nodejs通過phantomjs實現下載網頁簡單介紹

antzone發表於2017-04-07

能其實很見簡單,通過 phantomjs.exe 採集 url 載入的資源,通過子程式的方式,啟動nodejs 載入所有的資源,對於css的資源,匹配css內容,下載裡面的url資源。

當然功能還是很簡單的,在響應式設計和非同步載入的情況下,還是有很多資源沒有能夠下載,需要根據實際情況處理。

首先當然是下載 nodejs 和 phantomjs:

下面是 phantomjs.exe 執行的 down.js

[JavaScript] 純文字檢視 複製程式碼
var page = require('webpage').create(),
  system = require('system');
var spawn = require("child_process").spawn
  
if (system.args.length === 1) {
  console.log('Usage: netsniff.js <some URL>');
  phantom.exit(1);
} else {
  var urls = [];
  page.address = system.args[1];
  page.onResourceReceived = function (res) {
    if (res.stage === 'start') {
      urls.push(res.url);
    }
  };
  page.open(page.address, function (status) {
    var har;
    if (status !== 'success') {
      console.log('FAIL to load the address');
      phantom.exit(1);
    } else {
      console.log('down resource ' + urls.length + ' urls.');
      var child = spawn("node", ["--harmony", "downHtml.js", urls.join(',')])
      child.stdout.on("data", function (data) {
       console.log(data);
      })
      child.stderr.on("data", function (data) {
       console.log(data);
      })
      child.on("exit", function (code) {
       phantom.exit();
      })      
    }
  });
}

下面是對應的node執行的 downHtml.js

[JavaScript] 純文字檢視 複製程式碼
"use strict";
var fs = require('fs');
var http = require('http');
var path = require('path');
var r_url = require('url');
  
var dirCache = {};//快取減少判斷
function makedir (pathStr, callback) {
  if (dirCache[pathStr] == 1) {
    callback();
  } else {
    fs.exists(pathStr, function (exists) {
      if (exists == true) {
        dirCache[pathStr] == 1;
        callback();
      } else {
        makedir(path.dirname(pathStr), function () {
          fs.mkdir(pathStr, function () {
            dirCache[pathStr] == 1;
            callback();
          })
        });
      }
    })
  }
};
  
var reg = /[:,]\s*url\(['"]?.*?(\1)\)/g
var reg2 = /\((['"]?)(.*?)(\1)\)/
var isDownMap = {};
var downImgFromCss = function (URL) {
  http.get(URL, function(res) {
    //console.log(path.resolve(process.cwd(), 'index.min.css'))
    //res.pipe(fs.createWriteStream(path.resolve(process.cwd(), 'index.min.css')));
    var body = "";
    res.setEncoding('utf8');
    res.on('data', function (chunk) {
      body += chunk;
    });
    res.on('end', function () {
      var match = body.match(reg);
      for (var i = 0, len = match.length; i < len; i++){
        var m = match[i].match(reg2);
        if (m && m[2]) {
          var url = m[2];
          let imgUrl = r_url.resolve(URL, url);
          if (!isDownMap[imgUrl]) {
            var uo = r_url.parse(imgUrl);
            let filepath = CWD + '/' + uo.hostname + uo.pathname;
            makedir(path.dirname(filepath), function () {
              http.get(imgUrl, function (res) {
                res.pipe(fs.createWriteStream(filepath));
              })
            })
            isDownMap[imgUrl] = 1;
          }
        }
      }
    });
  });
}
  
var URLS = process.argv[2].split(',');
var CWD = process.cwd();
//下載資源
URLS.forEach(function (URL) {
  var uo = r_url.parse(URL);
  var filepath;
  if (uo.pathname == '/' || uo.pathname == '') {
    filepath = CWD + '/' + uo.hostname + '/index.html';
  } else {
    filepath = CWD + '/' + uo.hostname + uo.pathname;
  }
  makedir(path.dirname(filepath), function () {
    http.get(URL, function (res) {
      if (URL.indexOf('.css') != -1 || (res.headers["content-type"] && res.headers["content-type"].indexOf('text/css')!= -1)) {
        console.log('down images form css file:' + URL + '.');
        downImgFromCss(URL);
      }
      res.pipe(fs.createWriteStream(filepath));
    })
  });
});

down.js downHtml.js 放在同一個資料夾下 通過下列 cmd 執行

D:\phantomjs-2.0.0-windows\bin\phantomjs.exe down.js http://www.softwhy.com/

相關文章