|
| 1 | +"use strict"; |
| 2 | + |
| 3 | +parserFactory.register("novelarrow.com", () => new NovelarrowParser()); |
| 4 | + |
| 5 | +class NovelarrowParser extends Parser { // eslint-disable-line no-unused-vars |
| 6 | + constructor() { |
| 7 | + super(); |
| 8 | + } |
| 9 | + |
| 10 | + async getChapterUrls(dom) { |
| 11 | + return [...dom.querySelectorAll(".jsx-6d23f35167deb67d.space-y-6 a")] |
| 12 | + .map(a => ({ |
| 13 | + sourceUrl: a.href, |
| 14 | + title: a.querySelector("span.hidden")?.textContent, |
| 15 | + })) |
| 16 | + .reverse(); |
| 17 | + } |
| 18 | + |
| 19 | + findContent(dom) { |
| 20 | + return Parser.findConstrutedContent(dom); |
| 21 | + } |
| 22 | + |
| 23 | + extractTitleImpl(dom) { |
| 24 | + return dom.querySelector("h1"); |
| 25 | + } |
| 26 | + |
| 27 | + extractAuthor(dom) { |
| 28 | + let author = dom.querySelector("a[href*='/author/']"); |
| 29 | + return (author === null) ? super.extractAuthor(dom) : author.innerText; } |
| 30 | + |
| 31 | + // Optional, supply if individual chapter titles are not inside the content element |
| 32 | + /* |
| 33 | + findChapterTitle(dom) { |
| 34 | + // typical implementation is find node with the Title |
| 35 | + // Return Title element, OR the title as a string |
| 36 | + return dom.querySelector("h3.dashhead-title"); |
| 37 | + } |
| 38 | + */ |
| 39 | + |
| 40 | + findCoverImageUrl(dom) { |
| 41 | + return util.getFirstImgSrc(dom, ".novel-cover-frame"); |
| 42 | + } |
| 43 | + |
| 44 | + preprocessRawDom(webPageDom) { |
| 45 | + let content = this.locateContent(webPageDom); |
| 46 | + let doc = util.sanitize(`<div class='${Parser.WEB_TO_EPUB_CLASS_NAME}'>"${content}</div>`); |
| 47 | + let node = doc.querySelector("."+Parser.WEB_TO_EPUB_CLASS_NAME); |
| 48 | + webPageDom.body.appendChild(node); |
| 49 | + } |
| 50 | + |
| 51 | + locateContent(webPageDom) { |
| 52 | + let encoded = [...webPageDom.querySelectorAll("script")] |
| 53 | + .filter(s => this.isContent(s)) |
| 54 | + .map(s => this.extractContentString(s.textContent))[0]; |
| 55 | + return encoded |
| 56 | + ? this.cleanUnicode(encoded) |
| 57 | + : ""; |
| 58 | + } |
| 59 | + |
| 60 | + cleanUnicode(s) { |
| 61 | + return s.replace(/\\u003c/g, "<") |
| 62 | + .replace(/\\u003e/g, ">") |
| 63 | + .replace(/\\"/g, "\"") |
| 64 | + .replace(/\\n/g, ""); |
| 65 | + } |
| 66 | + |
| 67 | + extractContentString(raw) { |
| 68 | + let start = raw.indexOf("\""); |
| 69 | + let end = raw.lastIndexOf("\""); |
| 70 | + return raw.substring(start + 1, end); |
| 71 | + } |
| 72 | + |
| 73 | + isContent(script) { |
| 74 | + let text = script.textContent; |
| 75 | + if (text.includes("self.__next_f.push([1,")) { |
| 76 | + let s = this.extractContentString(text); |
| 77 | + return s.startsWith("\\u003c"); |
| 78 | + } |
| 79 | + return false; |
| 80 | + } |
| 81 | + |
| 82 | + getInformationEpubItemChildNodes(dom) { |
| 83 | + return [...dom.querySelectorAll(".site-reading-copy")]; |
| 84 | + } |
| 85 | +} |
0 commit comments