_to_bytes
     from urllib.parse import unquote as compat_urllib_parse_unquote
+    from urllib.parse import unquote_plus as compat_urllib_parse_unquote_plus
 except ImportError:  # Python 2
-    # HACK: The following are the correct unquote_to_bytes and unquote
+    _asciire = (compat_urllib_parse._asciire if hasattr(compat_urllib_parse, '_asciire')
+                else re.compile('([\x00-\x7f]+)'))
+
+    # HACK: The following are the correct unquote_to_bytes, unquote and unquote_plus
     # implementations from cpython 3.4.3's stdlib. Python 2's version
     # is apparently broken (see https://github.com/rg3/youtube-dl/pull/6244)
 
@@ -123,7 +127,7 @@ except ImportError:  # Python 2
             encoding = 'utf-8'
         if errors is None:
             errors = 'replace'
-        bits = compat_urllib_parse._asciire.split(string)
+        bits = _asciire.split(string)
         res = [bits[0]]
         append = res.append
         for i in range(1, len(bits), 2):
@@ -131,6 +135,15 @@ except ImportError:  # Python 2
             append(bits[i + 1])
         return ''.join(res)
 
+    def compat_urllib_parse_unquote_plus(string, encoding='utf-8', errors='replace'):
+        """Like unquote(), but also replace plus signs by spaces, as required for
+        unquoting HTML form values.
+
+        unquote_plus('%7e/abc+def') -> '~/abc def'
+        """
+        string = string.replace('+', ' ')
+        return compat_urllib_parse_unquote(string, encoding, errors)
+
 try:
     compat_str = unicode  # Python 2
 except NameError:
@@ -441,6 +454,7 @@ __all__ = [
     'compat_urllib_error',
     'compat_urllib_parse',
     'compat_urllib_parse_unquote',
+    'compat_urllib_parse_unquote_plus',
     'compat_urllib_parse_unquote_to_bytes',
     'compat_urllib_parse_urlparse',
     'compat_urllib_request',