2017-11-20 16:38:10 +08:00
|
|
|
#include <QCoreApplication>
|
|
|
|
|
|
|
|
|
|
#include <GumboQueryDocument.h>
|
|
|
|
|
#include <GumboQuerySelection.h>
|
|
|
|
|
#include <GumboQueryNode.h>
|
|
|
|
|
|
2017-11-22 19:22:53 +08:00
|
|
|
#include "stdlib.h"
|
|
|
|
|
#include "stdio.h"
|
|
|
|
|
|
2017-11-20 16:38:10 +08:00
|
|
|
void test_parser()
|
|
|
|
|
{
|
2017-11-22 19:22:53 +08:00
|
|
|
std::string page("<h1><a>wrong link</a><a class=\"special\"\\>some link</a></h1>");
|
2017-11-20 16:38:10 +08:00
|
|
|
GumboQueryDocument doc;
|
2017-11-22 19:22:53 +08:00
|
|
|
doc.parse(page.c_str());
|
2017-11-20 16:38:10 +08:00
|
|
|
|
2017-11-22 19:22:53 +08:00
|
|
|
GumboQuerySelection c = doc.find("h1 a.special");
|
|
|
|
|
GumboQueryNode 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());
|
2017-11-20 16:38:10 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void test_html()
|
|
|
|
|
{
|
|
|
|
|
std::string page = "<html><div><span>1\n</span>2\n</div></html>";
|
|
|
|
|
GumboQueryDocument doc;
|
2017-11-22 19:22:53 +08:00
|
|
|
doc.parse(page.c_str());
|
|
|
|
|
GumboQueryNode pNode = doc.find("div").nodeAt(0);
|
|
|
|
|
std::string content = page.substr(pNode.startPos(), pNode.endPos() - pNode.startPos());
|
|
|
|
|
printf("Node: #%s#\n", content.c_str());
|
2017-11-20 16:38:10 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void test_escape()
|
|
|
|
|
{
|
|
|
|
|
std::string page = "<html><div><span id=\"that's\">1\n</span>2\n</div></html>";
|
|
|
|
|
GumboQueryDocument doc;
|
2017-11-22 19:22:53 +08:00
|
|
|
doc.parse(page.c_str());
|
|
|
|
|
GumboQueryNode 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());
|
2017-11-20 16:38:10 +08:00
|
|
|
}
|
|
|
|
|
|
2017-11-22 19:22:53 +08:00
|
|
|
int main(int argc, char* argv[])
|
2017-11-20 16:38:10 +08:00
|
|
|
{
|
2017-11-22 19:22:53 +08:00
|
|
|
QCoreApplication a(argc, argv);
|
2017-11-20 16:38:10 +08:00
|
|
|
test_parser();
|
|
|
|
|
test_html();
|
|
|
|
|
test_escape();
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
