MATLAB | 如何使用MATLAB获取顶刊《Nature》全部绘图(附带近3年全部图像)-Toy模板网

这篇具有很好参考价值的文章主要介绍了MATLAB | 如何使用MATLAB获取顶刊《Nature》全部绘图(附带近3年全部图像)。希望对大家有所帮助。如果存在错误或未考虑完全的地方，请大家不吝赐教，您也可以点击"举报违法"按钮提交疑问。

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

我出了如何使用MATLAB获取期刊《Cell》全部绘图，立马就有粉丝问《Nature》、《Sience》、《PNAS》啥的会不会安排，这期就给大家安排《Nature》全部绘图获取，之后其他期刊也会慢慢安排，但是不会一次性全出完(毕竟不能抓住一个主题就狠更)。

由于《Nature》绘图获取需要科学上网让自己位置变到美国，不然下载就会巨慢，因此建议直接去文末拿图像压缩包，每年的图像压缩包大约2G大小，搜集了近三年一万多张图。

杷虫代码也放一下叭，使用方法很简单，例如下载2022年图片，就命令行窗口运行getNaturePNGWhileTure(2022)：

function getNaturePNGWhileTure(YEAR)
if nargin < 1
    YEAR = 2023;
end

pbegin = 1; ibegin = 1; jbegin = 1; 
forderName=['Year_',num2str(YEAR)];
if exist(['.\image_',forderName,'\pijbreak.mat'],'file')
    load(['.\image_',forderName,'\pijbreak.mat']);
end
if ~exist(['.\image_',forderName],'dir')
    mkdir(['.\image_',forderName]);
end
disp([pbegin,ibegin,jbegin])

url_full = 'https://www.nature.com/nature/research-articles?searchType=journalSearch&sort=PubDate&year=<Y/>&page=<P/>';
url_year = strrep(url_full,'<Y/>',num2str(YEAR));

options=weboptions('Timeout',inf);
html_year  = webread(strrep(url_year,'<P/>','1'),options);fprintf('1->')
A_page_num = strfind(html_year,'u-visually-hidden'); 
Z_page_num = strfind(html_year,'data-page="next"');
page_num   = html_year(A_page_num(find(A_page_num<Z_page_num,1,'last')):Z_page_num);
page_num   = page_num(32:36);
page_num   = str2double(page_num(abs(page_num)<=57&abs(page_num)>=48));

for p = pbegin:page_num
    url_page  = strrep(url_year,'<P/>',num2str(p));
    html_page = webread(url_page,options);fprintf('2\n')
    A_html_artical = strfind(html_page,'itemprop="name headline"');
    Z_html_artical = strfind(html_page,'data-track-action="view article"');

    for i = ibegin:length(Z_html_artical)
        html_artical = html_page(A_html_artical(find(A_html_artical<Z_html_artical(i),1,'last')):Z_html_artical(i));
        A_artical    = strfind(html_artical,'<a href=');
        Z_artical    = strfind(html_artical,'class="c-card__link u-link-inherit"');
        html_artical = html_artical(A_artical(1)+10:Z_artical);
        html_artical = html_artical(1:find(html_artical=='"')-1);

        for j = jbegin:50
            pbegin = p; ibegin = i ; jbegin = j;
            save(['.\image_',forderName,'\pijbreak.mat'],'pbegin','ibegin','jbegin')
            html_png=webread(['https://www.nature.com/',html_artical,'/figures/',num2str(j)]);
            A_png        = strfind(html_png,'aria-describedby');
            Z_png        = strfind(html_png,'alt="Fig.');
            
            if isempty(Z_png)
                break;
            else
                url_png  = html_png(A_png:Z_png(find(Z_png>A_png,1)));
                url_png  = ['https:',url_png(strfind(url_png,'src="')+5:end-3)];
                url_png  = strrep(url_png,'lw685','full');
                name_png = ['.\image_',forderName,'\',html_artical(10:end),' P',num2str(j)];
                websave(name_png,url_png,options);
            disp(['Downloading Year-',num2str(YEAR),...
                ' Page-',num2str(p),' Artical-',num2str(i),...
                ' Pic-',num2str(j),':',html_artical])
            end
        end
        jbegin = 1;
    end
    ibegin = 1;
end
end