def _replace(match_obj):
original_str = match_obj.group(0)
digits, xdigits, name = map(_translate, match_obj.group(1, 3, 5))
if digits is not None:
return chr(int(digits))
elif xdigits is not None:
return chr(int(xdigits, base=16))
elif name is not None:
txt = name2txt.get(name, None)
if txt is None:
txt = name2txt.get(name + ';', original_str)
return txt
raise logic - error
def remove_html_tags(html):
# If we would want more speed, we could make these global
re_strip_tags = re.compile('<[^>]*>')
re_unicode_entities = re.compile(r'&#(\d{2,4});')
re_html_entities = re.compile('&(.{2,8});')
re_newline_tags = re.compile('(<br[^>]*>|<[/]?ul[^>]*>|</li>)', re.I)
re_listing_tags = re.compile('<li[^>]*>', re.I)
result = html
# Convert common HTML elements to their text equivalent
result = re_newline_tags.sub('\n', result)
result = re_listing_tags.sub('\n * ', result)
result = re.sub('<[Pp]>', '\n\n', result)
# Remove all HTML/XML tags from the string
result = re_strip_tags.sub('', result)
# Convert numeric XML entities to their unicode character
result = re_unicode_entities.sub(lambda x: chr(int(x.group(1))), result)
# Convert named HTML entities to their unicode character
result = re_html_entities.sub(
lambda x: str(entitydefs.get(x.group(1), ''), 'iso-8859-1'), result
)
# Convert more than two newlines to two newlines
result = re.sub('([\r\n]{2})([\r\n])+', '\\1', result)
return mark_safe(result.strip())
def remove_html_tags(html):
# If we would want more speed, we could make these global
re_strip_tags = re.compile('<[^>]*>')
re_unicode_entities = re.compile('&#(\d{2,4});')
re_html_entities = re.compile('&(.{2,8});')
re_newline_tags = re.compile('(<br[^>]*>|<[/]?ul[^>]*>|</li>)', re.I)
re_listing_tags = re.compile('<li[^>]*>', re.I)
result = html
# Convert common HTML elements to their text equivalent
result = re_newline_tags.sub('\n', result)
result = re_listing_tags.sub('\n * ', result)
result = re.sub('<[Pp]>', '\n\n', result)
# Remove all HTML/XML tags from the string
result = re_strip_tags.sub('', result)
# Convert numeric XML entities to their unicode character
result = re_unicode_entities.sub(lambda x: chr(int(x.group(1))), result)
# Convert named HTML entities to their unicode character
result = re_html_entities.sub(
lambda x: str(entitydefs.get(x.group(1), ''), 'iso-8859-1'), result
)
# Convert more than two newlines to two newlines
result = re.sub('([\r\n]{2})([\r\n])+', '\\1', result)
return mark_safe(result.strip())
def skippedEntity(self, name):
# Encoding?
content = html_entity_defs.get(name)
if not content:
raise RuntimeError("Unknown HTML entity &%s;" % name)
return self.characters(str(content))
def fixup(m):
text = m.group(0)
startswith = text.startswith
if startswith('<'):
return '' # ignore tags
if startswith('&'):
if startswith('&#'):
try:
if startswith('&#x'):
return chr(int(text[3:-1], 16))
else:
return chr(int(text[2:-1]))
except ValueError:
pass
else:
entity = htmlentitydefs.get(text[1:-1])
if entity:
if entity.startswith('&#'): # TODO: test this case
try:
return chr(int(entity[2:-1]))
except ValueError:
pass
else:
# return unicode(entity, "iso-8859-1")
return entity # TODO: encode ?
return text # Leave as is
def fix_up(m):
sub_text = m.group(0)
startswith = sub_text.startswith
if startswith('<'):
return '' # ignore tags
if startswith('&'):
if startswith('&#'):
try:
if startswith('&#x'):
return chr(int(sub_text[3:-1], 16))
else:
return chr(int(sub_text[2:-1]))
except ValueError:
pass
else:
entity = html_entities.get(sub_text[1:-1])
if entity:
# if entity.startswith('&#'):
# try:
# return chr(int(entity[2:-1]))
# except ValueError:
# pass
# else:
# return entity
return entity # TODO: encode ?
return sub_text # Leave as is
def convert_entity(m):
if m.group(1):
try:
return chr(int(m.group(2)))
except ValueError:
return m.group(0)
return entitydefs.get(m.group(2), m.group(0))
def process(self, html):
"""
Remove HTML tags from a string and replace numeric and
named entities with the corresponding character, so the
HTML text can be displayed in a simple text view.
"""
if html is None:
return None
# If we would want more speed, we could make these global
re_strip_tags = re.compile('<[^>]*>')
re_unicode_entities = re.compile('&#(\d{2,4});')
re_html_entities = re.compile('&(.{2,8});')
re_newline_tags = re.compile('(<br[^>]*>|<[/]?ul[^>]*>|</li>)', re.I)
re_listing_tags = re.compile('<li[^>]*>', re.I)
result = html
# Convert common HTML elements to their text equivalent
result = re_newline_tags.sub('\n', result)
result = re_listing_tags.sub('\n * ', result)
result = re.sub('<[Pp]>', '\n\n', result)
# Remove all HTML/XML tags from the string
result = re_strip_tags.sub('', result)
# Convert numeric XML entities to their unicode character
result = re_unicode_entities.sub(
lambda x: chr(int(x.group(1))),
result)
# Convert named HTML entities to their unicode character
result = re_html_entities.sub(
lambda x: str(entitydefs.get(x.group(1), ''), 'iso-8859-1'),
result)
# Convert more than two newlines to two newlines
result = re.sub('([\r\n]{2})([\r\n])+', '\\1', result)
return result.strip()
def process(self, html):
"""
Remove HTML tags from a string and replace numeric and
named entities with the corresponding character, so the
HTML text can be displayed in a simple text view.
"""
if html is None:
return None
# If we would want more speed, we could make these global
re_strip_tags = re.compile('<[^>]*>')
re_unicode_entities = re.compile('&#(\d{2,4});')
re_html_entities = re.compile('&(.{2,8});')
re_newline_tags = re.compile('(<br[^>]*>|<[/]?ul[^>]*>|</li>)', re.I)
re_listing_tags = re.compile('<li[^>]*>', re.I)
result = html
# Convert common HTML elements to their text equivalent
result = re_newline_tags.sub('\n', result)
result = re_listing_tags.sub('\n * ', result)
result = re.sub('<[Pp]>', '\n\n', result)
# Remove all HTML/XML tags from the string
result = re_strip_tags.sub('', result)
# Convert numeric XML entities to their unicode character
result = re_unicode_entities.sub(lambda x: chr(int(x.group(1))),
result)
# Convert named HTML entities to their unicode character
result = re_html_entities.sub(
lambda x: str(entitydefs.get(x.group(1), ''), 'iso-8859-1'),
result)
# Convert more than two newlines to two newlines
result = re.sub('([\r\n]{2})([\r\n])+', '\\1', result)
return result.strip()
