void LinkExtractor::safeHandleStartTag(const std::string& tag_name,
attr_list_t& attrs, bool empty_element_tag)
{
LinkExtractor::link_tag_map_t::const_iterator _i;
std::string _attr;
std::string name = tag_name;
to_lower(name);
// Base should be treat separately
if ((name == "base") and (attrs.find("href") != attrs.end()) ) {
this->base = attrs["href"].str();
} else if ( name == "meta" ){
this->handleMetaTag(tag_name, attrs);
}
// Extract Links
// - Is this a tag link?
// - If so, is the corresponding attribute of this tag present?
_i = this->LINK_TAGS.find(name);
if ( (_i != this->LINK_TAGS.end()) and
( attrs.find( _attr = _i->second ) != attrs.end() ))
{
this->links.insert( attrs[_attr].str() );
}
}
void FindEncParser::handleProcessingInstruction(const std::string& name,
attr_list_t& attrs)
{
if ( name == "xml" and attrs.find("encoding") != attrs.end()) {
this->enc = attrs["encoding"].str();
this->enc = strip(this->enc);
throw CharsetDetectedException("Found in a Processing Instruction");
}
}
void FindEncParser::safeHandleStartTag(const std::string& name,
attr_list_t& attrs, bool empty_element_tag)
{
std::string val;
if ( name == "meta" and attrs.find("http-equiv") != attrs.end() ) {
val = attrs["http-equiv"].str();
to_lower(val);
if (val == "content-type" and attrs.find("content") != attrs.end() ) {
val = attrs["content"].str();
to_lower(val);
std::string charset = get_charset_from_content_type(val);
if (not charset.empty()) {
this->enc = strip(charset);
throw CharsetDetectedException("Found in a Meta Tag");
}
}
}
}
void LinkExtractor::handleMetaTag( const std::string& tag_name,
attr_list_t& attrs)
{
std::string value;
std::string content;
attr_list_t::const_iterator name_attr = attrs.find("name");
if (name_attr != attrs.end()){
value = name_attr->second.str();
to_lower(value);
if (value == "robots"){
if ( attrs.count("content") ) {
content = attrs["content"].str();
handleRobotsMetaContent(content);
}
}
}
}