module.exports = (function () {
"use strict"
var fs = require('fs')
, fetch = require('./fetch.js')
, _jobs = {};
function _send(campaignId){
var job = _jobs[campaignId];
if (!job) return;
if (job.waiting) {
job.waiting = false;
clearTimeout(job.timeout);
var finish = (job.urlsNum === job.finishNum) urls: job.urls,
完成：完成
};
job.urls = []; 刪除_jobs[campaignId]
}
res.writeHead(200, {'Content-類型': 'appli res.writeHead(200, {'Content-Type': 'appli/json'}); 🎜> res.end ( JSON.stringify(data));
}
}
function register(campaignId, urls, req, res, next) { : urls.length,
finishNum: 0,
urls: [],
iting: false,
timeout: null
} ;
watch(campaignId, req, res, next);
}
function watch(campaignId, req, res, next) {
_jobs[campaignId].res = res;
// 20 秒逾時
{
_send(campaignId);
}, 20000);
}
function fire(opts) {
var CampaignId = opts.campaignId
, job = _jobs[campaignId]
if (job) {
if ( opts.status && fetchObj.title) {
🎜> url: opts.url,
圖片：opts.image，
標題：fetchObj.title， });
}其他{
job.urls.push({
id: opts.id,
});
}
if（!🎜> job.finishNum ;
} else {
console.log('作業
function getUrls(campaignId) {
var job = _jobs[campaignId];
if (job) return job.cacheUrls;
if (job) return job.cacheUrls;
>
return {
註冊：註冊，
觀看：觀看，
火：火，
getUrls：getUrls
})();
這裡我們用fetch對html進行抓取其標題與描述，fetch實作比較簡單（fetch.js）：
複製程式碼
程式碼如下：
module.exports = (function () {
"使用嚴格"
回傳函數 (html) {
if (!html) return { 標題: false, 說明: false };
var title = html.match(/
(.*?)/)
, meta = html.match(/
; /g)
，描述；
if (meta) {
for (var i = meta.length; i--;) {
if(meta[i].indexOf('name="description if(meta[i].indexOf('name="description) | | 元[i].indexOf('name="描述"') > -1){
說明= 元[i].match(/content="(.*?)"/)[1] ;
}
}
}
(標題&& 標題[1] !== '') ? (標題= 標題[1]) : (標題= '無標題');
描述|| (說明= '無描述');
return {
標題：標題，
說明：說明
};
}
; };
}
;;
;
;
;
最後是PhantomJS運行的源代碼，其啟動後通過HTTP向bridge獲取job信息，然後每完成job的其中一個url就通過返回HTTP給bridge（snapshot.js）：
複製程式碼程式碼如下：
var webpage = require('webpage')
, args = require('system').args
, fs = require('fs')
, campaignId = args[1]
, pkg = JSON.parse(fs.read('./package.json'));
function snapshot(id, url, imagePath) {
var page = webpage.create()
, send
, begin
, save
, end;
page.viewportSize = { width: 1024, height: 800 };
page.clipRect = { top: 0, left: 0, width: 1024, height: 800 };
page.settings = {
javascriptEnabled: false,
loadImages: true,
userAgent: 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.31 (KHTML, like Gecko) PhantomJS/1.9.0'
};
page.open(url, function (status) {
var data;
if (status === 'fail') {
data = [
'campaignId=',
campaignId,
'&url=',
encodeURIComponent(url),
'&id=',
id,
'&status=',
].join('');
postPage.open('http://localhost:' + pkg.port + '/bridge', 'POST', data, function () {});
} else {
page.render(imagePath);
var html = page.content;
// callback NodeJS
data = [
'campaignId=',
campaignId,
'&html=',
encodeURIComponent(html),
'&url=',
encodeURIComponent(url),
'&image=',
encodeURIComponent(imagePath),
'&id=',
id,
'&status=',
].join('');
postMan.post(data);
}
// release the memory
page.close();
});
}
var postMan = {
postPage: null,
posting: false,
datas: [],
len: 0,
currentNum: 0,
init: function (snapshot) {
var postPage = webpage.create();
postPage.customHeaders = {
'secret': pkg.secret
};
postPage.open('http://localhost:' + pkg.port + '/bridge?campaignId=' + campaignId, function () {
var urls = JSON.parse(postPage.plainText).urls
, url;
this.len = urls.length;
if (this.len) {
for (var i = this.len; i--;) {
url = urls[i];
snapshot(url.id, url.url , url.imagePath);
}
}
});
this.postPage = postPage;
},
post: function (data) {
this.datas .push(data);
if (!this.posting) {
this.posting = true;
this.fire();
}
},
fire: function () {
if (this.datas.length) {
var data = this.datas.shift()
, that = this;
this.postPage.open('http:// localhost:' pkg.port '/bridge', 'POST', data, function () {
that.fire();
// 子プロセスを強制終了
setTimeout(function () {
if ( this.currentNum === this.len) {
that.postPage.close();
phantom.exit();
}
}, 500);
}) ;
} else {
this.posting = false;
}
}
};
postMan.init(snapshot);
效果
