def set_up_substitutions(self, tag):
# We are only interested in <meta> tags
if tag.name != 'meta':
return False
http_equiv = tag.get('http-equiv')
content = tag.get('content')
charset = tag.get('charset')
# We are interested in <meta> tags that say what encoding the
# document was originally in. This means HTML 5-style <meta>
# tags that provide the "charset" attribute. It also means
# HTML 4-style <meta> tags that provide the "content"
# attribute and have "http-equiv" set to "content-type".
#
# In both cases we will replace the value of the appropriate
# attribute with a standin object that can take on any
# encoding.
meta_encoding = None
if charset is not None:
# HTML 5 style:
# <meta charset="utf8">
meta_encoding = charset
tag['charset'] = CharsetMetaAttributeValue(charset)
elif (content is not None and http_equiv is not None
and http_equiv.lower() == 'content-type'):
# HTML 4 style:
# <meta http-equiv="content-type" content="text/html; charset=utf8">
tag['content'] = ContentMetaAttributeValue(content)
return (meta_encoding is not None)
def set_up_substitutions(self, tag):
"""Replace the declared encoding in a <meta> tag with a placeholder,
to be substituted when the tag is output to a string.
An HTML document may come in to Beautiful Soup as one
encoding, but exit in a different encoding, and the <meta> tag
needs to be changed to reflect this.
:param tag: A `Tag`
:return: Whether or not a substitution was performed.
"""
# We are only interested in <meta> tags
if tag.name != "meta":
return False
http_equiv = tag.get("http-equiv")
content = tag.get("content")
charset = tag.get("charset")
# We are interested in <meta> tags that say what encoding the
# document was originally in. This means HTML 5-style <meta>
# tags that provide the "charset" attribute. It also means
# HTML 4-style <meta> tags that provide the "content"
# attribute and have "http-equiv" set to "content-type".
#
# In both cases we will replace the value of the appropriate
# attribute with a standin object that can take on any
# encoding.
meta_encoding = None
if charset is not None:
# HTML 5 style:
# <meta charset="utf8">
meta_encoding = charset
tag["charset"] = CharsetMetaAttributeValue(charset)
elif (
content is not None
and http_equiv is not None
and http_equiv.lower() == "content-type"
):
# HTML 4 style:
# <meta http-equiv="content-type" content="text/html; charset=utf8">
tag["content"] = ContentMetaAttributeValue(content)
return meta_encoding is not None
def test_content_meta_attribute_value(self):
value = ContentMetaAttributeValue("text/html; charset=euc-jp")
self.assertEqual("text/html; charset=euc-jp", value)
self.assertEqual("text/html; charset=euc-jp", value.original_value)
self.assertEqual("text/html; charset=utf8", value.encode("utf8"))
def test_content_meta_attribute_value(self):
value = ContentMetaAttributeValue("text/html; charset=euc-jp")
self.assertEqual("text/html; charset=euc-jp", value)
self.assertEqual("text/html; charset=euc-jp", value.original_value)
self.assertEqual("text/html; charset=utf8", value.encode("utf8"))
def test_content_meta_attribute_value(self):
value = ContentMetaAttributeValue("text/html; charset=euc-jp")
assert "text/html; charset=euc-jp" == value
assert "text/html; charset=euc-jp" == value.original_value
assert "text/html; charset=utf8" == value.encode("utf8")
assert "text/html; charset=ascii" == value.encode("ascii")
