htmlquery's Introduction

htmlquery

Overview

htmlquery is an XPath query package for HTML, lets you extract data or evaluate from HTML documents by an XPath expression.

Changelogs

2019-02-04

#7 Removed deprecated FindEach() and FindEachWithBreak() methods.

2018-12-28

Avoid adding duplicate elements to list for Find() method. #6

Installation

$ go get github.com/antchfx/htmlquery

Getting Started

Load HTML document from URL.

doc, err := htmlquery.LoadURL("http://example.com/")

Load HTML document from string.

s := `<html>....</html>`
doc, err := htmlquery.Parse(strings.NewReader(s))

Find all A elements.

list := htmlquery.Find(doc, "//a")

Find all A elements that have `href` attribute.

list := range htmlquery.Find(doc, "//a[@href]")

Find all A elements and only get `href` attribute self.

list := range htmlquery.Find(doc, "//a/@href")

Find the third A element.

a := htmlquery.FindOne(doc, "//a[3]")

Evaluate the number of all IMG element.

expr, _ := xpath.Compile("count(//img)")
v := expr.Evaluate(htmlquery.CreateXPathNavigator(doc)).(float64)
fmt.Printf("total count is %f", v)

Quick Tutorial

func main() {
	doc, err := htmlquery.LoadURL("https://www.bing.com/search?q=golang")
	if err != nil {
		panic(err)
	}
	// Find all news item.
	for i, n := range htmlquery.Find(doc, "//ol/li") {
		a := htmlquery.FindOne(n, "//a")
		fmt.Printf("%d %s(%s)\n", i, htmlquery.InnerText(a), htmlquery.SelectAttr(a, "href"))
	}
}