@nosferatu500/textract/lib/extractors/epub.js

Extracting text from files of various type including html, pdf, doc, docx, xls, xlsx, csv, pptx, png, jpg, gif, rtf, text/*, and various open office.

const EPub = require("epub2/node");
const htmlExtract = require("./html");

function extractText(filePath, options, cb) {
    const epub = new EPub(filePath);
    let allText = "";
    let hasError = false;
    let chapterCount = 0;
    epub.on("end", function () {
        // Iterate over each chapter...
        for (const chapter of epub.flow) {
            // if already error, don't do anything
            if (!hasError) {
                // Get the chapter text
                epub.getChapterRaw(chapter.id, function (rawChaperError, text) {
                    if (rawChaperError) {
                        hasError = true;
                        cb(rawChaperError, null);
                    } else {
                        // Extract the raw text from the chapter text (it's html)
                        htmlExtract.extractFromText(text, options, function (htmlExtractError, outText) {
                            if (htmlExtractError) {
                                hasError = true;
                                cb(htmlExtractError, null);
                            } else {
                                allText += outText;
                                chapterCount++;
                                if (chapterCount === epub.flow.length) {
                                    cb(null, allText);
                                }
                            }
                        });
                    }
                });
            }
        }
    });

    epub.parse();
}

module.exports = {
    types: ["application/epub+zip"],
    extract: extractText,
};