diff options
| -rw-r--r-- | NEWS.txt | 4 | ||||
| -rw-r--r-- | bs4/builder/_htmlparser.py | 11 |
2 files changed, 10 insertions, 5 deletions
@@ -10,6 +10,10 @@ * Added a warning when you instantiate a BeautifulSoup object without explicitly naming a parser. [bug=1398866] +* In Python 3.4 and above, set the new convert_charrefs argument to + the html.parser constructor to avoid a warning and future + failures. Patch by Stefano Revera. [bug=1375721] + * Added a Chinese translation of the documentation by Delong .w. = 4.3.2 (20131002) = diff --git a/bs4/builder/_htmlparser.py b/bs4/builder/_htmlparser.py index 3e78c65..bf231f1 100644 --- a/bs4/builder/_htmlparser.py +++ b/bs4/builder/_htmlparser.py @@ -19,10 +19,8 @@ import warnings # At the end of this file, we monkeypatch HTMLParser so that # strict=True works well on Python 3.2.2. major, minor, release = sys.version_info[:3] -CONSTRUCTOR_TAKES_STRICT = ( - major > 3 - or (major == 3 and minor > 2) - or (major == 3 and minor == 2 and release >= 3)) +CONSTRUCTOR_TAKES_STRICT = major == 3 and minor == 2 and release >= 3 +CONSTRUCTOR_TAKES_CONVERT_CHARREFS = major == 3 and minor >= 4 from bs4.element import ( CData, @@ -63,7 +61,8 @@ class BeautifulSoupHTMLParser(HTMLParser): def handle_charref(self, name): # XXX workaround for a bug in HTMLParser. Remove this once - # it's fixed. + # it's fixed in all supported versions. + # http://bugs.python.org/issue13633 if name.startswith('x'): real_name = int(name.lstrip('x'), 16) elif name.startswith('X'): @@ -134,6 +133,8 @@ class HTMLParserTreeBuilder(HTMLTreeBuilder): def __init__(self, *args, **kwargs): if CONSTRUCTOR_TAKES_STRICT: kwargs['strict'] = False + if CONSTRUCTOR_TAKES_CONVERT_CHARREFS: + kwargs['convert_charrefs'] = False self.parser_args = (args, kwargs) def prepare_markup(self, markup, user_specified_encoding=None, |