Merge branch 'main' into ssh-server

docs/md/demo.md

@@ -0,0 +1,231 @@
+# Interactive Demo for Crowler
+<div id="demo">
+    <form id="crawlForm" class="terminal-form">
+        <fieldset>
+            <legend>Enter URL and Options</legend>
+            <div class="form-group">
+                <label for="url">Enter URL:</label>
+                <input type="text" id="url" name="url" required>
+            </div>
+            <div class="form-group">
+                <label for="screenshot">Get Screenshot:</label>
+                <input type="checkbox" id="screenshot" name="screenshot">
+            </div>
+            <div class="form-group">
+                <button class="btn btn-default" type="submit">Submit</button>
+            </div>
+
+        </fieldset>
+    </form>
+
+    <div id="loading" class="loading-message">
+        <div class="terminal-alert terminal-alert-primary">Loading... Please wait.</div>
+    </div>
+
+    <section id="response" class="response-section">
+        <h2>Response</h2>
+        <div class="tabs">
+            <ul class="tab-list">
+                <li class="tab-item" onclick="showTab('markdown')">Markdown</li>
+                <li class="tab-item" onclick="showTab('cleanedHtml')">Cleaned HTML</li>
+                <li class="tab-item" onclick="showTab('media')">Media</li>
+                <li class="tab-item" onclick="showTab('extractedContent')">Extracted Content</li>
+                <li class="tab-item" onclick="showTab('screenshot')">Screenshot</li>
+                <li class="tab-item" onclick="showTab('pythonCode')">Python Code</li>
+            </ul>
+            <div class="tab-content" id="tab-markdown">
+                <header>
+                    <div>
+                        <button class="btn btn-default btn-ghost btn-sm" onclick="copyToClipboard('markdownContent')">Copy</button>
+                        <button class="btn btn-default btn-ghost btn-sm" onclick="downloadContent('markdownContent', 'markdown.md')">Download</button>
+                    </div>
+                </header>
+                <pre><code id="markdownContent" class="language-markdown hljs"></code></pre>
+            </div>
+
+            <div class="tab-content" id="tab-cleanedHtml" style="display: none;">
+                <header >
+                    <div>
+                        <button class="btn btn-default btn-ghost btn-sm" onclick="copyToClipboard('cleanedHtmlContent')">Copy</button>
+                        <button class="btn btn-default btn-ghost btn-sm" onclick="downloadContent('cleanedHtmlContent', 'cleaned.html')">Download</button>
+                    </div>
+                </header>
+                <pre><code id="cleanedHtmlContent" class="language-html hljs"></code></pre>
+            </div>
+
+            <div class="tab-content" id="tab-media" style="display: none;">
+                <header >
+                    <div>
+                        <button class="btn btn-default btn-ghost btn-sm" onclick="copyToClipboard('mediaContent')">Copy</button>
+                        <button class="btn btn-default btn-ghost btn-sm" onclick="downloadContent('mediaContent', 'media.json')">Download</button>
+                    </div>
+                </header>
+                <pre><code id="mediaContent" class="language-json hljs"></code></pre>
+            </div>
+
+            <div class="tab-content" id="tab-extractedContent" style="display: none;">
+                <header >
+                    <div>
+                        <button class="btn btn-default btn-ghost btn-sm" onclick="copyToClipboard('extractedContentContent')">Copy</button>
+                        <button class="btn btn-default btn-ghost btn-sm" onclick="downloadContent('extractedContentContent', 'extracted_content.json')">Download</button>
+                    </div>
+                </header>
+                <pre><code id="extractedContentContent" class="language-json hljs"></code></pre>
+            </div>
+
+            <div class="tab-content" id="tab-screenshot" style="display: none;">
+                <header >
+                    <div>
+                        <button class="btn btn-default btn-ghost btn-sm" onclick="downloadImage('screenshotContent', 'screenshot.png')">Download</button>
+                    </div>
+                </header>
+                <pre><img id="screenshotContent" /></pre>
+            </div>
+
+            <div class="tab-content" id="tab-pythonCode" style="display: none;">
+                <header >
+                    <div>
+                        <button class="btn btn-default btn-ghost btn-sm" onclick="copyToClipboard('pythonCode')">Copy</button>
+                        <button class="btn btn-default btn-ghost btn-sm" onclick="downloadContent('pythonCode', 'example.py')">Download</button>
+                    </div>
+                </header>
+                <pre><code id="pythonCode" class="language-python hljs"></code></pre>
+            </div>
+        </div>
+    </section>
+
+    <div id="error" class="error-message" style="display: none; margin-top:1em;">
+        <div class="terminal-alert terminal-alert-error"></div>
+    </div>
+
+    <script>
+        function showTab(tabId) {
+            const tabs = document.querySelectorAll('.tab-content');
+            tabs.forEach(tab => tab.style.display = 'none');
+            document.getElementById(`tab-${tabId}`).style.display = 'block';
+        }
+
+        function redo(codeBlock, codeText){
+            codeBlock.classList.remove('hljs');
+            codeBlock.removeAttribute('data-highlighted');
+
+            // Set new code and re-highlight
+            codeBlock.textContent = codeText;
+            hljs.highlightBlock(codeBlock);
+        }
+
+        function copyToClipboard(elementId) {
+            const content = document.getElementById(elementId).textContent;
+            navigator.clipboard.writeText(content).then(() => {
+                alert('Copied to clipboard');
+            });
+        }
+
+        function downloadContent(elementId, filename) {
+            const content = document.getElementById(elementId).textContent;
+            const blob = new Blob([content], { type: 'text/plain' });
+            const url = window.URL.createObjectURL(blob);
+            const a = document.createElement('a');
+            a.style.display = 'none';
+            a.href = url;
+            a.download = filename;
+            document.body.appendChild(a);
+            a.click();
+            window.URL.revokeObjectURL(url);
+            document.body.removeChild(a);
+        }
+
+        function downloadImage(elementId, filename) {
+            const content = document.getElementById(elementId).src;
+            const a = document.createElement('a');
+            a.style.display = 'none';
+            a.href = content;
+            a.download = filename;
+            document.body.appendChild(a);
+            a.click();
+            document.body.removeChild(a);
+        }
+
+        document.getElementById('crawlForm').addEventListener('submit', function(event) {
+            event.preventDefault();
+            document.getElementById('loading').style.display = 'block';
+            document.getElementById('response').style.display = 'none';
+
+            const url = document.getElementById('url').value;
+            const screenshot = document.getElementById('screenshot').checked;
+            const data = {
+                urls: [url],
+                bypass_cache: false,
+                word_count_threshold: 5,
+                screenshot: screenshot
+            };
+
+            fetch('https://crawl4ai.com/crawl', {
+                method: 'POST',
+                headers: {
+                    'Content-Type': 'application/json'
+                },
+                body: JSON.stringify(data)
+            })
+            .then(response => {
+                if (!response.ok) {
+                    if (response.status === 429) {
+                        return response.json().then(err => { 
+                            throw Object.assign(new Error('Rate limit exceeded'), { status: 429, details: err });
+                        });
+                    }
+                    throw new Error('Network response was not ok');
+                }
+                return response.json();
+            })
+            .then(data => {
+                data = data.results[0]; // Only one URL is requested
+                document.getElementById('loading').style.display = 'none';
+                document.getElementById('response').style.display = 'block';
+                redo(document.getElementById('markdownContent'), data.markdown);
+                redo(document.getElementById('cleanedHtmlContent'), data.cleaned_html);
+                redo(document.getElementById('mediaContent'), JSON.stringify(data.media, null, 2));
+                redo(document.getElementById('extractedContentContent'), data.extracted_content);
+                if (screenshot) {
+                    document.getElementById('screenshotContent').src = `data:image/png;base64,${data.screenshot}`;
+                }
+                const pythonCode = `
+from crawl4ai.web_crawler import WebCrawler
+
+crawler = WebCrawler()
+crawler.warmup()
+
+result = crawler.run(
+    url='${url}',
+    screenshot=${screenshot}
+)
+print(result)
+                `;
+                redo(document.getElementById('pythonCode'), pythonCode);
+                document.getElementById('error').style.display = 'none';
+            })
+            .catch(error => {
+                document.getElementById('loading').style.display = 'none';
+                document.getElementById('error').style.display = 'block';
+                let errorMessage = 'An unexpected error occurred. Please try again later.';
+                
+                if (error.status === 429) {
+                    const details = error.details;
+                    if (details.retry_after) {
+                        errorMessage = `Rate limit exceeded. Please wait ${parseFloat(details.retry_after).toFixed(1)} seconds before trying again.`;
+                    } else if (details.reset_at) {
+                        const resetTime = new Date(details.reset_at);
+                        const waitTime = Math.ceil((resetTime - new Date()) / 1000);
+                        errorMessage = `Rate limit exceeded. Please try again after ${waitTime} seconds.`;
+                    } else {
+                        errorMessage = `Rate limit exceeded. Please try again later.`;
+                    }
+                } else if (error.message) {
+                    errorMessage = error.message;
+                }
+                
+                document.querySelector('#error .terminal-alert').textContent = errorMessage;
+            });
+        });
+    </script>
+</div>

main.py

@@ -380,97 +380,97 @@ def read_root():
     return {"message": "Crawl4AI API service is running"}
 
 
-@app.post("/crawl", dependencies=[Depends(verify_token)])
+# @app.post("/crawl", dependencies=[Depends(verify_token)])
-async def crawl(request: CrawlRequest) -> Dict[str, str]:
+# async def crawl(request: CrawlRequest) -> Dict[str, str]:
-    task_id = await crawler_service.submit_task(request)
+#     task_id = await crawler_service.submit_task(request)
-    return {"task_id": task_id}
+#     return {"task_id": task_id}
 
-@app.get("/task/{task_id}", dependencies=[Depends(verify_token)])
+# @app.get("/task/{task_id}", dependencies=[Depends(verify_token)])
-async def get_task_status(task_id: str):
+# async def get_task_status(task_id: str):
-    task_info = crawler_service.task_manager.get_task(task_id)
+#     task_info = crawler_service.task_manager.get_task(task_id)
-    if not task_info:
+#     if not task_info:
-        raise HTTPException(status_code=404, detail="Task not found")
+#         raise HTTPException(status_code=404, detail="Task not found")
 
-    response = {
+#     response = {
-        "status": task_info.status,
+#         "status": task_info.status,
-        "created_at": task_info.created_at,
+#         "created_at": task_info.created_at,
-    }
+#     }
 
-    if task_info.status == TaskStatus.COMPLETED:
+#     if task_info.status == TaskStatus.COMPLETED:
-        # Convert CrawlResult to dict for JSON response
+#         # Convert CrawlResult to dict for JSON response
-        if isinstance(task_info.result, list):
+#         if isinstance(task_info.result, list):
-            response["results"] = [result.dict() for result in task_info.result]
+#             response["results"] = [result.dict() for result in task_info.result]
-        else:
+#         else:
-            response["result"] = task_info.result.dict()
+#             response["result"] = task_info.result.dict()
-    elif task_info.status == TaskStatus.FAILED:
+#     elif task_info.status == TaskStatus.FAILED:
-        response["error"] = task_info.error
+#         response["error"] = task_info.error
 
-    return response
+#     return response
 
-@app.post("/crawl_sync", dependencies=[Depends(verify_token)])
+# @app.post("/crawl_sync", dependencies=[Depends(verify_token)])
-async def crawl_sync(request: CrawlRequest) -> Dict[str, Any]:
+# async def crawl_sync(request: CrawlRequest) -> Dict[str, Any]:
-    task_id = await crawler_service.submit_task(request)
+#     task_id = await crawler_service.submit_task(request)
     
-    # Wait up to 60 seconds for task completion
+#     # Wait up to 60 seconds for task completion
-    for _ in range(60):
+#     for _ in range(60):
-        task_info = crawler_service.task_manager.get_task(task_id)
+#         task_info = crawler_service.task_manager.get_task(task_id)
-        if not task_info:
+#         if not task_info:
-            raise HTTPException(status_code=404, detail="Task not found")
+#             raise HTTPException(status_code=404, detail="Task not found")
             
-        if task_info.status == TaskStatus.COMPLETED:
+#         if task_info.status == TaskStatus.COMPLETED:
-            # Return same format as /task/{task_id} endpoint
+#             # Return same format as /task/{task_id} endpoint
-            if isinstance(task_info.result, list):
+#             if isinstance(task_info.result, list):
-                return {"status": task_info.status, "results": [result.dict() for result in task_info.result]}
+#                 return {"status": task_info.status, "results": [result.dict() for result in task_info.result]}
-            return {"status": task_info.status, "result": task_info.result.dict()}
+#             return {"status": task_info.status, "result": task_info.result.dict()}
             
-        if task_info.status == TaskStatus.FAILED:
+#         if task_info.status == TaskStatus.FAILED:
-            raise HTTPException(status_code=500, detail=task_info.error)
+#             raise HTTPException(status_code=500, detail=task_info.error)
             
-        await asyncio.sleep(1)
+#         await asyncio.sleep(1)
     
-    # If we get here, task didn't complete within timeout
+#     # If we get here, task didn't complete within timeout
-    raise HTTPException(status_code=408, detail="Task timed out")
+#     raise HTTPException(status_code=408, detail="Task timed out")
 
-@app.post("/crawl_direct", dependencies=[Depends(verify_token)])
+# @app.post("/crawl_direct", dependencies=[Depends(verify_token)])
-async def crawl_direct(request: CrawlRequest) -> Dict[str, Any]:
+# async def crawl_direct(request: CrawlRequest) -> Dict[str, Any]:
-    try:
+#     try:
-        crawler = await crawler_service.crawler_pool.acquire(**request.crawler_params)
+#         crawler = await crawler_service.crawler_pool.acquire(**request.crawler_params)
-        extraction_strategy = crawler_service._create_extraction_strategy(request.extraction_config)
+#         extraction_strategy = crawler_service._create_extraction_strategy(request.extraction_config)
         
-        try:
+#         try:
-            if isinstance(request.urls, list):
+#             if isinstance(request.urls, list):
-                results = await crawler.arun_many(
+#                 results = await crawler.arun_many(
-                    urls=[str(url) for url in request.urls],
+#                     urls=[str(url) for url in request.urls],
-                    extraction_strategy=extraction_strategy,
+#                     extraction_strategy=extraction_strategy,
-                    js_code=request.js_code,
+#                     js_code=request.js_code,
-                    wait_for=request.wait_for,
+#                     wait_for=request.wait_for,
-                    css_selector=request.css_selector,
+#                     css_selector=request.css_selector,
-                    screenshot=request.screenshot,
+#                     screenshot=request.screenshot,
-                    magic=request.magic,
+#                     magic=request.magic,
-                    cache_mode=request.cache_mode,
+#                     cache_mode=request.cache_mode,
-                    session_id=request.session_id,
+#                     session_id=request.session_id,
-                    **request.extra,
+#                     **request.extra,
-                )
+#                 )
-                return {"results": [result.dict() for result in results]}
+#                 return {"results": [result.dict() for result in results]}
-            else:
+#             else:
-                result = await crawler.arun(
+#                 result = await crawler.arun(
-                    url=str(request.urls),
+#                     url=str(request.urls),
-                    extraction_strategy=extraction_strategy,
+#                     extraction_strategy=extraction_strategy,
-                    js_code=request.js_code,
+#                     js_code=request.js_code,
-                    wait_for=request.wait_for,
+#                     wait_for=request.wait_for,
-                    css_selector=request.css_selector,
+#                     css_selector=request.css_selector,
-                    screenshot=request.screenshot,
+#                     screenshot=request.screenshot,
-                    magic=request.magic,
+#                     magic=request.magic,
-                    cache_mode=request.cache_mode,
+#                     cache_mode=request.cache_mode,
-                    session_id=request.session_id,
+#                     session_id=request.session_id,
-                    **request.extra,
+#                     **request.extra,
-                )
+#                 )
-                return {"result": result.dict()}
+#                 return {"result": result.dict()}
-        finally:
+#         finally:
-            await crawler_service.crawler_pool.release(crawler)
+#             await crawler_service.crawler_pool.release(crawler)
-    except Exception as e:
+#     except Exception as e:
-        logger.error(f"Error in direct crawl: {str(e)}")
+#         logger.error(f"Error in direct crawl: {str(e)}")
-        raise HTTPException(status_code=500, detail=str(e))
+#         raise HTTPException(status_code=500, detail=str(e))
     
 @app.get("/health")
 async def health_check():

mkdocs.yml

@@ -8,7 +8,7 @@ docs_dir: docs/md_v2
 nav:
   - Home: 'index.md'
   - 'Installation': 'basic/installation.md'
-  - 'Docker Deplotment': 'basic/docker-deploymeny.md'
+  - 'Docker Deployment': 'basic/docker-deploymeny.md'
   - 'Quick Start': 'basic/quickstart.md'
   - Changelog & Blog:
     - 'Blog Home': 'blog/index.md'