node.js 爬取图片
/**
* _ooOoo_
* o8888888o
* 88" . "88
* (| -_- |)
* O\ = /O
* ____/`---'\____
* . ' \\| |// `.
* / \\||| : |||// \
* / _||||| -:- |||||- \
* | | \\\ - /// | |
* | \_| ''\---/'' | |
* \ .-\__ `-` ___/-. /
* ___`. .' /--.--\ `. . __
* ."" '< `.___\_<|>_/___.' >'"".
* | | : `- \`.;`\ _ /`;.`/ - ` : | |
* \ \ `-. \_ __\ /__ _/ .-` / /
* ======`-.____`-.___\_____/___.-`____.-'======
* `=---='
*
* .............................................
* 佛祖保佑 永无BUG
*
* Created by Ning on 2018/8/16.
*/
var http = require("http");
var fs = require("fs");
var path = require("path");
var url = "http://www.xxxxxxxx.cn/";
http.get(url,function (res) {
var content = '';
res.on('data',function (data) {
content += data;
});
res.on('end',function () {
//正则匹配jpg png图片
var reg = /src="(.*?\.jpg|.*?\.png)"/img;
var filename = "";
//循环匹配
while (filename = reg.exec(content)){
getImage(url,filename[1]);
// url = "http://hospital.dev.ftbj.net" + filename[1];
}
});
});
//爬取图片
function getImage(url,filename) {
//获取图片的文件名
var obj = path.parse(filename);
var fn = obj.base;
var streaml = fs.createWriteStream('./image/'+fn);
var image = url + filename;
http.get(image,function (res) {
//管道的方式流入文件中
res.pipe(streaml);
});
}