乐趣区

关于javascript:前端常规sao操作之我用opencvjs识别爬取的乐谱图片二维码位置并覆盖

jiezi

前言：有一天，产品经理贱兮兮的跟你说：“咱们看到一个挺好的搜谱小程序，咱们来仿一个吧，爬出他们的数据来，放到咱们库里”

没方法，搞吧！！！！！！

爬数据

剖析小程序接口

首先安利一个好用的 ios 零碎收费抓包软件：stream

通过剖析指标小程序接口发现，有一个接口能够获取单个详情，并且发现每个乐谱的 id 是自增的，，啧啧！这就好说了啊

上代码 

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

const getDetil = (id) => {
    // 获取 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 万左右就没有了，总共爬了 9 万条数据

剖析数据

通过剖析发现，每张乐谱都有竞品小程序二维码，这样的必定不行

这样就不能搞一个脚本去固定贴二维码了，！！！

opencvjs 辨认二维码

不说了上 opencv 辨认二维码啊, 先整个 html 测试下，具体 opencvjs 辨认原理我打算稍后独自出一个文章解释

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);
            // 轮廓筛选
            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)
                // }
                // 找到定位点信息
                if (ic == 2) {//let cnt = matVec.get(0);
                    contours2.push_back(contours.get(parentIdx));
                    ic = 0;
                    parentIdx = -1;
                }

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

            // 填充定位点
            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>

启动

抉择一个乐谱上传

看到三个回型。阐明辨认胜利

接下来就是下载图片。定位地位。用 canvas 贴上咱们二维码。入库～

好啦～，产品经理的需要就这么欢快的搞定了！

退出移动版