for a folder of pdfs find the doi and look up the websites in matlab

main.m
folder = 'path/to/folder'; % Update with the actual path to the folder
pdfFiles = dir(fullfile(folder, '*.pdf'));

for i = 1:numel(pdfFiles)
    pdfPath = fullfile(folder, pdfFiles(i).name);
    % Read the PDF file using your preferred method (e.g., 'pdf2image' or 'pdfRead')
    % Process each page if needed
end
314 chars
9 lines

main.m
% Use suitable function/library to extract text from the PDF pages
textPages = extractTextFromPDF(pdfPath); % Replace with actual function/library call
152 chars
3 lines

main.m
dois = cell(numel(textPages), 1);
for page = 1:numel(textPages)
    % Use regular expressions to search for DOI patterns in the text
    doiPattern = '(10\.\d{4,}(?:\.\d+)*\/\S+)';
    dois{page} = regexp(textPages{page}, doiPattern, 'match');
end
248 chars
7 lines

main.m
websites = cell(numel(dois), 1);
for i = 1:numel(dois)
    if ~isempty(dois{i}) % If DOI is found
        doi = dois{i}{1};
        % Use a suitable method (e.g., web scraping or using APIs) to look up the website using the DOI
        website = lookUpWebsite(doi); % Replace with actual method to look up the website
        websites{i} = website;
    end
end
361 chars
10 lines