[utils] Add extract_attributes for extracting html tag attributes

This is much more robust than just using regexps, and handles all
the common scenarios, such as empty/no values, repeated attributes,
entity decoding, mixed case names, and the different possible value
quoting schemes.

1 files changed, 6 insertions, 0 deletions

diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py
index b497da696..7b9afc36d 100644
--- a/youtube_dl/compat.py
+++ b/youtube_dl/compat.py
@@ -77,6 +77,11 @@ try:
 except ImportError:  # Python 2
     from urllib import urlretrieve as compat_urlretrieve
 
+try:
+    from html.parser import HTMLParser as compat_HTMLParser
+except ImportError:  # Python 2
+    from HTMLParser import HTMLParser as compat_HTMLParser
+
 
 try:
     from subprocess import DEVNULL
@@ -540,6 +545,7 @@ else:
     from tokenize import generate_tokens as compat_tokenize_tokenize
 
 __all__ = [
+    'compat_HTMLParser',
     'compat_HTTPError',
     'compat_basestring',
     'compat_chr',