feedparser.py

来自「Harvestman-最新版本」· Python 代码 · 共 1,630 行 · 第 1/5 页

    def _start_prodlink(self, attrsD):
        self.pushContent('content', attrsD, 'text/html', 1)

    def _start_body(self, attrsD):
        self.pushContent('content', attrsD, 'application/xhtml+xml', 1)
    _start_xhtml_body = _start_body

    def _start_content_encoded(self, attrsD):
        self.pushContent('content', attrsD, 'text/html', 1)
    _start_fullitem = _start_content_encoded

    def _end_content(self):
        copyToDescription = self.mapContentType(self.contentparams.get('type')) in (['text/plain'] + self.html_types)
        value = self.popContent('content')
        if copyToDescription:
            self._save('description', value)
    _end_body = _end_content
    _end_xhtml_body = _end_content
    _end_content_encoded = _end_content
    _end_fullitem = _end_content
    _end_prodlink = _end_content

    def _start_itunes_image(self, attrsD):
        self.push('itunes_image', 0)
        self._getContext()['image'] = FeedParserDict({'href': attrsD.get('href')})
    _start_itunes_link = _start_itunes_image
        
    def _end_itunes_block(self):
        value = self.pop('itunes_block', 0)
        self._getContext()['itunes_block'] = (value == 'yes') and 1 or 0

    def _end_itunes_explicit(self):
        value = self.pop('itunes_explicit', 0)
        self._getContext()['itunes_explicit'] = (value == 'yes') and 1 or 0

if _XML_AVAILABLE:
    class _StrictFeedParser(_FeedParserMixin, xml.sax.handler.ContentHandler):
        def __init__(self, baseuri, baselang, encoding):
            if _debug: sys.stderr.write('trying StrictFeedParser\n')
            xml.sax.handler.ContentHandler.__init__(self)
            _FeedParserMixin.__init__(self, baseuri, baselang, encoding)
            self.bozo = 0
            self.exc = None
        
        def startPrefixMapping(self, prefix, uri):
            self.trackNamespace(prefix, uri)
        
        def startElementNS(self, name, qname, attrs):
            namespace, localname = name
            lowernamespace = str(namespace or '').lower()
            if lowernamespace.find('backend.userland.com/rss') <> -1:
                # match any backend.userland.com namespace
                namespace = 'http://backend.userland.com/rss'
                lowernamespace = namespace
            if qname and qname.find(':') > 0:
                givenprefix = qname.split(':')[0]
            else:
                givenprefix = None
            prefix = self._matchnamespaces.get(lowernamespace, givenprefix)
            if givenprefix and (prefix == None or (prefix == '' and lowernamespace == '')) and not self.namespacesInUse.has_key(givenprefix):
                    raise UndeclaredNamespace, "'%s' is not associated with a namespace" % givenprefix
            if prefix:
                localname = prefix + ':' + localname
            localname = str(localname).lower()
            if _debug: sys.stderr.write('startElementNS: qname = %s, namespace = %s, givenprefix = %s, prefix = %s, attrs = %s, localname = %s\n' % (qname, namespace, givenprefix, prefix, attrs.items(), localname))

            # qname implementation is horribly broken in Python 2.1 (it
            # doesn't report any), and slightly broken in Python 2.2 (it
            # doesn't report the xml: namespace). So we match up namespaces
            # with a known list first, and then possibly override them with
            # the qnames the SAX parser gives us (if indeed it gives us any
            # at all).  Thanks to MatejC for helping me test this and
            # tirelessly telling me that it didn't work yet.
            attrsD = {}
            for (namespace, attrlocalname), attrvalue in attrs._attrs.items():
                lowernamespace = (namespace or '').lower()
                prefix = self._matchnamespaces.get(lowernamespace, '')
                if prefix:
                    attrlocalname = prefix + ':' + attrlocalname
                attrsD[str(attrlocalname).lower()] = attrvalue
            for qname in attrs.getQNames():
                attrsD[str(qname).lower()] = attrs.getValueByQName(qname)
            self.unknown_starttag(localname, attrsD.items())

        def characters(self, text):
            self.handle_data(text)

        def endElementNS(self, name, qname):
            namespace, localname = name
            lowernamespace = str(namespace or '').lower()
            if qname and qname.find(':') > 0:
                givenprefix = qname.split(':')[0]
            else:
                givenprefix = ''
            prefix = self._matchnamespaces.get(lowernamespace, givenprefix)
            if prefix:
                localname = prefix + ':' + localname
            localname = str(localname).lower()
            self.unknown_endtag(localname)

        def error(self, exc):
            self.bozo = 1
            self.exc = exc
            
        def fatalError(self, exc):
            self.error(exc)
            raise exc

class _BaseHTMLProcessor(sgmllib.SGMLParser):
    elements_no_end_tag = ['area', 'base', 'basefont', 'br', 'col', 'frame', 'hr',
      'img', 'input', 'isindex', 'link', 'meta', 'param']
    
    def __init__(self, encoding):
        self.encoding = encoding
        if _debug: sys.stderr.write('entering BaseHTMLProcessor, encoding=%s\n' % self.encoding)
        sgmllib.SGMLParser.__init__(self)
        
    def reset(self):
        self.pieces = []
        sgmllib.SGMLParser.reset(self)

    def _shorttag_replace(self, match):
        tag = match.group(1)
        if tag in self.elements_no_end_tag:
            return '<' + tag + ' />'
        else:
            return '<' + tag + '></' + tag + '>'
        
    def feed(self, data):
        data = re.compile(r'<!((?!DOCTYPE|--|\[))', re.IGNORECASE).sub(r'&lt;!\1', data)
        #data = re.sub(r'<(\S+?)\s*?/>', self._shorttag_replace, data) # bug [ 1399464 ] Bad regexp for _shorttag_replace
        data = re.sub(r'<([^<\s]+?)\s*/>', self._shorttag_replace, data) 
        data = data.replace('&#39;', "'")
        data = data.replace('&#34;', '"')
        if self.encoding and type(data) == type(u''):
            data = data.encode(self.encoding)
        sgmllib.SGMLParser.feed(self, data)

    def normalize_attrs(self, attrs):
        # utility method to be called by descendants
        attrs = [(k.lower(), v) for k, v in attrs]
        attrs = [(k, k in ('rel', 'type') and v.lower() or v) for k, v in attrs]
        return attrs

    def unknown_starttag(self, tag, attrs):
        # called for each start tag
        # attrs is a list of (attr, value) tuples
        # e.g. for <pre class='screen'>, tag='pre', attrs=[('class', 'screen')]
        if _debug: sys.stderr.write('_BaseHTMLProcessor, unknown_starttag, tag=%s\n' % tag)
        uattrs = []
        # thanks to Kevin Marks for this breathtaking hack to deal with (valid) high-bit attribute values in UTF-8 feeds
        for key, value in attrs:
            if type(value) != type(u''):
                value = unicode(value, self.encoding)
            uattrs.append((unicode(key, self.encoding), value))
        strattrs = u''.join([u' %s="%s"' % (key, value) for key, value in uattrs]).encode(self.encoding)
        if tag in self.elements_no_end_tag:
            self.pieces.append('<%(tag)s%(strattrs)s />' % locals())
        else:
            self.pieces.append('<%(tag)s%(strattrs)s>' % locals())

    def unknown_endtag(self, tag):
        # called for each end tag, e.g. for </pre>, tag will be 'pre'
        # Reconstruct the original end tag.
        if tag not in self.elements_no_end_tag:
            self.pieces.append("</%(tag)s>" % locals())

    def handle_charref(self, ref):
        # called for each character reference, e.g. for '&#160;', ref will be '160'
        # Reconstruct the original character reference.
        self.pieces.append('&#%(ref)s;' % locals())
        
    def handle_entityref(self, ref):
        # called for each entity reference, e.g. for '&copy;', ref will be 'copy'
        # Reconstruct the original entity reference.
        self.pieces.append('&%(ref)s;' % locals())

    def handle_data(self, text):
        # called for each block of plain text, i.e. outside of any tag and
        # not containing any character or entity references
        # Store the original text verbatim.
        if _debug: sys.stderr.write('_BaseHTMLProcessor, handle_text, text=%s\n' % text)
        self.pieces.append(text)
        
    def handle_comment(self, text):
        # called for each HTML comment, e.g. <!-- insert Javascript code here -->
        # Reconstruct the original comment.
        self.pieces.append('<!--%(text)s-->' % locals())
        
    def handle_pi(self, text):
        # called for each processing instruction, e.g. <?instruction>
        # Reconstruct original processing instruction.
        self.pieces.append('<?%(text)s>' % locals())

    def handle_decl(self, text):
        # called for the DOCTYPE, if present, e.g.
        # <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
        #     "http://www.w3.org/TR/html4/loose.dtd">
        # Reconstruct original DOCTYPE
        self.pieces.append('<!%(text)s>' % locals())
        
    _new_declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9:]*\s*').match
    def _scan_name(self, i, declstartpos):
        rawdata = self.rawdata
        n = len(rawdata)
        if i == n:
            return None, -1
        m = self._new_declname_match(rawdata, i)
        if m:
            s = m.group()
            name = s.strip()
            if (i + len(s)) == n:
                return None, -1  # end of buffer
            return name.lower(), m.end()
        else:
            self.handle_data(rawdata)
#            self.updatepos(declstartpos, i)
            return None, -1

    def output(self):
        '''Return processed HTML as a single string'''
        return ''.join([str(p) for p in self.pieces])

class _LooseFeedParser(_FeedParserMixin, _BaseHTMLProcessor):
    def __init__(self, baseuri, baselang, encoding):
        sgmllib.SGMLParser.__init__(self)
        _FeedParserMixin.__init__(self, baseuri, baselang, encoding)

    def decodeEntities(self, element, data):
        data = data.replace('&#60;', '&lt;')
        data = data.replace('&#x3c;', '&lt;')
        data = data.replace('&#62;', '&gt;')
        data = data.replace('&#x3e;', '&gt;')
        data = data.replace('&#38;', '&amp;')
        data = data.replace('&#x26;', '&amp;')
        data = data.replace('&#34;', '&quot;')
        data = data.replace('&#x22;', '&quot;')
        data = data.replace('&#39;', '&apos;')
        data = data.replace('&#x27;', '&apos;')
        if self.contentparams.has_key('type') and not self.contentparams.get('type', 'xml').endswith('xml'):
            data = data.replace('&lt;', '<')
            data = data.replace('&gt;', '>')
            data = data.replace('&amp;', '&')
            data = data.replace('&quot;', '"')
            data = data.replace('&apos;', "'")
        return data
        
class _RelativeURIResolver(_BaseHTMLProcessor):
    relative_uris = [('a', 'href'),
                     ('applet', 'codebase'),
                     ('area', 'href'),
                     ('blockquote', 'cite'),
                     ('body', 'background'),
                     ('del', 'cite'),
                     ('form', 'action'),
                     ('frame', 'longdesc'),
                     ('frame', 'src'),
                     ('iframe', 'longdesc'),
                     ('iframe', 'src'),
                     ('head', 'profile'),
                     ('img', 'longdesc'),
                     ('img', 'src'),
                     ('img', 'usemap'),
                     ('input', 'src'),
                     ('input', 'usemap'),
                     ('ins', 'cite'),
                     ('link', 'href'),
                     ('object', 'classid'),
                     ('object', 'codebase'),
                     ('object', 'data'),
                     ('object', 'usemap'),
                     ('q', 'cite'),
                     ('script', 'src')]

    def __init__(self, baseuri, encoding):
        _BaseHTMLProcessor.__init__(self, encoding)
        self.baseuri = baseuri

    def resolveURI(self, uri):
        return _urljoin(self.baseuri, uri)
    
    def unknown_starttag(self, tag, attrs):
        attrs = self.normalize_attrs(attrs)
        attrs = [(key, ((tag, key) in self.relative_uris) and self.resolveURI(value) or value) for key, value in attrs]
        _BaseHTMLProcessor.unknown_starttag(self, tag, attrs)
        
def _resolveRelativeURIs(htmlSource, baseURI, encoding):
    if _debug: sys.stderr.write('entering _resolveRelativeURIs\n')
    p = _RelativeURIResolver(baseURI, encoding)
    p.feed(htmlSource)
    return p.output()

class _HTMLSanitizer(_BaseHTMLProcessor):
    acceptable_elements = ['a', 'abbr', 'acronym', 'address', 'area', 'b', 'big',
      'blockquote', 'br', 'button', 'caption', 'center', 'cite', 'code', 'col',
      'colgroup', 'dd', 'del', 'dfn', 'dir', 'div', 'dl', 'dt', 'em', 'fieldset',
      'font', 'form', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'input',
      'ins', 'kbd', 'label', 'legend', 'li', 'map', 'menu', 'ol', 'optgroup',
      'option', 'p', 'pre', 'q', 's', 'samp', 'select', 'small', 'span', 'strike',
      'strong', 'sub', 'sup', 'table', 'tbody', 'td', 'textarea', 'tfoot', 'th',
      'thead', 'tr', 'tt', 'u', 'ul', 'var']

    acceptable_attributes = ['abbr', 'accept', 'accept-charset', 'accesskey',
      'action', 'align', 'alt', 'axis', 'border', 'cellpadding', 'cellspacing',
      'char', 'charoff', 'charset', 'checked', 'cite', 'class', 'clear', 'cols',
      'colspan', 'color', 'compact', 'coords', 'datetime', 'dir', 'disabled',
      'enctype', 'for', 'frame', 'headers', 'height', 'href', 'hreflang', 'hspace',
      'id', 'ismap', 'label', 'lang', 'longdesc', 'maxlength', 'media', 'method',
      'multiple', 'name', 'nohref', 'noshade', 'nowrap', 'prompt', 'readonly',
      'rel', 'rev', 'rows', 'rowspan', 'rules', 'scope', 'selected', 'shape', 'size',
      'span', 'src', 'start', 'summary', 'tabindex', 'target', 'title', 'type',
      'usemap', 'valign', 'value', 'vspace', 'width']

    unacceptable_elements_with_end_tag = ['script', 'applet']

    def reset(self):
        _BaseHTMLProcessor.reset(self)
        self.unacceptablestack = 0
        
    def unknown_starttag(self, tag, attrs):
        if not tag in self.acceptable_elements:
            if tag in self.unacceptable_elements_with_end_tag:
                self.unacceptablestack += 1
            return
        attrs = self.normalize_attrs(attrs)
        attr