def get_text(self, endat=None):
"""Get some text.
endat: stop reading text at this tag (the tag is included in the
returned text); endtag is a tuple (type, name) where type is
"starttag", "endtag" or "startendtag", and name is the element name of
the tag (element names must be given in lower case)
If endat is not given, .get_text() will stop at the next opening or
closing tag, or when there are no more tokens (no exception is raised).
Note that .get_text() includes the text representation (if any) of the
opening tag, but pushes the opening tag back onto the stack. As a
result, if you want to call .get_text() again, you need to call
.get_tag() first (unless you want an empty string returned when you
next call .get_text()).
Entity references are translated using the value of the entitydefs
constructor argument (a mapping from names to characters like that
provided by the standard module htmlentitydefs). Named entity
references that are not in this mapping are left unchanged.
The textify attribute is used to translate opening tags into text: see
the class docstring.
"""
text = []
tok = None
while True:
try:
tok = self.get_token()
except NoMoreTokensError:
# unget last token (not the one we just failed to get)
if tok:
self.unget_token(tok)
break
if tok.type == "data":
text.append(tok.data)
elif tok.type == "entityref":
t = unescape("&%s;" % tok.data, self._entitydefs,
self.encoding)
text.append(t)
elif tok.type == "charref":
t = unescape_charref(tok.data, self.encoding)
text.append(t)
elif tok.type in ["starttag", "endtag", "startendtag"]:
tag_name = tok.data
if tok.type in ["starttag", "startendtag"]:
alt = self.textify.get(tag_name)
if alt is not None:
if callable(alt):
text.append(alt(tok))
elif tok.attrs is not None:
for k, v in tok.attrs:
if k == alt:
text.append(v)
text.append("[%s]" % tag_name.upper())
if endat is None or endat == (tok.type, tag_name):
self.unget_token(tok)
break
return "".join(text)
def get_text(self, endat=None):
"""Get some text.
endat: stop reading text at this tag (the tag is included in the
returned text); endtag is a tuple (type, name) where type is
"starttag", "endtag" or "startendtag", and name is the element name of
the tag (element names must be given in lower case)
If endat is not given, .get_text() will stop at the next opening or
closing tag, or when there are no more tokens (no exception is raised).
Note that .get_text() includes the text representation (if any) of the
opening tag, but pushes the opening tag back onto the stack. As a
result, if you want to call .get_text() again, you need to call
.get_tag() first (unless you want an empty string returned when you
next call .get_text()).
Entity references are translated using the value of the entitydefs
constructor argument (a mapping from names to characters like that
provided by the standard module htmlentitydefs). Named entity
references that are not in this mapping are left unchanged.
The textify attribute is used to translate opening tags into text: see
the class docstring.
"""
text = []
tok = None
while 1:
try:
tok = self.get_token()
except NoMoreTokensError:
# unget last token (not the one we just failed to get)
if tok: self.unget_token(tok)
break
if tok.type == "data":
text.append(tok.data)
elif tok.type == "entityref":
t = unescape("&%s;"%tok.data, self._entitydefs, self.encoding)
text.append(t)
elif tok.type == "charref":
t = unescape_charref(tok.data, self.encoding)
text.append(t)
elif tok.type in ["starttag", "endtag", "startendtag"]:
tag_name = tok.data
if tok.type in ["starttag", "startendtag"]:
alt = self.textify.get(tag_name)
if alt is not None:
if callable(alt):
text.append(alt(tok))
elif tok.attrs is not None:
for k, v in tok.attrs:
if k == alt:
text.append(v)
text.append("[%s]" % tag_name.upper())
if endat is None or endat == (tok.type, tag_name):
self.unget_token(tok)
break
return "".join(text)
def unescape_attr(self, name):
#debug("%s", name)
return unescape(name, self._entitydefs, self._encoding)
def handle_entityref(self, name):
#debug("%s", name)
self.handle_data(unescape(
'&%s;' % name, self._entitydefs, self._encoding))
def unescape_attr(self, name):
return unescape(name, self._entitydefs, self.encoding)
def unescape_attr(self, name):
return unescape(name, self._entitydefs, self.encoding)