本文整理汇总了Python中bs4.dammit.contains_replacement_characters方法的典型用法代码示例。如果您正苦于以下问题：Python dammit.contains_replacement_characters方法的具体用法？Python dammit.contains_replacement_characters怎么用？Python dammit.contains_replacement_characters使用的例子？那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类bs4.dammit的用法示例。
在下文中一共展示了dammit.contains_replacement_characters方法的4个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: test_last_ditch_entity_replacement
# 需要导入模块: from bs4 import dammit [as 别名]
# 或者: from bs4.dammit import contains_replacement_characters [as 别名]
def test_last_ditch_entity_replacement(self):
# This is a UTF-8 document that contains bytestrings
# completely incompatible with UTF-8 (ie. encoded with some other
# encoding).
#
# Since there is no consistent encoding for the document,
# Unicode, Dammit will eventually encode the document as UTF-8
# and encode the incompatible characters as REPLACEMENT
# CHARACTER.
#
# If chardet is installed, it will detect that the document
# can be converted into ISO-8859-1 without errors. This happens
# to be the wrong encoding, but it is a consistent encoding, so the
# code we're testing here won't run.
#
# So we temporarily disable chardet if it's present.
doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
chardet = bs4.dammit.chardet_dammit
logging.disable(logging.WARNING)
try:
def noop(str):
return None
bs4.dammit.chardet_dammit = noop
dammit = UnicodeDammit(doc)
self.assertEqual(True, dammit.contains_replacement_characters)
self.assertTrue(u"\ufffd" in dammit.unicode_markup)
soup = BeautifulSoup(doc, "html.parser")
self.assertTrue(soup.contains_replacement_characters)
finally:
logging.disable(logging.NOTSET)
bs4.dammit.chardet_dammit = chardet 示例2: test_last_ditch_entity_replacement
# 需要导入模块: from bs4 import dammit [as 别名]
# 或者: from bs4.dammit import contains_replacement_characters [as 别名]
def test_last_ditch_entity_replacement(self):
# This is a UTF-8 document that contains bytestrings
# completely incompatible with UTF-8 (ie. encoded with some other
# encoding).
#
# Since there is no consistent encoding for the document,
# Unicode, Dammit will eventually encode the document as UTF-8
# and encode the incompatible characters as REPLACEMENT
# CHARACTER.
#
# If chardet is installed, it will detect that the document
# can be converted into ISO-8859-1 without errors. This happens
# to be the wrong encoding, but it is a consistent encoding, so the
# code we're testing here won't run.
#
# So we temporarily disable chardet if it's present.
doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
chardet = bs4.dammit.chardet
try:
bs4.dammit.chardet = None
with warnings.catch_warnings(record=True) as w:
dammit = UnicodeDammit(doc)
self.assertEqual(True, dammit.contains_replacement_characters)
self.assertTrue(u"\ufffd" in dammit.unicode_markup)
soup = BeautifulSoup(doc, "html.parser")
self.assertTrue(soup.contains_replacement_characters)
msg = w[0].message
self.assertTrue(isinstance(msg, UnicodeWarning))
self.assertTrue("Some characters could not be decoded" in str(msg))
finally:
bs4.dammit.chardet = chardet 示例3: test_last_ditch_entity_replacement
# 需要导入模块: from bs4 import dammit [as 别名]
# 或者: from bs4.dammit import contains_replacement_characters [as 别名]
def test_last_ditch_entity_replacement(self):
# This is a UTF-8 document that contains bytestrings
# completely incompatible with UTF-8 (ie. encoded with some other
# encoding).
#
# Since there is no consistent encoding for the document,
# Unicode, Dammit will eventually encode the document as UTF-8
# and encode the incompatible characters as REPLACEMENT
# CHARACTER.
#
# If chardet is installed, it will detect that the document
# can be converted into ISO-8859-1 without errors. This happens
# to be the wrong encoding, but it is a consistent encoding, so the
# code we're testing here won't run.
#
# So we temporarily disable chardet if it's present.
doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
chardet = bs4.dammit.chardet_dammit
logging.disable(logging.WARNING)
try:
def noop(str):
return None
bs4.dammit.chardet_dammit = noop
dammit = UnicodeDammit(doc)
self.assertEqual(True, dammit.contains_replacement_characters)
self.assertTrue("\ufffd" in dammit.unicode_markup)
soup = BeautifulSoup(doc, "html.parser")
self.assertTrue(soup.contains_replacement_characters)
finally:
logging.disable(logging.NOTSET)
bs4.dammit.chardet_dammit = chardet 示例4: test_last_ditch_entity_replacement
# 需要导入模块: from bs4 import dammit [as 别名]
# 或者: from bs4.dammit import contains_replacement_characters [as 别名]
def test_last_ditch_entity_replacement(self):
# This is a UTF-8 document that contains bytestrings
# completely incompatible with UTF-8 (ie. encoded with some other
# encoding).
#
# Since there is no consistent encoding for the document,
# Unicode, Dammit will eventually encode the document as UTF-8
# and encode the incompatible characters as REPLACEMENT
# CHARACTER.
#
# If chardet is installed, it will detect that the document
# can be converted into ISO-8859-1 without errors. This happens
# to be the wrong encoding, but it is a consistent encoding, so the
# code we're testing here won't run.
#
# So we temporarily disable chardet if it's present.
doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
chardet = bs4.dammit.chardet
try:
bs4.dammit.chardet = None
with warnings.catch_warnings(record=True) as w:
dammit = UnicodeDammit(doc)
self.assertEqual(True, dammit.contains_replacement_characters)
self.assertTrue("\ufffd" in dammit.unicode_markup)
soup = BeautifulSoup(doc, "html.parser")
self.assertTrue(soup.contains_replacement_characters)
msg = w[0].message
self.assertTrue(isinstance(msg, UnicodeWarning))
self.assertTrue("Some characters could not be decoded" in str(msg))
finally:
bs4.dammit.chardet = chardet