Last active
August 29, 2015 14:01
-
-
Save myjian/290f1531dd873b362e5a to your computer and use it in GitHub Desktop.
CCSP-HW4
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
var request = require('request'); | |
var cheerio = require('cheerio'); | |
var fs = require('fs'); | |
var appledailyURL = [ | |
'http://www.appledaily.com.tw/realtimenews/section/new/1', | |
'http://www.appledaily.com.tw/realtimenews/section/new/2', | |
'http://www.appledaily.com.tw/realtimenews/section/new/3', | |
'http://www.appledaily.com.tw/realtimenews/section/new/4', | |
'http://www.appledaily.com.tw/realtimenews/section/new/5']; | |
var categorizedNewsFile = 'appledaily.json'; | |
var news = []; | |
var categories = []; | |
var retrieved = 0; | |
function responseHandler(err, response, body){ | |
retrieved++; | |
if (!err && response.statusCode === 200){ | |
var $ = cheerio.load(body); | |
$('li.rtddt').each(function(i, element){ | |
var category = $(this).find('h2').text(); | |
var url = $(this).children('a').attr('href'); | |
var date = $(this).parent().prev().children('time').text(); | |
var time = $(this).find('time').text(); | |
var title = $(this).find('font').text(); | |
var hasVideo = $(this).hasClass('hsv'); | |
var newsItem = {category: category, title: title, date: date, url: url, time: time, video: hasVideo}; | |
news.push(newsItem); | |
if (categories.indexOf(category) === -1){ | |
categories.push(category); | |
} | |
}); | |
} | |
setTimeout(function(){sendRequest(retrieved)}, 100); | |
} | |
function sendRequest(i){ | |
if (i === appledailyURL.length){ | |
finish(); | |
} | |
else { | |
request(appledailyURL[i], responseHandler); | |
} | |
} | |
sendRequest(0); | |
function finish(){ | |
var categorizedNews = []; | |
categories.forEach(function(element, index, array){ | |
this.push({category: element, news: []}); | |
}, categorizedNews); | |
news.forEach(function(element, index, array){ | |
var categoryIdx = categories.indexOf(element.category); | |
this[categoryIdx].news.push({title: element.title, url: element.url, time: element.time, video: element.video}); | |
}, categorizedNews); | |
var mostNewsNumber = 0; | |
var mostNewsCategory = 0; | |
categorizedNews.forEach(function(element, index, array){ | |
element.news_count = element.news.length; | |
if (element.news_count > mostNewsNumber){ | |
mostNewsCategory = index; | |
mostNewsNumber = element.news_count; | |
} | |
}); | |
console.log(new Date()); | |
console.log('數量最多的分類為 [' + categories[mostNewsCategory] + '],共有 ' + mostNewsNumber + ' 則新聞'); | |
fs.writeFileSync(categorizedNewsFile, JSON.stringify(categorizedNews, null, 4)); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment