Last active
July 26, 2016 18:21
-
-
Save derofim/517b60c637dc2d8e0f680610ffd8722f to your computer and use it in GitHub Desktop.
Examples gumbo-query
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#include <iostream> | |
#include <Windows.h> | |
#include "Document.h" | |
#include "Node.h" | |
int main() | |
{ | |
SetConsoleOutputCP(65001); | |
{ | |
std::cout << "Example: \"h1 a\" to find all a tags in h1" << std::endl; | |
std::string page("<html><div><span>1\n</span>2\n</div><h1><a>some link</a></h1><h1><a>other link</a></h1><a>no link</a></html>"); | |
CDocument doc; | |
doc.parse(page.c_str()); | |
CSelection c = doc.find("h1 a"); | |
for (int i = 0; i < c.nodeNum(); i++) { | |
std::cout << c.nodeAt(i).text() << std::endl; | |
} | |
} | |
std::cout << "==========" << std::endl; | |
{ | |
std::cout << "Example: \"div\" to find all div tags" << std::endl; | |
std::string page = "<html><div><span>1\n</span>2\n</div><br/></html>"; | |
CDocument doc; | |
doc.parse(page.c_str()); | |
CSelection c = doc.find("div"); | |
CNode pNode = c.nodeAt(0); | |
std::string content = page.substr(pNode.startPos(), pNode.endPos() - pNode.startPos()); | |
std::cout << content << std::endl; | |
// Clears subtags: | |
std::cout << "--- OR ---" << std::endl; | |
for (int i = 0; i < c.nodeNum(); i++) { | |
std::cout << c.nodeAt(i).text() << std::endl; | |
} | |
} | |
// Example: "h1 a.special" to find a tags with class="special" | |
// Example: "span[id='spid'][class='spcls']" to find span tags with id='spid' and class='spcls' | |
std::cout << "==========" << std::endl; | |
{ | |
std::cout << "Example: inner find" << std::endl; | |
std::string page = "<html><div>outer\n<div>inner\n<h1>title\n</h1></div></div></html>"; | |
CDocument doc; | |
doc.parse(page.c_str()); | |
CSelection outer = doc.find("div div"); | |
CNode pNode = outer.nodeAt(0); | |
CSelection c = outer.find("h1"); | |
for (int i = 0; i < c.nodeNum(); i++) { | |
std::cout << c.nodeAt(i).text() << std::endl; | |
} | |
} | |
std::cout << "==========" << std::endl; | |
{ | |
std::cout << "Example: node manipulation" << std::endl; | |
std::string page = "<html><div>outer\n<div class=\"cls\">inner\n<h1>title\n</h1></div></div></html>"; | |
CDocument doc; | |
doc.parse(page.c_str()); | |
CSelection c = doc.find("div"); | |
for (int i = 0; i < c.nodeNum(); i++) | |
{ | |
if (!c.nodeAt(i).valid()) continue; | |
std::cout << "ownText(): " << c.nodeAt(i).ownText() << std::endl; // ignores text in subtags ;) | |
std::cout << "parent().tag(): " << c.nodeAt(i).parent().tag() << std::endl; // get parent tag name | |
std::cout << "class: " << c.nodeAt(i).attribute("class") << std::endl; // get class name | |
} | |
} | |
std::getchar(); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment