Node.js环境下编写爬虫爬取维基百科内容的实例分享

var regKey = ['航空母舰','航空母艦','航母'];  //链接中若包含此中关键词，即为目标
var allKeys = [];              //链接的title，也是页面标识，避免重复抓取
var keys = ['Category:%E8%88%AA%E7%A9%BA%E6%AF%8D%E8%88%B0'];  //等待队列，起始页

$ = cheer.load(downHtml);
 var rsHtml = $.html();
 var imgs = $('#bodyContent .image');    //图片都由这个样式修饰
 for(img in imgs){
  if(typeof imgs[img].attribs === 'undefined' || typeof imgs[img].attribs.href === 'undefined')
   {continue;}  //结构为链接下的图片，链接不存在，跳过
  else
   {
    var picUrl = imgs[img].children[0].attribs.src;  //图片地址
    var dirs = picUrl.split('.');
    var filename = baseDir+uuid.v1()+'.'+dirs[dirs.length -1];  //重新命名

    request("https:"+picUrl).pipe(fs.createWriteStream('pages/'+filename));  //下载

    rsHtml = rsHtml.replace(picUrl,filename);  //换成本地路径
    // console.log(picUrl);
   }
 }

var keys = ['航空母舰'];
var key = keys.shift();
while(key){
 data.get({
  url:encodeURI(key),
  qs:null
 }).then(function(downHtml){
    ...
    keys.push(key);        //(1)
  }
 });
key = keys.shift();          //(2）
}

var key = keys.shift();
(function doNext(key){
 data.get({
  url:key,
  qs:null
 }).then(function(downHtml){
  ...
  keys.push(href);
  ...
  key = keys.shift();
  if(key){
   doNext(key);
  }else{
   console.log('抓取任务顺利完成。')
  }
 })
})(key);

var regs = [/<link rel=\"stylesheet\" href=\"?[^\"]*\">/g,
  /<script>?[^<]*<\/script>/g,
 /<style>?[^<]*<\/style>/g,
 /<a ?[^>]*>/g,
 /<\/a>/g,
 /srcset=(\"?[^\"]*\")/g
 ]
 regs.forEach(function(rs){
  var mactches = rsHtml.match(rs);
  for (var i=0;i < mactches.length ; i++)
  {
   rsHtml = rsHtml.replace(mactches[i],mactches[i].indexOf('stylesheet')>-1?'<link rel="stylesheet" href="wiki'+(i+1)+'.css"':'');
  }
 })