c++解析html

https://github.com/cejutue/cjhtmlparser

 

基于gumbo-parser 和gumbo-query 改造成为了 可以适用 Windows和Linux的 html解析库, 原gumbo为google的开源c库, 且仅仅hi吃Linux.

编译: gumbo-parser 所有文件全部直接加入到工程直接编译即可

基本用法如下:

#pragma once
#include "stdafx.h"

#include "enumtest.cpp"

#include "gumbo-parser/Selector.h"

#include "gumbo-parser/Document.h"
#include "gumbo-parser/Selection.h"
#include "gumbo-parser/Node.h"

void test_parser() {
	std::string page("
wrong linksome link
");
	CDocument doc;
	doc.parse(page.c_str());

	CSelection c = doc.find("h1 a.special");
	CNode node = c.nodeAt(0);
	printf("Node: %s\n", node.text().c_str());
	std::string content = page.substr(node.startPos(), node.endPos() - node.startPos());
	printf("Node: %s\n", content.c_str());

}

void test_html() {
	std::string page = "
1\n2\n
";
	CDocument doc;
	doc.parse(page.c_str());
	CNode pNode = doc.find("div").nodeAt(0);
	std::string content = page.substr(pNode.startPos(), pNode.endPos() - pNode.startPos());
	printf("Node: #%s#\n", content.c_str());
}

void test_escape() {
	std::string page = "
1\n2\n
";
	CDocument doc;
	doc.parse(page.c_str());
	CNode pNode = doc.find("span[id=\"that's\"]").nodeAt(0);
	std::string content = page.substr(pNode.startPos(), pNode.endPos() - pNode.startPos());
	printf("Node: #%s#\n", content.c_str());
}

int main() {
	test_parser();
	test_html();
	test_escape();
}