diff options
| author | Leonard Richardson <leonardr@segfault.org> | 2015-06-28 08:19:53 -0400 |
|---|---|---|
| committer | Leonard Richardson <leonardr@segfault.org> | 2015-06-28 08:19:53 -0400 |
| commit | e7eff8b01e3890f11dacf558bd9fd71c6dcbc29e (patch) | |
| tree | 53715f1704f6cf4c6135dce8c6fd464a0e54fa22 | |
| parent | 7d21694874e51a45a3ca03db1ad7c299e36834a7 (diff) | |
Accept 'xml' as an unambiguous identifier for the lxml XML parser, since it's the only XML parser supported at the moment.
| -rw-r--r-- | bs4/__init__.py | 9 | ||||
| -rw-r--r-- | bs4/builder/_lxml.py | 1 |
2 files changed, 8 insertions, 2 deletions
diff --git a/bs4/__init__.py b/bs4/__init__.py index e167544..f24d69c 100644 --- a/bs4/__init__.py +++ b/bs4/__init__.py @@ -77,7 +77,7 @@ class BeautifulSoup(Tag): ASCII_SPACES = '\x20\x0a\x09\x0c\x0d' - NO_PARSER_SPECIFIED_WARNING = "No parser was explicitly specified, so I'm using the best available parser for this system (\"%(parser)s\"). This usually isn't a problem, but if you run this code on another system, or in a different virtual environment, it may use a different parser and behave differently.\n\nTo get rid of this warning, change this:\n\n BeautifulSoup([your markup])\n\nto this:\n\n BeautifulSoup([your markup], \"%(parser)s\")\n" + NO_PARSER_SPECIFIED_WARNING = "No parser was explicitly specified, so I'm using the best available %(markup_type)s parser for this system (\"%(parser)s\"). This usually isn't a problem, but if you run this code on another system, or in a different virtual environment, it may use a different parser and behave differently.\n\nTo get rid of this warning, change this:\n\n BeautifulSoup([your markup])\n\nto this:\n\n BeautifulSoup([your markup], \"%(parser)s\")\n" def __init__(self, markup="", features=None, builder=None, parse_only=None, from_encoding=None, exclude_encodings=None, @@ -157,8 +157,13 @@ class BeautifulSoup(Tag): builder = builder_class() if not (original_features == builder.NAME or original_features in builder.ALTERNATE_NAMES): + if builder.is_xml: + markup_type = "XML" + else: + markup_type = "HTML" warnings.warn(self.NO_PARSER_SPECIFIED_WARNING % dict( - parser=builder.NAME)) + parser=builder.NAME, + markup_type=markup_type)) self.builder = builder self.is_xml = builder.is_xml diff --git a/bs4/builder/_lxml.py b/bs4/builder/_lxml.py index 2e33386..9e8f88f 100644 --- a/bs4/builder/_lxml.py +++ b/bs4/builder/_lxml.py @@ -31,6 +31,7 @@ class LXMLTreeBuilderForXML(TreeBuilder): is_xml = True NAME = "lxml-xml" + ALTERNATE_NAMES = ["xml"] # Well, it's permissive by XML parser standards. features = [NAME, LXML, XML, FAST, PERMISSIVE] |