Actual code for downloading and generating EPUB

This commit is contained in:
Nemo 2020-01-11 00:41:49 +05:30
parent 5a3d84924a
commit 3f73dd4c31
4 changed files with 295 additions and 37 deletions

52
generate.js Normal file
View File

@ -0,0 +1,52 @@
const AP = require("article-parser");
const tempFile = require("tempfile");
const nodePandoc = require("node-pandoc-promise");
const fs = require("fs");
const { DownloaderHelper } = require("node-downloader-helper");
const getArticle = async url => {
try {
const article = await AP.extract(url);
return article;
} catch (err) {
console.trace(err);
}
};
module.exports = (url, epubPath) => {
getArticle(url).then(res => {
let xml = `<dc:title id="epub-title-1">${res.title}</dc:title>
<dc:date>${res.published}</dc:date>
<dc:language>en-US</dc:language>
<dc:creator id="epub-creator-1" opf:role="aut">${res.author}</dc:creator>`;
let html = tempFile(".html");
let metadata = tempFile(".xml");
fs.writeFileSync(html, res.content);
fs.writeFileSync(metadata, xml);
const imageUrl = res.image;
const dl = new DownloaderHelper(res.image, "/tmp", {
fileName: "epub-to-image.jpg"
});
dl.start();
dl.on("end", () => {
nodePandoc(html, [
"-o",
epubPath,
`--epub-cover-image=/tmp/epub-to-image.jpg`,
`--epub-metadata=${metadata}`
])
.then(res => {
console.log(`Generated EPUB file at ${epubPath}`);
})
.catch(err => {
console.error("Oh No: ", err);
});
});
});
};

58
index.js Normal file → Executable file
View File

@ -1,34 +1,26 @@
const AP = require('article-parser');
var nodePandoc = require('node-pandoc-promise');
#!/usr/bin/env node
var argv = require("yargs").argv;
const generateEPUB = require("./generate");
const url = process.argv[2];
const getArticle = async (url) => {
try {
const article = await AP.extract(url);
return article;
} catch (err) {
console.trace(err);
}
};
getArticle(url).then(res=>{
`
<dc:title id="epub-title-1">${res.title}</dc:title>
<dc:date>${res.published}</dc:date>
<dc:language>en-US</dc:language>
<dc:creator id="epub-creator-1" opf:role="aut">${res.author}</dc:creator>
`
// TODO: Write res.content into a temp file
const imageUrl = res.image
nodePandoc(tmpFile, ['-o', 'filel.epub', '--epbu-cover-image', 'file.png', '--epub-metadata=something.xml'])
.then(res=>{
console.log(res);
}).catch(err=>{
console.error('Oh No: ',err);
});
})
require("yargs") // eslint-disable-line
.usage("$0 --output [output] <url>")
.help("h")
.command("$0 <url>", "Generate EPUB file from URL", yargs => {
yargs
.positional("url", {
describe: "The URL to download",
type: "string"
})
.option("output", {
alias: "o",
type: "string",
default: "url-to-epub.epub",
description: "Output file to save EPUB"
})
.example(
'$0 -o articulated-restraint.epub "https://www.tor.com/2019/02/06/articulated-restraint-mary-robinette-kowal/"'
)
.demandOption(["url"]);
}, (argv) => {
generateEPUB(argv.url, argv.output)
}).argv;

211
package-lock.json generated
View File

@ -4,6 +4,11 @@
"lockfileVersion": 1,
"requires": true,
"dependencies": {
"@types/color-name": {
"version": "1.1.1",
"resolved": "https://registry.npmjs.org/@types/color-name/-/color-name-1.1.1.tgz",
"integrity": "sha512-rr+OQyAjxze7GgWrSaJwydHStIhHq2lvY3BOC2Mj7KnzI7XK0Uw1TOOdI9lDoajEbSWLiYgoo4f1R51erQfhPQ=="
},
"@types/node": {
"version": "13.1.4",
"resolved": "https://registry.npmjs.org/@types/node/-/node-13.1.4.tgz",
@ -38,6 +43,11 @@
"uri-js": "^4.2.2"
}
},
"ansi-regex": {
"version": "5.0.0",
"resolved": "https://registry.npmjs.org/ansi-regex/-/ansi-regex-5.0.0.tgz",
"integrity": "sha512-bY6fj56OUQ0hU1KjFNDQuJFezqKdrAyFdIevADiqrWHwSlbmBNMHp5ak2f40Pm8JTFyM2mqxkG6ngkHO11f/lg=="
},
"ansi-styles": {
"version": "3.2.1",
"resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-3.2.1.tgz",
@ -129,6 +139,11 @@
"upper-case": "^1.1.1"
}
},
"camelcase": {
"version": "5.3.1",
"resolved": "https://registry.npmjs.org/camelcase/-/camelcase-5.3.1.tgz",
"integrity": "sha512-L28STB170nwWS63UjtlEOE3dldQApaJXZkOI1uMFfzf3rRuPegHaHesyee+YxQ+W6SvRDQV6UrdOdRiR153wJg=="
},
"caseless": {
"version": "0.12.0",
"resolved": "https://registry.npmjs.org/caseless/-/caseless-0.12.0.tgz",
@ -165,6 +180,16 @@
"source-map": "~0.6.0"
}
},
"cliui": {
"version": "6.0.0",
"resolved": "https://registry.npmjs.org/cliui/-/cliui-6.0.0.tgz",
"integrity": "sha512-t6wbgtoCXvAzst7QgXxJYqPt0usEfbgQdftEPbLL/cvv6HPE5VgvqCuAIDR0NgU52ds6rFwqrgakNLrHEjCbrQ==",
"requires": {
"string-width": "^4.2.0",
"strip-ansi": "^6.0.0",
"wrap-ansi": "^6.2.0"
}
},
"color-convert": {
"version": "1.9.3",
"resolved": "https://registry.npmjs.org/color-convert/-/color-convert-1.9.3.tgz",
@ -246,6 +271,11 @@
"ms": "^2.1.1"
}
},
"decamelize": {
"version": "1.2.0",
"resolved": "https://registry.npmjs.org/decamelize/-/decamelize-1.2.0.tgz",
"integrity": "sha1-9lNNFRSCabIDUue+4m9QH5oZEpA="
},
"deep-is": {
"version": "0.1.3",
"resolved": "https://registry.npmjs.org/deep-is/-/deep-is-0.1.3.tgz",
@ -296,6 +326,11 @@
"safer-buffer": "^2.1.0"
}
},
"emoji-regex": {
"version": "8.0.0",
"resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-8.0.0.tgz",
"integrity": "sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A=="
},
"entities": {
"version": "1.1.2",
"resolved": "https://registry.npmjs.org/entities/-/entities-1.1.2.tgz",
@ -372,6 +407,15 @@
"resolved": "https://registry.npmjs.org/fast-levenshtein/-/fast-levenshtein-2.0.6.tgz",
"integrity": "sha1-PYpcZog6FqMMqGQ+hR8Zuqd5eRc="
},
"find-up": {
"version": "4.1.0",
"resolved": "https://registry.npmjs.org/find-up/-/find-up-4.1.0.tgz",
"integrity": "sha512-PpOwAdQ/YlXQ2vj8a3h8IipDuYRi3wceVQQGYWxNINccq40Anw7BlsEXCMbt1Zt+OLA6Fq9suIpIWD0OsnISlw==",
"requires": {
"locate-path": "^5.0.0",
"path-exists": "^4.0.0"
}
},
"forever-agent": {
"version": "0.6.1",
"resolved": "https://registry.npmjs.org/forever-agent/-/forever-agent-0.6.1.tgz",
@ -387,6 +431,11 @@
"mime-types": "^2.1.12"
}
},
"get-caller-file": {
"version": "2.0.5",
"resolved": "https://registry.npmjs.org/get-caller-file/-/get-caller-file-2.0.5.tgz",
"integrity": "sha512-DyFP3BM/3YHTQOCUL/w0OZHR0lpKeGrxotcHWcqNEdnltqFwXVfhEBQ94eIo34AfQpo0rGki4cyIiftY06h2Fg=="
},
"getpass": {
"version": "0.1.7",
"resolved": "https://registry.npmjs.org/getpass/-/getpass-0.1.7.tgz",
@ -477,6 +526,11 @@
"resolved": "https://registry.npmjs.org/inherits/-/inherits-2.0.4.tgz",
"integrity": "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ=="
},
"is-fullwidth-code-point": {
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/is-fullwidth-code-point/-/is-fullwidth-code-point-3.0.0.tgz",
"integrity": "sha512-zymm5+u+sCsSWyD9qNaejV3DFvhCKclKdizYaJUuHA83RLjb7nSuGnddCHGv0hk+KY7BMAlsWeK4Ueg6EV6XQg=="
},
"is-typedarray": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/is-typedarray/-/is-typedarray-1.0.0.tgz",
@ -560,6 +614,14 @@
"type-check": "~0.3.2"
}
},
"locate-path": {
"version": "5.0.0",
"resolved": "https://registry.npmjs.org/locate-path/-/locate-path-5.0.0.tgz",
"integrity": "sha512-t7hw9pI+WvuwNJXwk5zVHpyhIqzg2qTlklJOf0mVxGSbe3Fp2VieZcduNYjaLDoy6p9uGpQEGWG87WpMKlNq8g==",
"requires": {
"p-locate": "^4.1.0"
}
},
"lodash": {
"version": "4.17.15",
"resolved": "https://registry.npmjs.org/lodash/-/lodash-4.17.15.tgz",
@ -629,6 +691,11 @@
"lower-case": "^1.1.1"
}
},
"node-downloader-helper": {
"version": "1.0.11",
"resolved": "https://registry.npmjs.org/node-downloader-helper/-/node-downloader-helper-1.0.11.tgz",
"integrity": "sha512-43vhEpmyTdU2OyVUHlOMqKUYbA8ryzpDdlqg4l2/AHhrl+EgRdEv+fAcH4Fk+KfEHPyx+uYK0OH9nJMC40pSDQ=="
},
"node-fetch": {
"version": "2.6.0",
"resolved": "https://registry.npmjs.org/node-fetch/-/node-fetch-2.6.0.tgz",
@ -683,6 +750,27 @@
"word-wrap": "~1.2.3"
}
},
"p-limit": {
"version": "2.2.2",
"resolved": "https://registry.npmjs.org/p-limit/-/p-limit-2.2.2.tgz",
"integrity": "sha512-WGR+xHecKTr7EbUEhyLSh5Dube9JtdiG78ufaeLxTgpudf/20KqyMioIUZJAezlTIi6evxuoUs9YXc11cU+yzQ==",
"requires": {
"p-try": "^2.0.0"
}
},
"p-locate": {
"version": "4.1.0",
"resolved": "https://registry.npmjs.org/p-locate/-/p-locate-4.1.0.tgz",
"integrity": "sha512-R79ZZ/0wAxKGu3oYMlz8jy/kbhsNrS7SKZ7PxEHBgJ5+F2mtFW2fK2cOtBh1cHYkQsbzFV7I+EoRKe6Yt0oK7A==",
"requires": {
"p-limit": "^2.2.0"
}
},
"p-try": {
"version": "2.2.0",
"resolved": "https://registry.npmjs.org/p-try/-/p-try-2.2.0.tgz",
"integrity": "sha512-R4nPAVTAU0B9D35/Gk3uJf/7XYbQcyohSKdvAxIRSNghFl4e71hVoGnBNQz9cWaXxO2I10KTC+3jMdvvoKw6dQ=="
},
"param-case": {
"version": "2.1.1",
"resolved": "https://registry.npmjs.org/param-case/-/param-case-2.1.1.tgz",
@ -699,6 +787,11 @@
"@types/node": "*"
}
},
"path-exists": {
"version": "4.0.0",
"resolved": "https://registry.npmjs.org/path-exists/-/path-exists-4.0.0.tgz",
"integrity": "sha512-ak9Qy5Q7jYb2Wwcey5Fpvg2KoAc/ZIhLSLOSBmRmygPsGwkVVt0fZa0qrtMz+m6tJTAHfZQ8FnmB4MG4LWy7/w=="
},
"performance-now": {
"version": "2.1.0",
"resolved": "https://registry.npmjs.org/performance-now/-/performance-now-2.1.0.tgz",
@ -807,6 +900,16 @@
}
}
},
"require-directory": {
"version": "2.1.1",
"resolved": "https://registry.npmjs.org/require-directory/-/require-directory-2.1.1.tgz",
"integrity": "sha1-jGStX9MNqxyXbiNE/+f3kqam30I="
},
"require-main-filename": {
"version": "2.0.0",
"resolved": "https://registry.npmjs.org/require-main-filename/-/require-main-filename-2.0.0.tgz",
"integrity": "sha512-NKN5kMDylKuldxYLSUfrbo5Tuzh4hd+2E8NPPX02mZtn1VuREQToYe/ZdlJy+J3uCpfaiGF05e7B8W0iXbQHmg=="
},
"safe-buffer": {
"version": "5.2.0",
"resolved": "https://registry.npmjs.org/safe-buffer/-/safe-buffer-5.2.0.tgz",
@ -839,6 +942,11 @@
"resolved": "https://registry.npmjs.org/sax/-/sax-1.2.4.tgz",
"integrity": "sha512-NqVDv9TpANUjFm0N8uM5GxL36UgKi9/atZw+x7YFnQ8ckwFGKrl4xX4yWtrey3UJm5nP1kUbnYgLopqWNSRhWw=="
},
"set-blocking": {
"version": "2.0.0",
"resolved": "https://registry.npmjs.org/set-blocking/-/set-blocking-2.0.0.tgz",
"integrity": "sha1-BF+XgtARrppoA93TgrJDkrPYkPc="
},
"source-map": {
"version": "0.6.1",
"resolved": "https://registry.npmjs.org/source-map/-/source-map-0.6.1.tgz",
@ -874,6 +982,16 @@
"resolved": "https://registry.npmjs.org/string-comparison/-/string-comparison-1.0.7.tgz",
"integrity": "sha512-vSIQT+5cD+CN/mWr90WhNILJZ3w7FFvc6jIHFDRKT4FGW1chK8R2XYPJmQeCgkAplEVxa+b97gTlsDT/qZ26Iw=="
},
"string-width": {
"version": "4.2.0",
"resolved": "https://registry.npmjs.org/string-width/-/string-width-4.2.0.tgz",
"integrity": "sha512-zUz5JD+tgqtuDjMhwIg5uFVV3dtqZ9yQJlZVfq4I01/K5Paj5UHj7VyrQOJvzawSVlKpObApbfD0Ed6yJc+1eg==",
"requires": {
"emoji-regex": "^8.0.0",
"is-fullwidth-code-point": "^3.0.0",
"strip-ansi": "^6.0.0"
}
},
"string_decoder": {
"version": "1.3.0",
"resolved": "https://registry.npmjs.org/string_decoder/-/string_decoder-1.3.0.tgz",
@ -882,6 +1000,14 @@
"safe-buffer": "~5.2.0"
}
},
"strip-ansi": {
"version": "6.0.0",
"resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-6.0.0.tgz",
"integrity": "sha512-AuvKTrTfQNYNIctbR1K/YGTR1756GycPsg7b9bdV9Duqur4gv6aKqHXah67Z8ImS7WEz5QVcOtlfW2rZEugt6w==",
"requires": {
"ansi-regex": "^5.0.0"
}
},
"supports-color": {
"version": "5.5.0",
"resolved": "https://registry.npmjs.org/supports-color/-/supports-color-5.5.0.tgz",
@ -895,6 +1021,20 @@
"resolved": "https://registry.npmjs.org/symbol-tree/-/symbol-tree-3.2.4.tgz",
"integrity": "sha512-9QNk5KwDF+Bvz+PyObkmSYjI5ksVUYtjW7AU22r2NKcfLJcXp96hkDWU3+XndOsUb+AQ9QhfzfCT2O+CNWT5Tw=="
},
"temp-dir": {
"version": "2.0.0",
"resolved": "https://registry.npmjs.org/temp-dir/-/temp-dir-2.0.0.tgz",
"integrity": "sha512-aoBAniQmmwtcKp/7BzsH8Cxzv8OL736p7v1ihGb5e9DJ9kTwGWHrQrVB5+lfVDzfGrdRzXch+ig7LHaY1JTOrg=="
},
"tempfile": {
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/tempfile/-/tempfile-3.0.0.tgz",
"integrity": "sha512-uNFCg478XovRi85iD42egu+eSFUmmka750Jy7L5tfHI5hQKKtbPnxaSaXAbBqCDYrw3wx4tXjKwci4/QmsZJxw==",
"requires": {
"temp-dir": "^2.0.0",
"uuid": "^3.3.2"
}
},
"tough-cookie": {
"version": "2.5.0",
"resolved": "https://registry.npmjs.org/tough-cookie/-/tough-cookie-2.5.0.tgz",
@ -1001,11 +1141,50 @@
}
}
},
"which-module": {
"version": "2.0.0",
"resolved": "https://registry.npmjs.org/which-module/-/which-module-2.0.0.tgz",
"integrity": "sha1-2e8H3Od7mQK4o6j6SzHD4/fm6Ho="
},
"word-wrap": {
"version": "1.2.3",
"resolved": "https://registry.npmjs.org/word-wrap/-/word-wrap-1.2.3.tgz",
"integrity": "sha512-Hz/mrNwitNRh/HUAtM/VT/5VH+ygD6DV7mYKZAtHOrbs8U7lvPS6xf7EJKMF0uW1KJCl0H701g3ZGus+muE5vQ=="
},
"wrap-ansi": {
"version": "6.2.0",
"resolved": "https://registry.npmjs.org/wrap-ansi/-/wrap-ansi-6.2.0.tgz",
"integrity": "sha512-r6lPcBGxZXlIcymEu7InxDMhdW0KDxpLgoFLcguasxCaJ/SOIZwINatK9KY/tf+ZrlywOKU0UDj3ATXUBfxJXA==",
"requires": {
"ansi-styles": "^4.0.0",
"string-width": "^4.1.0",
"strip-ansi": "^6.0.0"
},
"dependencies": {
"ansi-styles": {
"version": "4.2.1",
"resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-4.2.1.tgz",
"integrity": "sha512-9VGjrMsG1vePxcSweQsN20KY/c4zN0h9fLjqAbwbPfahM3t+NL+M9HC8xeXG2I8pX5NoamTGNuomEUFI7fcUjA==",
"requires": {
"@types/color-name": "^1.1.1",
"color-convert": "^2.0.1"
}
},
"color-convert": {
"version": "2.0.1",
"resolved": "https://registry.npmjs.org/color-convert/-/color-convert-2.0.1.tgz",
"integrity": "sha512-RRECPsj7iu/xb5oKYcsFHSppFNnsj/52OVTRKb4zP5onXwVF3zVmmToNcOfGC+CRDpfK/U584fMg38ZHCaElKQ==",
"requires": {
"color-name": "~1.1.4"
}
},
"color-name": {
"version": "1.1.4",
"resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.4.tgz",
"integrity": "sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA=="
}
}
},
"xml-name-validator": {
"version": "2.0.1",
"resolved": "https://registry.npmjs.org/xml-name-validator/-/xml-name-validator-2.0.1.tgz",
@ -1016,10 +1195,42 @@
"resolved": "https://registry.npmjs.org/xtend/-/xtend-4.0.2.tgz",
"integrity": "sha512-LKYU1iAXJXUgAXn9URjiu+MWhyUXHsvfp7mcuYm9dSUKK0/CjtrUwFAxD82/mCWbtLsGjFIad0wIsod4zrTAEQ=="
},
"y18n": {
"version": "4.0.0",
"resolved": "https://registry.npmjs.org/y18n/-/y18n-4.0.0.tgz",
"integrity": "sha512-r9S/ZyXu/Xu9q1tYlpsLIsa3EeLXXk0VwlxqTcFRfg9EhMW+17kbt9G0NrgCmhGb5vT2hyhJZLfDGx+7+5Uj/w=="
},
"yallist": {
"version": "3.1.1",
"resolved": "https://registry.npmjs.org/yallist/-/yallist-3.1.1.tgz",
"integrity": "sha512-a4UGQaWPH59mOXUYnAG2ewncQS4i4F43Tv3JoAM+s2VDAmS9NsK8GpDMLrCHPksFT7h3K6TOoUNn2pb7RoXx4g=="
},
"yargs": {
"version": "15.1.0",
"resolved": "https://registry.npmjs.org/yargs/-/yargs-15.1.0.tgz",
"integrity": "sha512-T39FNN1b6hCW4SOIk1XyTOWxtXdcen0t+XYrysQmChzSipvhBO8Bj0nK1ozAasdk24dNWuMZvr4k24nz+8HHLg==",
"requires": {
"cliui": "^6.0.0",
"decamelize": "^1.2.0",
"find-up": "^4.1.0",
"get-caller-file": "^2.0.1",
"require-directory": "^2.1.1",
"require-main-filename": "^2.0.0",
"set-blocking": "^2.0.0",
"string-width": "^4.2.0",
"which-module": "^2.0.0",
"y18n": "^4.0.0",
"yargs-parser": "^16.1.0"
}
},
"yargs-parser": {
"version": "16.1.0",
"resolved": "https://registry.npmjs.org/yargs-parser/-/yargs-parser-16.1.0.tgz",
"integrity": "sha512-H/V41UNZQPkUMIT5h5hiwg4QKIY1RPvoBV4XcjUbRM8Bk2oKqqyZ0DIEbTFZB0XjbtSPG8SAa/0DxCQmiRgzKg==",
"requires": {
"camelcase": "^5.0.0",
"decamelize": "^1.2.0"
}
}
}
}

View File

@ -1,15 +1,18 @@
{
"name": "url-to-epub",
"version": "1.0.0",
"description": "A single tool to generate a compliant EPUB from a webpage. Zero config. Requires pandoc",
"description": "A single tool to generate a standards-compliant EPUB from a webpage. Zero config. Requires pandoc",
"main": "index.js",
"scripts": {
"test": "echo \"Error: no test specified\" && exit 1"
"bin": {
"url-to-epub": "./index.js"
},
"author": "Nemo",
"license": "MIT",
"dependencies": {
"article-parser": "^4.1.1",
"node-pandoc-promise": "0.0.6"
"node-downloader-helper": "^1.0.11",
"node-pandoc-promise": "0.0.6",
"tempfile": "^3.0.0",
"yargs": "^15.1.0"
}
}