html::parser p;
html::node_ptr node = p.parse(R"( <!DOCTYPE html><body><div attr="val">text</div><!--comment--></body>)" // `parse` method returns root node of type html::node_t::noneassert (node->type_node == html::node_t ::none);
assert (node->at (0 )->type_node == html::node_t::doctype);
assert (node->at (1 )->type_node == html::node_t::tag);
assert (node->at (1 )->at(0 )->at(0 )->type_node == html::node_t::text);
assert (node->at (1 )->at(1 )->type_node == html::node_t::comment);
std::cout << " Number of child elements: " size () << std::endl << std::endl; // 2" Loop through child nodes: " for (auto & n : *(node->at (1 ))) {
std::cout << n->to_html () << std::endl;
}
std::cout << std::endl;
std::cout << " Get node properties: " " DOCTYPE name: " at (0 )->content << std::endl; // html" BODY tag: " at (1 )->tag_name << std::endl; // body" Attr value: " at (1 )->at(0 )->get_attr(" attr" // val" Text node: " at (1 )->at(0 )->at(0 )->content << std::endl; // text" Comment: " at (1 )->at(1 )->content << std::endl; // comment Find nodes using select method List of available selectors
html::parser p;
html::node_ptr node = p.parse(R"( <div id="my_id"><p class="my_class"></p></div>)" select (" div#my_id p.my_class" for (auto elem : selected) {
std::cout << elem->to_html () << std::endl;
} Access nodes using callback (called when the document is parsed) html::parser p;
p.set_callback(" meta[http-equiv='Content-Type'][content*='charset=']" if (n.type_node == html::node_t ::tag && n.type_tag == html::tag_t ::open ) {
std::cout << " Callback with selector to filter elements:" to_html () << std::endl << std::endl;
}
});
p.set_callback([](html::node& n) {
if (n.type_node == html::node_t ::tag && n.type_tag == html::tag_t ::open && n.tag_name == " meta" if (n.get_attr (" http-equiv" " Content-Type" get_attr (" content" find (" charset=" " Callback without selector:" to_html () << std::endl;
}
}
});
p.parse(R"( <head><title>Title</title><meta http-equiv="Content-Type" content="text/html; charset=utf-8" /></head>)" std::cout << " Search `li` tags which not in `ol`:" " <ul><li>li1</li><li>li2</li></ul><ol><li>li</li></ol>" walk ([](html::node& n) {
if (n.type_node == html::node_t ::tag && n.tag_name == " ol" return false ; // not scan child tagsif (n.type_node == html::node_t ::tag && n.tag_name == " li" to_html () << std::endl;
}
return true ; // scan child tags html::parser p;
// Callback to handle errorserr_t e, html::node& n) {
if (e == html::err_t ::tag_not_closed) {
std::cout << " Tag not closed: " to_html (' ' false );
std::string msg;
html::node* current = &n;
while (current->get_parent ()) {
msg.insert (0 , " " tag_name );
current = current->get_parent ();
}
msg.insert (0 , " \n Path:" " <div><p><a></p></div>" html::parser p;
html::node_ptr node = p.parse(" <ul><li>li1</li><li>li2</li></ul><ol><li>li</li></ol>" // method takes two arguments, the indentation character and whether to output child elements (tabulation and true by default)to_html (' ' true ) << std::endl; Print text content of a node html::parser p;
html::node_ptr node = p.parse(" <div><p><b>First</b> p</p><p><i>Second</i> p</p>Text<br />Text</div>" " Print text with line breaks preserved:" to_text () << std::endl << std::endl;
std::cout << " Print text with line breaks replaced with spaces:" to_text (true ) << std::endl; std::cout << " Using helpers:" node_t ::tag, " div" node_t ::text, " Link:" node_t ::tag, " br" node_t ::tag, " a" " href" " https://github.com/" " class" " a_class" node_t ::text, " Github.com" " Without helpers:" node_t ::tag;
div.tag_name = " div" node_t ::text;
text.content = " Link:" node_t ::tag;
br.tag_name = " br" true ;
div.append(br);
html::node a;
a.type_node = html::node_t ::tag;
a.tag_name = " a" " href" " https://github.com/" " class" " a_class" node_t ::text;
a_text.content = " Github.com"
Selector example
Description
select
callback
*
all elements
√
√
div
tag name
√
√
#id1
id="id1"
√
√
.class1
class="class1"
√
√
.class1.class2
class="class1 class2"
√
√
:first
first element
√
√
:last
last element
√
-
:eq(3)
element index = 3 (starts from 0)
√
√
:gt(3)
element index > 3 (starts from 0)
√
√
:lt(3)
element index < 3 (starts from 0)
√
√
[attr]
element that have attribute "attr"
√
√
[attr='val']
attribute is equal to "val"
√
√
[attr!='val']
attribute is not equal to "val" or does not exist
√
√
[attr^='http:']
attribute starts with "http:"
√
√
[attr$='.jpeg']
attribute ends with ".jpeg"
√
√
[attr*='/path/']
attribute contains "/path/"
√
√
[attr~='flower']
attribute contains word "flower"
√
√
[attr|='en']
attribute equal to "en" or starting with "en-"
√
√
div#id1.class1[attr='val']
element that matches all of these selectors
√
√
p,div
element that matches any of these selectors
√
√
div p
all <p> elements inside <div> elements
√
-
div>p
all <p> elements where the parent is a <div> element
√
-
div div>p>i
combination of nested selectors
√
-
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent