gmastergreatee
commented
4 months ago Try this and tell if this better
{
"guid": "c6f1562f-2f0a-441b-861c-9255b7192455",
"rule_name": "LightNovelWorld.com",
"url_regex": "(?:https://)*(?:www\\.)*(lightnovelworld).com/novel/",
"pagetype_code": "// https://www.lightnovelworld.com/novel/doomsday-spiritual-artifact-master-1676/chapter-5\n// https://www.lightnovelworld.com/novel/doomsday-spiritual-artifact-master\n\nif (document.title.toLowerCase().includes('just a moment')) {\n return -2;\n}\n\nreturn 0;",
"toc_code": "injectJquery();\n\nif ($('#chapter-list-page').length) {\n // means this is TOC page\n return {\n retry: 1,\n nextURL: $('.booktitle').attr('href')\n };\n}\n\nif ($('.booktitle').length) {\n // means this is chapter page\n return {\n retry: 1,\n nextURL: $('.booktitle').attr('href')\n };\n}\n\n// only allow to go past if it is novel page\nif ($('.chapter-latest-container').length <= 0) {\n throw Error('The page-type couldn\\'t be determined. Please re-check the URL.');\n}\n\n// compile list of chapters\nlet chListURL = $('.chapter-latest-container')[0].href;\nlet toc1 = await fetch(chListURL).then(x => x.text());\nlet tocPageCount = $(toc1).find('.pagination-container li').length - 1;\nlet tocs = [toc1];\nfor (let i = 1; i < tocPageCount; i++) {\n tocs.push(await fetch(chListURL + '?page=' + (i + 1)).then(x => x.text()));\n}\nlet chapterURLs = [];\ntocs.forEach(x => {\n chapterURLs.push(...Array.from($(x).find('li[data-chapterno] a')).map(x => x.href))\n});\n\nlet retMe = {\n 'CoverURL': $('.glass-background img')[0].src,\n 'Title': $('h1').text().trim(),\n 'Summary': Array.from($('.summary .content > p')).map(x => $(x).text().trim()).join('<br><br>'),\n 'ChapterCount': chapterURLs.length,\n 'ChapterURLs': chapterURLs,\n};\n\nreturn retMe;",
"chapter_code": "injectJquery();\n\n$('#chapter-container > div').remove();\n\nlet retMe = [\n {\n \"title\": $('.chapter-title').text().trim().replace(/^chapter\\s+/gi, ''),\n \"content\": $('#chapter-container').html(),\n \"nextURL\": \"\"\n },\n];\n\nreturn retMe;",
"url_blocks": "fonts.google\n/content/\nvntsm.com\ncriteo.net\ninmobi.com\ngoogletagmanager\nstatic.lightnovelworld.com/lib/"
},
AurelionSoldMe
Just contributing a custom rule
{ "guid": "a804de22-86bb-4aac-a1bf-cae1addfc889", "rule_name": "lightnovelworld", "url_regex": "(?:https:\\/\\/www\\.lightnovelworld\\.com|.co\\/novel\\/([a-zA-Z0-9\\-\\/]+))", "pagetype_code": "return 0;", "toc_code": "injectJquery();\n\n// Extract the URL from the \"Novel Chapters\" link\nlet novelChaptersURL = $('a.grdbtn.chapter-latest-container').attr('href');\n\n// Fetch the content of the \"Novel Chapters\" page\nlet response = await fetch(novelChaptersURL);\n\n// Parse the HTML content\nlet htmlContent = await response.text();\n\n// Create a virtual DOM for parsing\nlet virtualDOM = $(htmlContent);\n\n// Extract base URL\nlet baseURL = window.location.origin;\n\n// Extract cover URL\nlet coverURL = virtualDOM.find('.novel-item .novel-cover img').attr('src');\n\n// Extract title\nlet title = virtualDOM.find('.novel-item h1 a.text2row').text().trim();\n\n//Summary\nlet summary = $('meta[itemprop=\"description\"]').attr('content');\n\n\n// Extract all chapter URLs\nlet chapterURLs = [];\n\n// Loop through each chapter list item\nvirtualDOM.find('.chapter-list li a').each(function () {\n let chapterLink = $(this).attr('href');\n // Prepend the base URL to the relative chapter URL\n chapterURLs.push(new URL(chapterLink, baseURL).href);\n});\n\n// Check if there's a next page for chapters\nlet nextPageLink = virtualDOM.find('.pagination-container a[rel=\"next\"]').attr('href');\n\n// If there's a next page, fetch its content and extract chapter URLs\nwhile (nextPageLink) {\n response = await fetch(nextPageLink);\n htmlContent = await response.text();\n virtualDOM = $(htmlContent);\n\n virtualDOM.find('.chapter-list li a').each(function () {\n let chapterLink = $(this).attr('href');\n // Prepend the base URL to the relative chapter URL\n chapterURLs.push(new URL(chapterLink, baseURL).href);\n });\n\n // Check if there's another next page\n nextPageLink = virtualDOM.find('.pagination-container a[rel=\"next\"]').attr('href');\n}\n\nlet retMe = {\n 'CoverURL': coverURL,\n 'Title': title,\n 'Summary': summary,\n 'ChapterCount': chapterURLs.length,\n 'ChapterURLs': chapterURLs,\n};\n\nreturn retMe;\n", "chapter_code": "// Ensure jQuery is injected\ninjectJquery();\n\n// Set to keep track of visited chapter URLs\nlet visitedChapterURLs = new Set();\n\nlet retMe;\n\n// Check if the current page is the Table of Contents (TOC) page\nif (isTOCPage()) {\n console.error(\"Error: Script is on the Table of Contents page. Not a chapter page.\");\n} else {\n let currentChapterURL = window.location.href;\n\n if (visitedChapterURLs.has(currentChapterURL)) {\n console.error(\"Error: Same chapter URL loaded twice. Breaking the script.\");\n }\n\n visitedChapterURLs.add(currentChapterURL);\n\n // Extract chapter title\n let chapterTitle = $('.chapter-title').text().trim();\n console.log('Chapter Title:', chapterTitle);\n\n // Scroll down to the bottom of the page\n await scrollDown();\n\n // Add an increased delay (15 seconds) to ensure content is loaded\n await sleep(8000);\n\n // Extract chapter content after scrolling\n let chapterContent = $('#chapter-container').html();\n console.log('Chapter Content:', chapterContent);\n\n // Get the URL of the next chapter\n let nextChapterPartialURL = getNextChapterURL();\n console.log('Next Chapter Partial URL:', nextChapterPartialURL);\n\n // Check if the next chapter URL is complete\n let nextChapterURL = null;\n if (nextChapterPartialURL) {\n // Get the base URL of the website\n let baseURL = window.location.origin;\n \n // Create the complete next chapter URL\n nextChapterURL = new URL(nextChapterPartialURL, baseURL).href;\n console.log('Next Chapter Complete URL:', nextChapterURL);\n } else {\n console.log('No Next Chapter Button found, or the next chapter has been visited before. It might be the last chapter.');\n }\n\n // Add a delay (8 seconds) after logging the next chapter URL\n await sleep(3000);\n console.log('Delay complete.');\n\n // Create the response object\n retMe = [\n {\n \"title\": chapterTitle,\n \"content\": chapterContent,\n \"nextURL\": nextChapterURL\n },\n ];\n}\n\nfunction isTOCPage() {\n return $('.toc-container').length > 0;\n}\n\n// Function to scroll down to the bottom of the page\nasync function scrollDown() {\n return new Promise(resolve => {\n let totalHeight = 0;\n let distance = 100;\n let scrollHeight = document.body.scrollHeight;\n\n let timer = setInterval(() => {\n window.scrollBy(0, distance);\n totalHeight += distance;\n\n if (totalHeight >= scrollHeight) {\n clearInterval(timer);\n resolve();\n }\n }, 50); // Reduced delay to 50 milliseconds\n });\n}\n\n// Function to get the URL of the next chapter\nfunction getNextChapterURL() {\n // Extract the URL of the next chapter link\n let nextChapterLink = $('a.button.nextchap');\n if (nextChapterLink.length > 0) {\n return nextChapterLink.attr('href');\n } else {\n // If no next chapter link is found, it means it's the last chapter\n // You can handle this case accordingly, for example, returning null or a special value\n return null;\n }\n}\n\n// Function for sleep/delay\nfunction sleep(ms) {\n return new Promise(resolve => setTimeout(resolve, ms));\n}\n\nreturn retMe;\n", "url_blocks": "" },