nodejs express cheerio request爬虫
const express = require('express')
const cheerio = require('cheerio')
const request = require("request")
const app = express()
app.get("/:key", function (req, res) {
let spider = new Spider()
console.log(req.params.key)
spider.fetch("http://www.baidu.com/s?wd=" + req.params.key, (err, $) => {
spider.parse(err, $, res)
})
})
app.post('/postData', function (req, res) { //这里参数加上刚刚的解析的而且这里不是get了
let result = req.body
res.send(result);
})
app.listen(3000, () => {
console.log("开启服务，端口3000")
})
class Spider {
fetch(url, callback) {
request({url: url, encoding: null}, (err, response, body) => {
if (!err && response.statusCode === 200) {
callback(null, cheerio.load('<body>' + body + '</body>'));
} else {
callback(err, cheerio.load('<body></body>'));
}
})
}
parse(err, $, res) {
if (!err) {
let result = $('body').find("#content_left").html()
res.send(result)
}
}
}
封装request
class Spider {
fetch(url, method = "GET") {
return new Promise((resolve, reject) => {
var option = {
url: url,
method: method,
headers: {
"user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.128 Safari/537.36",
},
}
if (method == "POST") {
option = {
url: url,
method: method,
headers: {
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.114 Safari/537.36',
'cookie': 'JUTE_SESSION_ID='
},
body: "{}"
}
}
request(option, function (error, response, body) {
if (!error && response.statusCode == 200) {
resolve(body)
}
});
});
}
}
