跳至主要内容

go spider example hello golang crawler

package main

import (
"github.com/PuerkitoBio/goquery"
"github.com/hu17889/go_spider/core/common/page"
"github.com/hu17889/go_spider/core/pipeline"
"github.com/hu17889/go_spider/core/spider"
)

type MyPageProcesser struct {
}

func NewMyPageProcesser() *MyPageProcesser {
return &MyPageProcesser{}
}

// Parse html dom here and record the parse result that we want to Page.
// Package goquery (http://godoc.org/github.com/PuerkitoBio/goquery) is used to parse html.
func (this *MyPageProcesser) Process(p *page.Page) {
query := p.GetHtmlParser()
query.Find("td div[class='flex-middle']").Each(func(i int, s *goquery.Selection) {
println(s.Text())
})
}
func (*MyPageProcesser) Finish() {
}
func main() {
spider.NewSpider(NewMyPageProcesser(), "TaskName").
AddUrl("http://101.200.54.63/", "html").    // start url, html is the responce type ("html" or "json")
AddPipeline(pipeline.NewPipelineConsole()). // print result on screen
SetThreadnum(3).                            // crawl request by three Coroutines
Run()
}

评论

此博客中的热门博文

onsen ui example splitter side menu swipe

<!DOCTYPE html> <html> <head> <title>TheyTube - Watch free video online</title> <link rel="stylesheet" href="https://unpkg.com/onsenui/css/onsenui.css"> <link rel="stylesheet" href="https://unpkg.com/onsenui/css/onsen-css-components.min.css">   <script src="https://unpkg.com/onsenui/js/onsenui.min.js"></script>   <script type="text/javascript">   ons.platform.select('android')   </script> </head> <body> <ons-splitter>   <ons-splitter-side id="menu" side="left" width="220px" collapse swipeable>     <ons-page>       <ons-list>         <ons-list-item onclick="fn.load('home.html')" tappable>           Home         </ons-list-item>         <ons-list-item onclick="fn.load('settings.html')" tappable>           Setti

go golang get disk usage free space remain info

package main import ( "fmt" "syscall" ) func main() { fmt.Println(DiskUsage("./")) } func DiskUsage(path string) uint64 { fs := syscall.Statfs_t{} err := syscall.Statfs(path, &fs) if err != nil { return 0 } return fs.Bfree * uint64(fs.Bsize) } //All space   = fs.Blocks * uint64(fs.Bsize) //Free space = fs.Bfree * uint64(fs.Bsize) //Used space= fs.All - disk.Free