前端常規(sao)操做之：我用opencvjs識別爬取的曲譜圖片二維碼位置並覆蓋

時間 2020-12-31

標籤 javascript html java ios c++ shell canvas 小程序 api app 欄目 JavaScript 简体版

原文原文鏈接

前言：有一天，產品經理賤兮兮的跟你說：「咱們看到一個挺好的搜譜小程序，咱們來仿一個吧，爬出他們的數據來，放到咱們庫裏」

沒辦法，搞吧！！！！！！javascript

爬數據

分析小程序接口

首先安利一個好用的ios系統免費抓包軟件： streamhtml

經過分析目標小程序接口發現，有一個接口能夠獲取單個詳情，而且發現每一個曲譜的id是自增的，，嘖嘖！這就好說了啊java

上代碼

const shell = require('shelljs')
const fs = require('fs')

const getDetil = (id) => {
    // 獲取curl
    let curl = `curl 'https://api.quxuege.com/search/one?id=${id}'  -H 'Host: api.quxuege.com'  -H 'Accept: */*'  -H 'Content-Type: application/x-www-form-urlencoded'  -H 'Accept-Encoding: gzip, deflate, br'  -H 'Connection: keep-alive'  -H 'Cookie: '  -H 'User-Agent: Mozilla/5.0 (iPhone; CPU iPhone OS 14_0 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Mobile/15E148 MicroMessenger/7.0.15(0x17000f31) NetType/WIFI Language/zh_CN'  -H 'Referer: https://servicewechat.com/wx21c9c829a9ecfc04/8/page-frame.html'  -H 'token: '  -H 'Accept-Language: zh-cn'`
    const res = JSON.parse(shell.exec(curl).stdout)

    if (res.code === 200) {
        const p = res.data
        if (p && p.id) {
            let t = [p.id, p.title, p.createTime, p.details[0].image]
            fs.appendFileSync('sopu.txt', `${t.join(',')}\n`)
        }
    }
}

for (let i = 101042; i < 199999; i++) {
    getDetil(i)
}

id爬到20萬左右就沒有了，總共爬了9萬條數據ios

分析數據

通過分析發現，每張曲譜都有競品小程序二維碼，這樣的確定不行

這樣就不能搞一個腳本去固定貼二維碼了，！！！c++

opencvjs識別二維碼

不說了上opencv識別二維碼啊,先整個html測試下，具體opencvjs識別原理我計劃稍後單獨出一個文章解釋

引入opencvjs

<script async src="opencv.js" onload="onOpenCvReady();" type="text/javascript"></script>

<!DOCTYPE html>
<html>

<head>
    <meta charset="utf-8">
    <title>Hello OpenCV.js</title>
    <script async src="opencv.js" onload="onOpenCvReady();" type="text/javascript"></script>
</head>

<body>
    <h2>Hello OpenCV.js</h2>
    <p id="status">OpenCV.js is loading...</p>
    <div>
        <div class="inputoutput">
            <img id="imageSrc" alt="No Image" />
            <div class="caption">imageSrc <input type="file" id="fileInput" name="file" /></div>
        </div>
        <div class="inputoutput">
            <canvas id="canvasOutput"></canvas>
            <div class="caption">canvasOutput</div>
        </div>
        <div class="inputoutput2">
            <canvas id="canvasOutput2"></canvas>
            <div class="caption">canvasOutput2</div>
        </div>
    </div>
    <script type="text/javascript">
        let imgElement = document.getElementById('imageSrc');
        let inputElement = document.getElementById('fileInput');
        inputElement.addEventListener('change', (e) => {
            imgElement.src = URL.createObjectURL(e.target.files[0]);
        }, false);
        imgElement.onload = function (e) {
            console.log(imgElement);
            let src = cv.imread(imgElement);
            let src_clone = cv.imread(imgElement);
            let dsize = new cv.Size(800, 1000);
            // You can try more different parameters
            cv.resize(src, src, dsize); cv.resize(src_clone, src_clone, dsize);
            let dst = cv.Mat.zeros(src.rows, src.cols, cv.CV_8UC3);
            cv.cvtColor(src, src, cv.COLOR_RGBA2GRAY, 0);
            let ksize = new cv.Size(1, 1);
            // You can try more different parameters 
            cv.blur(src, src, ksize);

            cv.threshold(src, src, 0, 255, cv.THRESH_OTSU);
            let contours = new cv.MatVector();
            let contours2 = new cv.MatVector();
            let hierarchy = new cv.Mat();
            // You can try more different parameters
            cv.findContours(src, contours, hierarchy, cv.RETR_TREE, cv.CHAIN_APPROX_NONE);
            //輪廓篩選
            let c = 0, ic = 0, area = 0;
            let parentIdx = -1;
            for (let i = 0; i < contours.size(); i++) {
                //let hier = hierarchy.intPtr(0, i)
                // console.log(hierarchy.intPtr(0, i))
                if (hierarchy.intPtr(0, i)[2] != -1 && ic == 0) {
                    parentIdx = i;
                    ic++;
                }
                else if (hierarchy.intPtr(0, i)[2] != -1) {
                    console.log(hierarchy.intPtr(0, i))
                    ic++;
                }
                else if (hierarchy.intPtr(0, i)[2] == -1) {
                    ic = 0;
                    parentIdx = -1;
                }

                // if (ic == 2) {
                //     console.log(parentIdx, i)
                // }
                //找到定位點信息
                if (ic == 2) {
                    //let cnt = matVec.get(0);
                    contours2.push_back(contours.get(parentIdx));
                    ic = 0;
                    parentIdx = -1;
                }

            }
            console.log(contours2.size());

            //填充定位點
            for (let i = 0; i < contours.size(); i++) {
                let color = new cv.Scalar(255, 0, 0, 255);
                cv.drawContours(src_clone, contours, i, color, 1);
            }
            cv.imshow('canvasOutput', src_clone);

            for (let i = 0; i < contours2.size(); i++) {
                let color = new cv.Scalar(Math.round(Math.random() * 255), Math.round(Math.random() * 255),
                    Math.round(Math.random() * 255));
                    console.log(contours2)
                cv.drawContours(dst, contours2, i, color, 1);
            }
            cv.imshow('canvasOutput2', dst);
            src.delete(); src_clone.delete();
            dst.delete(); contours.delete(); hierarchy.delete();

        };
        function onOpenCvReady() {
            document.getElementById('status').innerHTML = 'OpenCV.js is ready.';
        }
    </script>

</body>

</html>