MATLAB | 如何使用MATLAB获取顶刊cell全部绘图(附带近3年全部图像)

news2024/10/5 16:28:09

众所周知，学习科研绘图、配色最好的办法就是去观摩顶级期刊上的作图，本来想着收集各个顶级期刊绘图提供给大家，但是每年的图像加起来大约3-5G，撑死也就能提供三四年的图像，再多内存可能不太够了，于是我写了一段杷虫代码，可以下载任意册期刊的全部图像，运行就命令行运行例如getCellJPG(185)，就可以下载第185册(2022)的全部图像，这段代码也不算长，就放这吧(我杷虫代码功底属实一般，大家见谅)：

function getCellJPG(volume)
if nargin < 1
volume = 184;
end

url_archive0   = 'https://www.cell.com/cell/issues';
html_archive   = urlread(url_archive0);
A_html_archive = strfind(html_archive,'data-groupid');
Z_html_archive = strfind(html_archive,['>Volume ',num2str(volume)]);
url_archiven   = html_archive(A_html_archive(find(A_html_archive<Z_html_archive,1,'last')):Z_html_archive);
url_archiven   = url_archiven(15:end-59);

url_archive1   = 'https://www.cell.com/cell/archive?issueGroupId=';
url_archive2   = '&publicationCode=cell';
url_archive    = [url_archive1,url_archiven,url_archive2];

html_archive   = urlread(url_archive);
A_html_archive = strfind(html_archive,['Volume ',num2str(volume)]);
Z_html_archive = strfind(html_archive,'archive?publicationCode=cell');
Z_html_archive = Z_html_archive(find(Z_html_archive>A_html_archive,1));
html_archive   = html_archive(A_html_archive:Z_html_archive);

A_issue = strfind(html_archive,'<a href=');
Z_issue = strfind(html_archive,'">');

ibegin = 1; jbegin = 1; kbegin = 1;
forderName=['Volume_',num2str(volume)];
if exist(['.\image_',forderName,'\ijkbreak.mat'],'file')
    load(['.\image_',forderName,'\ijkbreak.mat']);
end
if ~exist(['.\image_',forderName],'dir')
    mkdir(['.\image_',forderName]);
end
disp([ibegin,jbegin,kbegin])

for i = ibegin:length(A_issue)
    url_issue    = html_archive(A_issue(i):Z_issue(find(Z_issue>A_issue(i),1)));
    url_issue    = url_issue(10:end-1);
    html_issue   = urlread(['https://www.cell.com',url_issue]);
    A_html_issue = strfind(html_issue,'id="Articles"');
    Z_html_issue = strfind(html_issue,'The content on this site');
    html_issue   = html_issue(A_html_issue:Z_html_issue);

    A_article = strfind(html_issue,'class="toc__item__title"');
    Z_article = strfind(html_issue,'">');

    for j = jbegin:length(A_article)

        url_article  = html_issue(A_article(j):Z_article(find(Z_article>A_article(j)+30,2)));
        url_article  = url_article(50:end-1);
        html_article = urlread(['https://www.cell.com/cell/fulltext/',url_article]);

        A_jpg = strfind(html_article,'<a href="');
        Z_jpg = strfind(html_article,'download-links__download-Hi-res');

        for k = kbegin:length(Z_jpg)
            ibegin = i ; jbegin = j; kbegin = k;
            save(['.\image_',forderName,'\ijkbreak.mat'],'ibegin','jbegin','kbegin')
            url_jpg  = html_article(A_jpg(find(A_jpg<Z_jpg(k),1,'last')):Z_jpg(k));
            url_jpg  = ['https://www.cell.com',url_jpg(10:end-10)];
            name_jpg = ['.\image_',forderName,'\',url_article,' P',num2str(k)];
            websave(name_jpg,url_jpg);
            disp(['Downloading Volume-',num2str(volume),...
                ' Issue-',num2str(i),' Artical-',num2str(j),...
                ' Pic-',num2str(k),':',url_article])

        end
        kbegin = 1;
    end
    jbegin = 1;
end
end