diff options
| author | Stefan Behnel <stefan_ml@behnel.de> | 2017-03-18 10:09:00 +0100 |
|---|---|---|
| committer | Stefan Behnel <stefan_ml@behnel.de> | 2017-03-18 10:09:00 +0100 |
| commit | 6e1d219ffebebfabaf4408236f4d46c4990d782d (patch) | |
| tree | 71c7a3b17fc5a8429ee23136a4b3f802cc24100c | |
| parent | 82a354a2ad2a1ecafc729e619bd7875646250fcc (diff) | |
| download | python-lxml-6e1d219ffebebfabaf4408236f4d46c4990d782d.tar.gz | |
improve type check and comment
| -rw-r--r-- | src/lxml/html/html5parser.py | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/src/lxml/html/html5parser.py b/src/lxml/html/html5parser.py index ba9d41b3..ed70b340 100644 --- a/src/lxml/html/html5parser.py +++ b/src/lxml/html/html5parser.py @@ -148,10 +148,10 @@ def fromstring(html, guess_charset=True, parser=None): # document starts with doctype or <html>, full document! start = html[:50] - if hasattr(start, 'decode'): - # In python3, we may have been presented with a bytes object. - # Decode in ascii, that also covers latin-1 and utf-8 for the - # characters we need + if isinstance(start, bytes): + # Allow text comparison in python3. + # Decode as ascii, that also covers latin-1 and utf-8 for the + # characters we need. start = start.decode('ascii', 'replace') start = start.lstrip().lower() |