BeautifulSoup::HTMLParserBuilder Class Reference

Inherits HTMLParser::HTMLParser, and HTMLParser::HTMLParser.

List of all members.

Public Member Functions
def	__init__
def	__init__
def	handle_charref
def	handle_charref
def	handle_comment
def	handle_comment
def	handle_data
def	handle_data
def	handle_decl
def	handle_decl
def	handle_endtag
def	handle_endtag
def	handle_entityref
def	handle_entityref
def	handle_pi
def	handle_pi
def	handle_starttag
def	handle_starttag
def	parse_declaration
def	parse_declaration
Public Attributes
	soup
Private Member Functions
def	_toStringSubclass
def	_toStringSubclass

---

Detailed Description

Definition at line 1005 of file BeautifulSoup.py.

---

Constructor & Destructor Documentation

def BeautifulSoup::HTMLParserBuilder::__init__	(		self,
			soup
	)

Definition at line 1007 of file BeautifulSoup.py.

                            :
        HTMLParser.__init__(self)
        self.soup = soup

def BeautifulSoup::HTMLParserBuilder::__init__	(		self,
			soup
	)

Definition at line 1007 of file BeautifulSoup.py.

                            :
        HTMLParser.__init__(self)
        self.soup = soup

---

Member Function Documentation

def BeautifulSoup::HTMLParserBuilder::_toStringSubclass	(		self,
			text,
			subclass
	)		[private]

Adds a certain piece of text to the tree as a NavigableString
subclass.

Definition at line 1025 of file BeautifulSoup.py.

                                               :
        """Adds a certain piece of text to the tree as a NavigableString
        subclass."""
        self.soup.endData()
        self.handle_data(text)
        self.soup.endData(subclass)

def BeautifulSoup::HTMLParserBuilder::_toStringSubclass	(		self,
			text,
			subclass
	)		[private]

Adds a certain piece of text to the tree as a NavigableString
subclass.

Definition at line 1025 of file BeautifulSoup.py.

                                               :
        """Adds a certain piece of text to the tree as a NavigableString
        subclass."""
        self.soup.endData()
        self.handle_data(text)
        self.soup.endData(subclass)

def BeautifulSoup::HTMLParserBuilder::handle_charref	(		self,
			ref
	)

Definition at line 1044 of file BeautifulSoup.py.

                                 :
        "Handle character references as data."
        if self.soup.convertEntities:
            data = unichr(int(ref))
        else:
            data = '&#%s;' % ref
        self.handle_data(data)

def BeautifulSoup::HTMLParserBuilder::handle_charref	(		self,
			ref
	)

Definition at line 1044 of file BeautifulSoup.py.

                                 :
        "Handle character references as data."
        if self.soup.convertEntities:
            data = unichr(int(ref))
        else:
            data = '&#%s;' % ref
        self.handle_data(data)

def BeautifulSoup::HTMLParserBuilder::handle_comment	(		self,
			text
	)

Definition at line 1040 of file BeautifulSoup.py.

                                  :
        "Handle comments as Comment objects."
        self._toStringSubclass(text, Comment)

def BeautifulSoup::HTMLParserBuilder::handle_comment	(		self,
			text
	)

Definition at line 1040 of file BeautifulSoup.py.

                                  :
        "Handle comments as Comment objects."
        self._toStringSubclass(text, Comment)

def BeautifulSoup::HTMLParserBuilder::handle_data	(		self,
			content
	)

Definition at line 1022 of file BeautifulSoup.py.

                                  :
        self.soup.handle_data(content)

def BeautifulSoup::HTMLParserBuilder::handle_data	(		self,
			content
	)

Definition at line 1022 of file BeautifulSoup.py.

                                  :
        self.soup.handle_data(content)

def BeautifulSoup::HTMLParserBuilder::handle_decl	(		self,
			data
	)

Definition at line 1095 of file BeautifulSoup.py.

                               :
        "Handle DOCTYPEs and the like as Declaration objects."
        self._toStringSubclass(data, Declaration)

def BeautifulSoup::HTMLParserBuilder::handle_decl	(		self,
			data
	)

Definition at line 1095 of file BeautifulSoup.py.

                               :
        "Handle DOCTYPEs and the like as Declaration objects."
        self._toStringSubclass(data, Declaration)

def BeautifulSoup::HTMLParserBuilder::handle_endtag	(		self,
			name
	)

Definition at line 1019 of file BeautifulSoup.py.

                                 :
        self.soup.unknown_endtag(name)

def BeautifulSoup::HTMLParserBuilder::handle_endtag	(		self,
			name
	)

Definition at line 1019 of file BeautifulSoup.py.

                                 :
        self.soup.unknown_endtag(name)

def BeautifulSoup::HTMLParserBuilder::handle_entityref	(		self,
			ref
	)

Handle entity references as data, possibly converting known
HTML and/or XML entity references to the corresponding Unicode
characters.

Definition at line 1052 of file BeautifulSoup.py.

                                   :
        """Handle entity references as data, possibly converting known
        HTML and/or XML entity references to the corresponding Unicode
        characters."""
        data = None
        if self.soup.convertHTMLEntities:
            try:
                data = unichr(name2codepoint[ref])
            except KeyError:
                pass

        if not data and self.soup.convertXMLEntities:
                data = self.soup.XML_ENTITIES_TO_SPECIAL_CHARS.get(ref)

        if not data and self.soup.convertHTMLEntities and \
            not self.soup.XML_ENTITIES_TO_SPECIAL_CHARS.get(ref):
                # TODO: We've got a problem here. We're told this is
                # an entity reference, but it's not an XML entity
                # reference or an HTML entity reference. Nonetheless,
                # the logical thing to do is to pass it through as an
                # unrecognized entity reference.
                #
                # Except: when the input is "&carol;" this function
                # will be called with input "carol". When the input is
                # "AT&T", this function will be called with input
                # "T". We have no way of knowing whether a semicolon
                # was present originally, so we don't know whether
                # this is an unknown entity or just a misplaced
                # ampersand.
                #
                # The more common case is a misplaced ampersand, so I
                # escape the ampersand and omit the trailing semicolon.
                data = "&%s" % ref
        if not data:
            # This case is different from the one above, because we
            # haven't already gone through a supposedly comprehensive
            # mapping of entities to Unicode characters. We might not
            # have gone through any mapping at all. So the chances are
            # very high that this is a real entity, and not a
            # misplaced ampersand.
            data = "&%s;" % ref
        self.handle_data(data)

def BeautifulSoup::HTMLParserBuilder::handle_entityref	(		self,
			ref
	)

Handle entity references as data, possibly converting known
HTML and/or XML entity references to the corresponding Unicode
characters.

Definition at line 1052 of file BeautifulSoup.py.

                                   :
        """Handle entity references as data, possibly converting known
        HTML and/or XML entity references to the corresponding Unicode
        characters."""
        data = None
        if self.soup.convertHTMLEntities:
            try:
                data = unichr(name2codepoint[ref])
            except KeyError:
                pass

        if not data and self.soup.convertXMLEntities:
                data = self.soup.XML_ENTITIES_TO_SPECIAL_CHARS.get(ref)

        if not data and self.soup.convertHTMLEntities and \
            not self.soup.XML_ENTITIES_TO_SPECIAL_CHARS.get(ref):
                # TODO: We've got a problem here. We're told this is
                # an entity reference, but it's not an XML entity
                # reference or an HTML entity reference. Nonetheless,
                # the logical thing to do is to pass it through as an
                # unrecognized entity reference.
                #
                # Except: when the input is "&carol;" this function
                # will be called with input "carol". When the input is
                # "AT&T", this function will be called with input
                # "T". We have no way of knowing whether a semicolon
                # was present originally, so we don't know whether
                # this is an unknown entity or just a misplaced
                # ampersand.
                #
                # The more common case is a misplaced ampersand, so I
                # escape the ampersand and omit the trailing semicolon.
                data = "&%s" % ref
        if not data:
            # This case is different from the one above, because we
            # haven't already gone through a supposedly comprehensive
            # mapping of entities to Unicode characters. We might not
            # have gone through any mapping at all. So the chances are
            # very high that this is a real entity, and not a
            # misplaced ampersand.
            data = "&%s;" % ref
        self.handle_data(data)

def BeautifulSoup::HTMLParserBuilder::handle_pi	(		self,
			text
	)

Handle a processing instruction as a ProcessingInstruction
object, possibly one with a %SOUP-ENCODING% slot into which an
encoding will be plugged later.

Definition at line 1032 of file BeautifulSoup.py.

                             :
        """Handle a processing instruction as a ProcessingInstruction
        object, possibly one with a %SOUP-ENCODING% slot into which an
        encoding will be plugged later."""
        if text[:3] == "xml":
            text = u"xml version='1.0' encoding='%SOUP-ENCODING%'"
        self._toStringSubclass(text, ProcessingInstruction)

def BeautifulSoup::HTMLParserBuilder::handle_pi	(		self,
			text
	)

Handle a processing instruction as a ProcessingInstruction
object, possibly one with a %SOUP-ENCODING% slot into which an
encoding will be plugged later.

Definition at line 1032 of file BeautifulSoup.py.

                             :
        """Handle a processing instruction as a ProcessingInstruction
        object, possibly one with a %SOUP-ENCODING% slot into which an
        encoding will be plugged later."""
        if text[:3] == "xml":
            text = u"xml version='1.0' encoding='%SOUP-ENCODING%'"
        self._toStringSubclass(text, ProcessingInstruction)

def BeautifulSoup::HTMLParserBuilder::handle_starttag	(		self,
			name,
			attrs
	)

Definition at line 1013 of file BeautifulSoup.py.

                                          :
        if name == 'meta':
            self.soup.extractCharsetFromMeta(attrs)
        else:
            self.soup.unknown_starttag(name, attrs)

def BeautifulSoup::HTMLParserBuilder::handle_starttag	(		self,
			name,
			attrs
	)

Definition at line 1013 of file BeautifulSoup.py.

                                          :
        if name == 'meta':
            self.soup.extractCharsetFromMeta(attrs)
        else:
            self.soup.unknown_starttag(name, attrs)

def BeautifulSoup::HTMLParserBuilder::parse_declaration	(		self,
			i
	)

Treat a bogus SGML declaration as raw data. Treat a CDATA
declaration as a CData object.

Definition at line 1099 of file BeautifulSoup.py.

                                  :
        """Treat a bogus SGML declaration as raw data. Treat a CDATA
        declaration as a CData object."""
        j = None
        if self.rawdata[i:i+9] == '<![CDATA[':
             k = self.rawdata.find(']]>', i)
             if k == -1:
                 k = len(self.rawdata)
             data = self.rawdata[i+9:k]
             j = k+3
             self._toStringSubclass(data, CData)
        else:
            try:
                j = HTMLParser.parse_declaration(self, i)
            except HTMLParseError:
                toHandle = self.rawdata[i:]
                self.handle_data(toHandle)
                j = i + len(toHandle)
        return j

def BeautifulSoup::HTMLParserBuilder::parse_declaration	(		self,
			i
	)

Treat a bogus SGML declaration as raw data. Treat a CDATA
declaration as a CData object.

Definition at line 1099 of file BeautifulSoup.py.

                                  :
        """Treat a bogus SGML declaration as raw data. Treat a CDATA
        declaration as a CData object."""
        j = None
        if self.rawdata[i:i+9] == '<![CDATA[':
             k = self.rawdata.find(']]>', i)
             if k == -1:
                 k = len(self.rawdata)
             data = self.rawdata[i+9:k]
             j = k+3
             self._toStringSubclass(data, CData)
        else:
            try:
                j = HTMLParser.parse_declaration(self, i)
            except HTMLParseError:
                toHandle = self.rawdata[i:]
                self.handle_data(toHandle)
                j = i + len(toHandle)
        return j

---

Member Data Documentation

BeautifulSoup::HTMLParserBuilder::soup

Definition at line 1007 of file BeautifulSoup.py.