简易版图片蜘蛛

Posted 2020-08-24 ecofast

　　可能，宅男或老司机某种程度上会喜欢这个工具。事实上，这个工具也确实是应老司机的需求而写，只是还比较简易，短期内可能不会再作改进或增强（譬如绕过防盗链处理等）。

　　完整参考命令行：MiniImageCrawler -numCrawlGoroutine=5 -baseInterval=2 -randomInterval=5 -tickerInterval=10 -savePath=d:/test -imgWidthMin=500 -imgHeightMin=500 http://eladies.sina.com.cn/　　

　　或直接：MiniImageCrawler http://eladies.sina.com.cn/

　　于是即可坐等程序将指定网站的所有（符合条件的）图片抓取到本地。

 

package main

import (
	"ImageCrawler"
	"flag"
	"fmt"
	"helperutils"
	"image"
	_ "image/jpeg"
	_ "image/png"
	"log"
	"math/rand"
	"net/url"
	"os"
	"runtime"
	"sync/atomic"
	"time"
)

var numCrawlGoroutine int
var baseInterval, randomInterval int
var tickerInterval int
var savePath string
var imgWidthMin, imgHeightMin int

var urlHost string

func init() {
	rand.Seed(time.Now().UnixNano())
}

func parseFlag() {
	flag.IntVar(&numCrawlGoroutine, "numCrawlGoroutine", 5, "最大抓取线程数")
	flag.IntVar(&baseInterval, "baseInterval", 2, "最短抓取间隔")
	flag.IntVar(&randomInterval, "randomInterval", 5, "抓取随机间隔")
	flag.IntVar(&tickerInterval, "tickerInterval", 10, "Goroutine数目报告间隔(单位: s)")
	flag.StringVar(&savePath, "savePath", "", "图片保存目录(默认为程序所在目录)")
	flag.IntVar(&imgWidthMin, "imgWidthMin", 0, "最小图片宽度")
	flag.IntVar(&imgHeightMin, "imgHeightMin", 0, "最小图片高度")

	flag.Parse()

	if len(flag.Args()) == 0 {
		panic("请指定起始抓取网页地址！")
	} else {
		u, err := url.Parse(flag.Args()[0])
		if err != nil {
			panic(err)
		}
		urlHost = u.Host
	}

	if numCrawlGoroutine < 1 {
		panic("请设定不小于 1 的最大抓取线程数！")
	}
	if baseInterval < 1 {
		panic("请设定不小于 1 的最短抓取间隔！")
	}
	if randomInterval < 2 {
		panic("请设定合法的抓取随机间隔！")
	}
	if tickerInterval < 5 {
		panic("请设定不小于 5 的报告间隔！")
	}
	if savePath == "" {
		savePath = helperutils.GetAppPath() + urlHost + `\\`
		if !helperutils.DirectoryExists(savePath) {
			if err := os.Mkdir(savePath, os.ModePerm); err != nil {
				panic(fmt.Sprintf("Can not make dir: %s", savePath))
			}
		}
	} else {
		if !helperutils.DirectoryExists(savePath) {
			panic("不合法的图片保存目录设置！")
		}
		savePath = helperutils.IncludeTrailingBackslash(savePath)
	}
	if imgWidthMin < 0 {
		panic("请设定不小于 0 的最小图片宽度！")
	}
	if imgHeightMin < 0 {
		panic("请设定不小于 0 的最小图片高度！")
	}
}

func parsePage(url, homePage string, numChan chan<- string) []string {
	ret, err := ImageCrawler.ParsePage(url, homePage, savePath, numChan)
	if err != nil {
		return nil
	}

	time.Sleep(time.Duration(rand.Intn(randomInterval)+baseInterval) * time.Second)
	return ret
}

func checkImageSize(fileName string, minWidth, minHeight int) bool {
	file, err := os.Open(fileName)
	if err != nil {
		return false
	}

	img, _, err := image.Decode(file)
	if err != nil {
		file.Close()
		os.Remove(fileName)
		return false
	}

	pt := img.Bounds().Size()
	if pt.X < minWidth || pt.Y < minHeight {
		file.Close()
		os.Remove(fileName)
		return false
	}

	file.Close()
	return true
}

func main() {
	parseFlag()

	var imgNum, smallNum int64
	nameChan := make(chan string)
	go func() {
		for s := range nameChan {
			imgNum += 1
			go func(imgName string) {
				if !CheckImageSize(imgName, imgWidthMin, imgHeightMin) {
					atomic.AddInt64(&smallNum, 1)
				}
			}(s)
		}
	}()

	worklist := make(chan []string)
	pendingNum := 1
	go func() {
		worklist <- []string{flag.Args()[0]}
	}()

	ticker := time.NewTicker(time.Duration(tickerInterval) * time.Second)
	go func() {
		for range ticker.C {
			log.Printf("Num of Goroutines: %d\\n", runtime.NumGoroutine())
		}
	}()

	tokens := make(chan struct{}, numCrawlGoroutine)
	seenUrls := make(map[string]bool)

	log.Println("图片抓取已启动...")
	timeBegin := time.Now()
	for ; pendingNum > 0; pendingNum-- {
		list := <-worklist
		for _, link := range list {
			if !seenUrls[link] {
				seenUrls[link] = true
				pendingNum++
				go func(url string) {
					tokens <- struct{}{}
					defer func() {
						<-tokens
					}()
					worklist <- parsePage(url, urlHost, nameChan)
				}(link)
			}
		}
	}
	log.Printf("图片抓取结束。耗时: %s\\n", time.Since(timeBegin).String())

	log.Println("正在进行收尾统计...")
	close(nameChan)
	ticker.Stop()
	time.Sleep(time.Millisecond * 2000)
	invalidNum := atomic.LoadInt64(&smallNum)
	log.Printf("抓取总计: 图片总数 %d, 小图片数 %d, 有效图片数 %d\\n", imgNum, invalidNum, imgNum-invalidNum)

	log.Println("The End.")
}

　　

package ImageCrawler

import (
	"fmt"
	"io"
	"net/http"
	"os"
	"path/filepath"
	"strings"

	"golang.org/x/net/html"
)

func ParsePage(url, homePage, savePath string, nameChan chan<- string) ([]string, error) {
	resp, err := http.Get(url)
	if err != nil {
		return nil, err
	}
	defer resp.Body.Close()

	if resp.StatusCode != http.StatusOK {
		return nil, fmt.Errorf("getting %s: %s", url, resp.Status)
	}

	doc, err := html.Parse(resp.Body)
	if err != nil {
		return nil, fmt.Errorf("parsing %s as HTML: %v", url, err)
	}

	var links []string
	visitNode := func(n *html.Node) {
		if n.Type == html.ElementNode && n.Data == "a" {
			for _, a := range n.Attr {
				if a.Key != "href" {
					continue
				}
				link, err := resp.Request.URL.Parse(a.Val)
				if err != nil {
					continue
				}
				addr := link.String()
				if strings.HasSuffix(addr, ".jpg") || strings.HasSuffix(addr, ".jpeg") || strings.HasSuffix(addr, ".png") {
					DownloadImage(addr, savePath, nameChan)
				} else {
					if strings.Contains(addr, homePage) {
						links = append(links, addr)
					}
				}
			}
		} else if n.Type == html.ElementNode && n.Data == "img" {
			for _, a := range n.Attr {
				if a.Key != "src" {
					continue
				}
				link, err := resp.Request.URL.Parse(a.Val)
				if err != nil {
					continue
				}
				addr := link.String()
				if strings.HasSuffix(addr, ".jpg") || strings.HasSuffix(addr, ".jpeg") || strings.HasSuffix(addr, ".png") {
					DownloadImage(addr, savePath, nameChan)
				}
			}
		}
	}
	forEachNode(doc, visitNode, nil)
	return links, nil
}

func DownloadImage(addr, savePath string, nameChan chan<- string) {
	resp, err := http.Get(addr)
	if err != nil {
		return
	}
	defer resp.Body.Close()

	if resp.StatusCode != http.StatusOK {
		return
	}

	fileName := savePath + filepath.Base(addr)
	dst, err := os.Create(fileName)
	if err != nil {
		return
	}

	io.Copy(dst, resp.Body)
	dst.Close()

	nameChan <- fileName
}

func forEachNode(n *html.Node, pre, post func(n *html.Node)) {
	if pre != nil {
		pre(n)
	}
	for c := n.FirstChild; c != nil; c = c.NextSibling {
		forEachNode(c, pre, post)
	}
	if post != nil {
		post(n)
	}
}

 

　　

 

　　可执行文件下载链接在这里。