• Stars
    star
    363
  • Rank 117,374 (Top 3 %)
  • Language
    Go
  • License
    MIT License
  • Created almost 7 years ago
  • Updated over 1 year ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

xmlquery is Golang XPath package for XML query.

xmlquery

Build Status GoDoc Go Report Card

Overview

xmlquery is an XPath query package for XML documents, allowing you to extract data or evaluate from XML documents with an XPath expression.

xmlquery has a built-in query object caching feature that caches recently used XPATH query strings. Enabling caching can avoid recompile XPath expression for each query.

You can visit this page to learn about the supported XPath(1.0/2.0) syntax. https://github.com/antchfx/xpath

htmlquery - Package for the HTML document query.

xmlquery - Package for the XML document query.

jsonquery - Package for the JSON document query.

Installation

 $ go get github.com/antchfx/xmlquery

Quick Starts

import (
	"github.com/antchfx/xmlquery"
)

func main(){
	s := `<?xml version="1.0" encoding="UTF-8" ?>
<rss version="2.0">
<channel>
  <title>W3Schools Home Page</title>
  <link>https://www.w3schools.com</link>
  <description>Free web building tutorials</description>
  <item>
    <title>RSS Tutorial</title>
    <link>https://www.w3schools.com/xml/xml_rss.asp</link>
    <description>New RSS tutorial on W3Schools</description>
  </item>
  <item>
    <title>XML Tutorial</title>
    <link>https://www.w3schools.com/xml</link>
    <description>New XML tutorial on W3Schools</description>
  </item>
</channel>
</rss>`

	doc, err := xmlquery.Parse(strings.NewReader(s))
	if err != nil {
		panic(err)
	}
	channel := xmlquery.FindOne(doc, "//channel")
	if n := channel.SelectElement("title"); n != nil {
		fmt.Printf("title: %s\n", n.InnerText())
	}
	if n := channel.SelectElement("link"); n != nil {
		fmt.Printf("link: %s\n", n.InnerText())
	}
	for i, n := range xmlquery.Find(doc, "//item/title") {
		fmt.Printf("#%d %s\n", i, n.InnerText())
	}
}

Getting Started

Find specified XPath query.

list, err := xmlquery.QueryAll(doc, "a")
if err != nil {
	panic(err)
}

Parse an XML from URL.

doc, err := xmlquery.LoadURL("http://www.example.com/sitemap.xml")

Parse an XML from string.

s := `<?xml version="1.0" encoding="utf-8"?><rss version="2.0"></rss>`
doc, err := xmlquery.Parse(strings.NewReader(s))

Parse an XML from io.Reader.

f, err := os.Open("../books.xml")
doc, err := xmlquery.Parse(f)

Parse an XML in a stream fashion (simple case without elements filtering).

f, _ := os.Open("../books.xml")
p, err := xmlquery.CreateStreamParser(f, "/bookstore/book")
for {
	n, err := p.Read()
	if err == io.EOF {
		break
	}
	if err != nil {
		panic(err)
	}
	fmt.Println(n)
}

Notes: CreateStreamParser() used for saving memory if your had a large XML file to parse.

Parse an XML in a stream fashion (simple case advanced element filtering).

f, _ := os.Open("../books.xml")
p, err := xmlquery.CreateStreamParser(f, "/bookstore/book", "/bookstore/book[price>=10]")
for {
	n, err := p.Read()
	if err == io.EOF {
		break
	}
	if err != nil {
		panic(err)
	}
	fmt.Println(n)
}

Find authors of all books in the bookstore.

list := xmlquery.Find(doc, "//book//author")
// or
list := xmlquery.Find(doc, "//author")

Find the second book.

book := xmlquery.FindOne(doc, "//book[2]")

Find the last book.

book := xmlquery.FindOne(doc, "//book[last()]")

Find all book elements and only get id attribute.

list := xmlquery.Find(doc,"//book/@id")
fmt.Println(list[0].InnerText) // outout @id value

Find all books with id bk104.

list := xmlquery.Find(doc, "//book[@id='bk104']")

Find all books with price less than 5.

list := xmlquery.Find(doc, "//book[price<5]")

Evaluate total price of all books.

expr, err := xpath.Compile("sum(//book/price)")
price := expr.Evaluate(xmlquery.CreateXPathNavigator(doc)).(float64)
fmt.Printf("total price: %f\n", price)

Count the number of books.

expr, err := xpath.Compile("count(//book)")
count := expr.Evaluate(xmlquery.CreateXPathNavigator(doc)).(float64)

Calculate the total price of all book prices.

expr, err := xpath.Compile("sum(//book/price)")
price := expr.Evaluate(xmlquery.CreateXPathNavigator(doc)).(float64)

Advanced Features

Parse UTF-16 XML file with ParseWithOptions().

f, _ := os.Open(`UTF-16.XML`)
// Convert UTF-16 XML to UTF-8
utf16ToUtf8Transformer := unicode.UTF16(unicode.LittleEndian, unicode.IgnoreBOM).NewDecoder()
utf8Reader := transform.NewReader(f, utf16ToUtf8Transformer)
// Sets `CharsetReader`
options := xmlquery.ParserOptions{
	Decoder: &xmlquery.DecoderOptions{
		CharsetReader: func(charset string, input io.Reader) (io.Reader, error) {
			return input, nil
		},
	},
}
doc, err := xmlquery.ParseWithOptions(utf8Reader, options)

Query with custom namespace prefix.

s := `<?xml version="1.0" encoding="UTF-8"?>
<pd:ProcessDefinition xmlns:pd="http://xmlns.xyz.com/process/2003" xmlns:xsl="http://www.w3.org/1999/XSL/Transform" xmlns:xsd="http://www.w3.org/2001/XMLSchema">
<pd:activity name="Invoke Request-Response Service">
<pd:type>RequestReplyActivity</pd:type>
<pd:resourceType>OpClientReqActivity</pd:resourceType>
<pd:x>300</pd:x>
<pd:y>80</pd:y>
</pd:activity>
</pd:ProcessDefinition>`
nsMap := map[string]string{
	"q": "http://xmlns.xyz.com/process/2003",
	"r": "http://www.w3.org/1999/XSL/Transform",
	"s": "http://www.w3.org/2001/XMLSchema",
}
expr, _ := xpath.CompileWithNS("//q:activity", nsMap)
node := xmlquery.QuerySelector(doc, expr)

Create XML document without call xml.Marshal.

doc := &xmlquery.Node{
	Type: xmlquery.DeclarationNode,
	Data: "xml",
	Attr: []xml.Attr{
		xml.Attr{Name: xml.Name{Local: "version"}, Value: "1.0"},
	},
}
root := &xmlquery.Node{
	Data: "rss",
	Type: xmlquery.ElementNode,
}
doc.FirstChild = root
channel := &xmlquery.Node{
	Data: "channel",
	Type: xmlquery.ElementNode,
}
root.FirstChild = channel
title := &xmlquery.Node{
	Data: "title",
	Type: xmlquery.ElementNode,
}
title_text := &xmlquery.Node{
	Data: "W3Schools Home Page",
	Type: xmlquery.TextNode,
}
title.FirstChild = title_text
channel.FirstChild = title

fmt.Println(doc.OutputXML(true))
fmt.Println(doc.OutputXMLWithOptions(WithOutputSelf()))

Output:

<?xml version="1.0"?><rss><channel><title>W3Schools Home Page</title></channel></rss>

FAQ

Find() vs QueryAll(), which is better?

Find and QueryAll both do the same thing: searches all of matched XML nodes. Find panics if provided with an invalid XPath query, while QueryAll returns an error.

Can I save my query expression object for the next query?

Yes, you can. We provide QuerySelector and QuerySelectorAll methods; they accept your query expression object.

Caching a query expression object avoids recompiling the XPath query expression, improving query performance.

Questions

Please let me know if you have any questions