Home

Awesome

Pagser

go-doc-img travis-img go-report-card-img Coverage Status

Pagser inspired by <u>pag</u>e par<u>ser</u>

Pagser is a simple, extensible, configurable parse and deserialize html page to struct based on goquery and struct tags for golang crawler.

Contents

Install

go get -u github.com/foolin/pagser

Or get the specified version:

go get github.com/foolin/pagser@{version}

The {version} release list: https://github.com/foolin/pagser/releases

Features

Docs

See Pagser

Usage


package main

import (
	"encoding/json"
	"github.com/foolin/pagser"
	"log"
)

const rawPageHtml = `
<!doctype html>
<html>
<head>
    <meta charset="utf-8">
    <title>Pagser Title</title>
	<meta name="keywords" content="golang,pagser,goquery,html,page,parser,colly">
</head>

<body>
	<h1>H1 Pagser Example</h1>
	<div class="navlink">
		<div class="container">
			<ul class="clearfix">
				<li id=''><a href="/">Index</a></li>
				<li id='2'><a href="/list/web" title="web site">Web page</a></li>
				<li id='3'><a href="/list/pc" title="pc page">Pc Page</a></li>
				<li id='4'><a href="/list/mobile" title="mobile page">Mobile Page</a></li>
			</ul>
		</div>
	</div>
</body>
</html>
`

type PageData struct {
	Title    string   `pagser:"title"`
	Keywords []string `pagser:"meta[name='keywords']->attrSplit(content)"`
	H1       string   `pagser:"h1"`
	Navs     []struct {
		ID   int    `pagser:"->attrEmpty(id, -1)"`
		Name string `pagser:"a->text()"`
		Url  string `pagser:"a->attr(href)"`
	} `pagser:".navlink li"`
}

func main() {
	//New default config
	p := pagser.New()

	//data parser model
	var data PageData
	//parse html data
	err := p.Parse(&data, rawPageHtml)
	//check error
	if err != nil {
		log.Fatal(err)
	}

	//print data
	log.Printf("Page data json: \n-------------\n%v\n-------------\n", toJson(data))
}

func toJson(v interface{}) string {
	data, _ := json.MarshalIndent(v, "", "\t")
	return string(data)
}

Run output:


Page data json: 
-------------
{
	"Title": "Pagser Title",
	"Keywords": [
		"golang",
		"pagser",
		"goquery",
		"html",
		"page",
		"parser",
		"colly"
	],
	"H1": "H1 Pagser Example",
	"Navs": [
		{
			"ID": -1,
			"Name": "Index",
			"Url": "/"
		},
		{
			"ID": 2,
			"Name": "Web page",
			"Url": "/list/web"
		},
		{
			"ID": 3,
			"Name": "Pc Page",
			"Url": "/list/pc"
		},
		{
			"ID": 4,
			"Name": "Mobile Page",
			"Url": "/list/mobile"
		}
	]
}
-------------

Configuration


type Config struct {
	TagName    string //struct tag name, default is `pagser`
	FuncSymbol   string //Function symbol, default is `->`
	Debug        bool   //Debug mode, debug will print some log, default is `false`
}

Struct Tag Grammar

[goquery selector]->[function]

Example:


type ExamData struct {
	Herf string `pagser:".navLink li a->attr(href)"`
}

1.Struct tag name: pagser
2.goquery selector: .navLink li a
3.Function symbol: ->
4.Function name: attr
5.Function arguments: href

grammar

Functions

Builtin functions

More builtin functions see docs: https://pkg.go.dev/github.com/foolin/pagser?tab=doc#BuiltinFunctions

Extension functions

Extensions function need register, like:

import "github.com/foolin/pagser/extensions/markdown"

p := pagser.New()

//Register Markdown
markdown.Register(p)

Custom function

Function interface


type CallFunc func(node *goquery.Selection, args ...string) (out interface{}, err error)

Define global function


//global function need call pagser.RegisterFunc("MyGlob", MyGlobalFunc) before use it.
// this global method must call pagser.RegisterFunc("MyGlob", MyGlobalFunc).
func MyGlobalFunc(node *goquery.Selection, args ...string) (out interface{}, err error) {
	return "Global-" + node.Text(), nil
}

type PageData struct{
  MyGlobalValue string    `pagser:"->MyGlob()"`
}

func main(){

    p := pagser.New()

    //Register global function `MyGlob`
    p.RegisterFunc("MyGlob", MyGlobalFunc)

    //Todo

    //data parser model
    var data PageData
    //parse html data
    err := p.Parse(&data, rawPageHtml)

    //...
}

Define struct function


type PageData struct{
  MyFuncValue int    `pagser:"->MyFunc()"`
}

// this method will auto call, not need register.
func (d PageData) MyFunc(node *goquery.Selection, args ...string) (out interface{}, err error) {
	return "Struct-" + node.Text(), nil
}


func main(){

    p := pagser.New()

    //Todo

    //data parser model
    var data PageData
    //parse html data
    err := p.Parse(&data, rawPageHtml)

    //...
}

Call Syntax

Note: all function arguments are string, single quotes are optional.

  1. Function call with no arguments

->fn()

  1. Function calls with one argument, and single quotes are optional

->fn(one)

->fn('one')

  1. Function calls with many arguments

->fn(one, two, three, ...)

->fn('one', 'two', 'three', ...)

  1. Function calls with single quotes and escape character

->fn('it\'s ok', 'two,xxx', 'three', ...)

Priority Order

Lookup function priority order:

struct method -> parent method -> ... -> global

More Examples

See advance example: https://github.com/foolin/pagser/tree/master/_examples/advance

Implicit type conversion

Automatic implicit type conversion, Output result string convert to int, int64, float64...

Support type:

Examples

Crawl page example


package main

import (
	"encoding/json"
	"github.com/foolin/pagser"
	"log"
	"net/http"
)

type PageData struct {
	Title    string `pagser:"title"`
	RepoList []struct {
		Names       []string `pagser:"h1->textSplit('/', true)"`
		Description string   `pagser:"h1 + p"`
		Stars       string   `pagser:"a.muted-link->eqAndText(0)"`
		Repo        string   `pagser:"h1 a->attrConcat('href', 'https://github.com', $value, '?from=pagser')"`
	} `pagser:"article.Box-row"`
}

func main() {
	resp, err := http.Get("https://github.com/trending")
	if err != nil {
		log.Fatal(err)
	}
	defer resp.Body.Close()

	//New default config
	p := pagser.New()

	//data parser model
	var data PageData
	//parse html data
	err = p.ParseReader(&data, resp.Body)
	//check error
	if err != nil {
		log.Fatal(err)
	}

	//print data
	log.Printf("Page data json: \n-------------\n%v\n-------------\n", toJson(data))
}

func toJson(v interface{}) string {
	data, _ := json.MarshalIndent(v, "", "\t")
	return string(data)
}


Run output:


2020/04/25 12:26:04 Page data json: 
-------------
{
	"Title": "Trending  repositories on GitHub today · GitHub",
	"RepoList": [
		{
			"Names": [
				"pcottle",
				"learnGitBranching"
			],
			"Description": "An interactive git visualization to challenge and educate!",
			"Stars": "16,010",
			"Repo": "https://github.com/pcottle/learnGitBranching?from=pagser"
		},
		{
			"Names": [
				"jackfrued",
				"Python-100-Days"
			],
			"Description": "Python - 100天从新手到大师",
			"Stars": "83,484",
			"Repo": "https://github.com/jackfrued/Python-100-Days?from=pagser"
		},
		{
			"Names": [
				"brave",
				"brave-browser"
			],
			"Description": "Next generation Brave browser for macOS, Windows, Linux, Android.",
			"Stars": "5,963",
			"Repo": "https://github.com/brave/brave-browser?from=pagser"
		},
		{
			"Names": [
				"MicrosoftDocs",
				"azure-docs"
			],
			"Description": "Open source documentation of Microsoft Azure",
			"Stars": "3,798",
			"Repo": "https://github.com/MicrosoftDocs/azure-docs?from=pagser"
		},
		{
			"Names": [
				"ahmetb",
				"kubectx"
			],
			"Description": "Faster way to switch between clusters and namespaces in kubectl",
			"Stars": "6,979",
			"Repo": "https://github.com/ahmetb/kubectx?from=pagser"
		},

        //...        

		{
			"Names": [
				"serverless",
				"serverless"
			],
			"Description": "Serverless Framework – Build web, mobile and IoT applications with serverless architectures using AWS Lambda, Azure Functions, Google CloudFunctions \u0026 more! –",
			"Stars": "35,502",
			"Repo": "https://github.com/serverless/serverless?from=pagser"
		},
		{
			"Names": [
				"vuejs",
				"vite"
			],
			"Description": "Experimental no-bundle dev server for Vue SFCs",
			"Stars": "1,573",
			"Repo": "https://github.com/vuejs/vite?from=pagser"
		}
	]
}
-------------

Colly Example

Work with colly:


p := pagser.New()


// On every a element which has href attribute call callback
collector.OnHTML("body", func(e *colly.HTMLElement) {
	//data parser model
	var data PageData
	//parse html data
	err := p.ParseSelection(&data, e.Dom)

})

Dependencies

Extensions: