Web Scraper Bookmarklet

📥 Installation

Drag this link to your bookmarks bar:

Installation Steps:

Show bookmarks bar: Press Ctrl+Shift+B (Windows) or Cmd+Shift+B (Mac)
Drag the button: Click and drag the "Scraper" button above to your bookmarks bar
Done! The bookmarklet is now installed

⚠️ Alternative Installation (if dragging doesn't work):

Right-click on your bookmarks bar → Add new bookmark
Name: Scraper
URL: Copy the code from the gray box below

Bookmarklet Code (copy this if drag doesn't work):

javascript:(function(){function startTool(){let css=document.createElement("style");css.textContent="#scraper-overlay{position:fixed;inset:0;background:rgba(0,0,0,0.85);z-index:9999999;display:flex;align-items:center;justify-content:center}#scraper-panel{background:#fff;border-radius:12px;padding:24px;width:92%;max-width:480px;max-height:90vh;overflow-y:auto}#scraper-panel div{margin-bottom:14px}#scraper-panel label{display:block;margin-bottom:4px;font-weight:600}#scraper-panel input{width:100%;padding:10px;border:2px solid #eee;border-radius:6px}#scraper-panel .btns{display:flex;gap:10px;margin-bottom:0}#scraper-panel #btnStart{flex:1;padding:11px;border:none;border-radius:6px;background:#667eea;color:#fff;font-weight:600;cursor:pointer}#scraper-panel #btnClose{padding:11px 18px;border:none;border-radius:6px;background:#f44336;color:#fff;font-weight:600;cursor:pointer}#scraper-status{margin-top:15px;padding:10px;border-radius:6px;display:none}";document.head.appendChild(css);if(document.getElementById("scraper-overlay"))return;let overlay=document.createElement("div");overlay.id="scraper-overlay";let panel=document.createElement("div");panel.id="scraper-panel";panel.innerHTML='<h2 style="margin:0 0 18px;color:#667eea">🌐 文章批量采集</h2><div><label>正文选择器</label><input id="selContent" value="article, .article, .content, #article, #content"></div><div><label>标题选择器</label><input id="selTitle" value="#title, .title"></div><div><label>最大页数</label><input id="maxPage" value="300"></div><div><label>自定义文件名</label><input id="txtName" placeholder="默认使用网页标题"></div><div class="btns"><button id="btnStart">🚀 开始采集</button><button id="btnClose">✕ 关闭</button></div><div id="scraper-status"></div>';overlay.appendChild(panel);document.body.appendChild(overlay);document.getElementById("btnClose").onclick=function(){document.body.removeChild(overlay);document.head.removeChild(css)};document.getElementById("btnStart").onclick=startScrape;function formatText(el){let clone=el.cloneNode(true);clone.querySelectorAll("script").forEach(s=>s.remove());let html=clone.innerHTML.replace(/<script\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/script>/gi,"").replace(/ /g," ").replace(/ /g," ").replace(/ /g," ").replace(/\xa0/g," ").replace(/<br\s*\/?>/gi,"\n").replace(/<\/(p|div|h1|h2|h3|h4|h5|h6)>/gi,"\n\n").replace(/<[^>]+>/g,"").replace(/[ \t]+/g," ").replace(/\n\s+/g,"\n").replace(/\n{3,}/g,"\n\n");return html.trim()}async function fetchDoc(url){try{let res=await fetch(url,{credentials:"include"});let txt=await res.text();return new DOMParser().parseFromString(txt,"text/html")}catch(e){return null}}function getNextUrl(doc){let nextEl=doc.querySelector("[class*=next], [id*=next]");if(nextEl){if(nextEl.tagName==="A"&&nextEl.href)return new URL(nextEl.href,doc.baseURI).href;if(nextEl.tagName==="BUTTON"){let parent=nextEl.closest("a");if(parent&&parent.href)return new URL(parent.href,doc.baseURI).href}}let reg=/下.*页|下.*章|下.*节|next/i;let links=doc.querySelectorAll("a, button");for(let el of links){let t=el.textContent.trim();if(reg.test(t)){if(el.tagName==="A"&&el.href)return new URL(el.href,doc.baseURI).href;if(el.tagName==="BUTTON"){let parent=el.closest("a");if(parent&&parent.href)return new URL(parent.href,doc.baseURI).href}}}return""}async function startScrape(){let selC=document.getElementById("selContent").value;let selT=document.getElementById("selTitle").value;let maxP=parseInt(document.getElementById("maxPage").value)||300;let name=document.getElementById("txtName").value;let status=document.getElementById("scraper-status");let btn=document.getElementById("btnStart");btn.disabled=true;btn.innerText="采集中...";status.style.display="block";status.style.background="#e3f2fd";status.style.color="#1976d2";let all="";let currUrl=location.href;let count=0;while(count<maxP){count++;status.innerText=`正在采集 ${count}/${maxP}`;let doc=await fetchDoc(currUrl);if(!doc)break;let title="无标题";let tEl=doc.querySelector(selT);if(!tEl)tEl=doc.querySelector("[class*=title], [id*=title]");if(tEl)title=tEl.textContent.trim().replace(/【|】/g,"").replace(/\s+/g," ");let cont="";let cEls=doc.querySelectorAll(selC);if(!cEls.length)cEls=doc.querySelectorAll("[class*=content], [class*=article], [id*=article]");if(cEls.length)cont=Array.from(cEls).map(x=>formatText(x)).join("\n\n");all+=`${title}\n\n${cont}\n\n`;let next=getNextUrl(doc);if(!next)break;currUrl=next;await new Promise(r=>setTimeout(r,500))}if(all.trim()){let defName=document.title.replace(/[^一-龥a-zA-Z0-9]/g,"_");let saveName=(name||defName||"article").substring(0,2);let blob=new Blob([all],{type:"text/plain;charset=utf-8"});let url=URL.createObjectURL(blob);let a=document.createElement("a");a.href=url;a.download=saveName+".txt";a.click();URL.revokeObjectURL(url);status.style.background="#e8f5e9";status.style.color="#388e3c";status.innerText=`✅ 完成！共 ${count} 页，已下载`}else{status.style.background="#ffebee";status.style.color="#c62828";status.innerText="❌ 未采集到内容，请检查选择器"}btn.disabled=false;btn.innerText="🚀 开始采集"}};startTool()})();

🚀 How to Use

1️⃣Navigate to Target Page

Go to the webpage you want to scrape (e.g., a blog article, novel chapter, documentation page)

2️⃣Click the Bookmarklet

Click the "Scraper" bookmark in your bookmarks bar. A scraper panel will appear on the page.

3️⃣Configure Selectors

The bookmarklet will show a form with smart defaults:

Content Selector: Where to extract text from
Title Selector: How to find the page title
Next Link Selector: How to find the "next page" button (optional)
Max Pages: How many pages to follow

4️⃣Start Scraping

Click "🚀 Start" and watch it work! The scraper will:

Extract content from the current page
Find and click the "next" link
Repeat until max pages or no more pages
Download everything as a single .txt file

🔬 Advanced Tips

Finding the Right Selectors:

Right-click on the content you want → "Inspect Element"
Look at the HTML element's class or id
Use #id for IDs (e.g., #content)
Use .class for classes (e.g., .article-body)
Use element names directly (e.g., article, main)

Testing Selectors in Console:

Press F12 to open Developer Console
Type: document.querySelector('YOUR_SELECTOR')
If it returns an element, your selector is correct!
Use querySelectorAll to see all matches

📚 Web Scraper Bookmarklet