首先按照示例尝试
1.首先定义需要的包
var fs = require('fs');
var myRequest = require('request')
var myCheerio = require('cheerio')//获取element内容
var myIconv = require('iconv-lite')//转码
require('date-utils');//解析日期
2.定义所爬取的种子界面
var source_name = "中国新闻网";
var domain = 'http://www.chinanews.com/';
var myEncoding = "utf-8";
var seedURL = 'http://www.chinanews.com/';
3.定义新闻页面具体元素读取方法,如date_formate在网页中是按照span id="pubtime_baidu"存储
var seedURL_format = "$('a')";//需要取出所有a的链接
var keywords_format = " $('meta[name=\"keywords\"]').eq(0).attr(\"content\")";//从header里面把keywords拿出来放到里面去,<meta name="keywords" content="。。。">
var title_format = "$('title').text()";
var date_format = "$('#pubtime_baidu').text()";//<span id="pubtime_baidu">2020-05-07 09:48:53</span>
var author_format = "$('#editor_baidu').text()";//<span id="editor_baidu">责任编辑:陈海峰</span>
var content_format = "$('.left_zw').text()";//<div class="left_zw">
var desc_format = " $('meta[name=\"description\"]').eq(0).attr(\"content\")";
var source_format = "$('#source_baidu').text()";
var url_reg = /\/(\d{4})\/(\d{2})-(\d{2})\/(\d{7}).shtml/;
var regExp = /((\d{4}|\d{2})(\-|\/|\.)\d{1,2}\3\d{1,2})|(\d{4}年\d{1,2}月\d{1,2}日)/
var fs = require('fs');
var myRequest = require('request')
var myCheerio = require('cheerio')//获取element内容
var myIconv = require('iconv-lite')//转码
require('date-utils');//解析日期
4.模仿浏览器request
4.1 request需要模伪装成仿浏览器,防止被屏蔽
//user-agent:显示是什么浏览器
var headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.65 Safari/537.36'
}
//request模块异步fetch url
function request(url, callback) {
var options = {
url: url,
encoding: null,
//proxy: 'http://x.x.x.x:8080',//过代理
headers: headers,
timeout: 10000 //
}
myRequest(options, callback)
}
4.2 读取种子页面,并爬取种子页面下的所有网页
request(seedURL, function(err, res, body) { //读取种子页面
// try {
//用iconv转换编码
var html = myIconv.decode(body, myEncoding);
//console.log(html);
//准备用cheerio解析html
var $ = myCheerio.load(html, { decodeEntities: true });
// } catch (e) { console.log('读种子页面并转码出错:' + e) };
var seedurl_news;
try {
seedurl_news = eval(seedURL_format);//取出所有a——href的链接
//console.log(seedurl_news);
} catch (e) { console.log('url列表所处的html块识别出错:' + e) };
seedurl_news.each(function(i, e) { //遍历种子页面里所有的a链接
var myURL = "";
try {
//得到具体新闻url
var href = "";
href = $(e).attr("href");
if (href.toLowerCase().indexOf('http://') >= 0) myURL = href; //http://开头的 绝对路径方式
else if (href.startsWith('//')) myURL = 'http:' + href; 开头的 相对路径 需要转换成绝对路径
else myURL = seedURL.substr(0, seedURL.lastIndexOf('/') + 1) + href; //其他
} catch (e) { console.log('识别种子页面中的新闻链接出错:' + e) }
if (!url_reg.test(myURL)) return; //检验是否符合新闻url的正则表达式,符合就用newsget读取
//console.log(myURL);
newsGet(myURL); //读取新闻页面
});
});
4.3 读取页面并进行格式化存储成js文件
function newsGet(myURL) { //读取新闻页面
request(myURL, function(err, res, body) { //读取新闻页面
//try {
var html_news = myIconv.decode(body, myEncoding); //用iconv转换编码
//console.log(html_news);
//准备用cheerio解析html_news
var $ = myCheerio.load(html_news, { decodeEntities: true });
myhtml = html_news;
//} catch (e) { console.log('读新闻页面并转码出错:' + e);};
console.log("转码读取成功:" + myURL);
//动态执行format字符串,构建json对象准备写入文件或数据库
var fetch = {};//构造空的fetch对象,用来存title、content、url等等
fetch.title = "";
fetch.content = "";
fetch.publish_date = (new Date()).toFormat("YYYY-MM-DD");
//fetch.html = myhtml;
fetch.url = myURL;
fetch.source_name = source_name;
fetch.source_encoding = myEncoding; //编码
fetch.crawltime = new Date();//爬取时间
if (keywords_format == "") fetch.keywords = source_name; // eval(keywords_format); //没有关键词就用sourcename
else fetch.keywords = eval(keywords_format);
if (title_format == "") fetch.title = ""
else fetch.title = eval(title_format); //标题
if (date_format != "") fetch.publish_date = eval(date_format); //刊登日期
console.log('date: ' + fetch.publish_date);
fetch.publish_date = regExp.exec(fetch.publish_date)[0];
fetch.publish_date = fetch.publish_date.replace('年', '-')
fetch.publish_date = fetch.publish_date.replace('月', '-')
fetch.publish_date = fetch.publish_date.replace('日', '')
fetch.publish_date = new Date(fetch.publish_date).toFormat("YYYY-MM-DD");
if (author_format == "") fetch.author = source_name; //eval(author_format); //作者
else fetch.author = eval(author_format);
if (content_format == "") fetch.content = "";
else fetch.content = eval(content_format).replace("\r\n" + fetch.author, ""); //内容,是否要去掉作者信息自行决定
if (source_format == "") fetch.source = fetch.source_name;
else fetch.source = eval(source_format).replace("\r\n", ""); //来源
if (desc_format == "") fetch.desc = fetch.title;
else fetch.desc = eval(desc_format).replace("\r\n", ""); //摘要
var filename = source_name + "_" + (new Date()).toFormat("YYYY-MM-DD") +
"_" + myURL.substr(myURL.lastIndexOf('/') + 1) + ".json";
存储json
fs.writeFileSync(filename, JSON.stringify(fetch));
});
}
最终结果