chore: Update version to 0.2.74 in setup.py

This commit adds a delay of 5 seconds after fetching the URL in the `after_get_url` hook of the crawler hooks. The delay is implemented using the `time.sleep()` function. This change ensures that the entire page is fetched before proceeding with further actions.

.gitignore

@@ -165,8 +165,6 @@ Crawl4AI.egg-info/
 Crawl4AI.egg-info/*
 crawler_data.db
 .vscode/
-.tests/
-.test_pads/
 test_pad.py
 test_pad*.py
 .data/

CHANGELOG.md

@@ -1,14 +1,5 @@
 # Changelog
 
-## [v0.2.75] - 2024-07-19
-
-Minor improvements for a more maintainable codebase:
-
-- 🔄 Fixed typos in `chunking_strategy.py` and `crawler_strategy.py` to improve code readability
-- 🔄 Removed `.test_pads/` directory from `.gitignore` to keep our repository clean and organized
-
-These changes may seem small, but they contribute to a more stable and sustainable codebase. By fixing typos and updating our `.gitignore` settings, we're ensuring that our code is easier to maintain and scale in the long run.
-
 ## [v0.2.74] - 2024-07-08
 A slew of exciting updates to improve the crawler's stability and robustness! 🎉
 

README.md

@@ -1,4 +1,4 @@
-# Crawl4AI v0.2.75 🕷️🤖
+# Crawl4AI v0.2.74 🕷️🤖
 
 [![GitHub Stars](https://img.shields.io/github/stars/unclecode/crawl4ai?style=social)](https://github.com/unclecode/crawl4ai/stargazers)
 [![GitHub Forks](https://img.shields.io/github/forks/unclecode/crawl4ai?style=social)](https://github.com/unclecode/crawl4ai/network/members)

crawl4ai/chunking_strategy.py

@@ -55,7 +55,7 @@ class TopicSegmentationChunking(ChunkingStrategy):
     
     def __init__(self, num_keywords=3, **kwargs):
         import nltk as nl
-        self.tokenizer = nl.tokenize.TextTilingTokenizer()
+        self.tokenizer = nl.toknize.TextTilingTokenizer()
         self.num_keywords = num_keywords
 
     def chunk(self, text: str) -> list:

crawl4ai/crawler_strategy.py

@@ -292,22 +292,15 @@ class LocalSeleniumCrawlerStrategy(CrawlerStrategy):
             # Open the screenshot with PIL
             image = Image.open(BytesIO(screenshot))
 
-            # Convert image to RGB mode
-            rgb_image = image.convert('RGB')
-
             # Convert to JPEG and compress
             buffered = BytesIO()
-            rgb_image.save(buffered, format="JPEG", quality=85)
+            image.save(buffered, format="JPEG", quality=85)
             img_base64 = base64.b64encode(buffered.getvalue()).decode('utf-8')
 
             if self.verbose:
                 print(f"[LOG] 📸 Screenshot taken and converted to base64")
 
             return img_base64
-        except Exception as e:
-            if self.verbose:
-                print(f"[ERROR] Failed to take screenshot: {str(e)}")
-            return ""
 
         except Exception as e:
             error_message = sanitize_input_encode(f"Failed to take screenshot: {str(e)}")

docs/md/changelog.md

@@ -1,15 +1,5 @@
 # Changelog
 
-## [v0.2.75] - 2024-07-19
-
-Minor improvements for a more maintainable codebase:
-
-- 🔄 Fixed typos in `chunking_strategy.py` and `crawler_strategy.py` to improve code readability
-- 🔄 Removed `.test_pads/` directory from `.gitignore` to keep our repository clean and organized
-
-These changes may seem small, but they contribute to a more stable and sustainable codebase. By fixing typos and updating our `.gitignore` settings, we're ensuring that our code is easier to maintain and scale in the long run.
-
-
 ## v0.2.74 - 2024-07-08
 A slew of exciting updates to improve the crawler's stability and robustness! 🎉
 

docs/md/demo.md

@@ -14,7 +14,6 @@
             <div class="form-group">
                 <button class="btn btn-default" type="submit">Submit</button>
             </div>
-
         </fieldset>
     </form>
 
@@ -94,10 +93,6 @@
         </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');
@@ -167,17 +162,7 @@
                 },
                 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(response => response.json())
             .then(data => {
                 data = data.results[0]; // Only one URL is requested
                 document.getElementById('loading').style.display = 'none';
@@ -202,29 +187,11 @@ result = crawler.run(
 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;
+                document.getElementById('response').style.display = 'block';
+                document.getElementById('markdownContent').textContent = 'Error: ' + error;
             });
         });
     </script>

docs/md/index.md

@@ -1,4 +1,4 @@
-# Crawl4AI v0.2.75
+# Crawl4AI v0.2.74
 
 Welcome to the official documentation for Crawl4AI! 🕷️🤖 Crawl4AI is an open-source Python library designed to simplify web crawling and extract useful information from web pages. This documentation will guide you through the features, usage, and customization of Crawl4AI.
 

main.py

@@ -22,15 +22,6 @@ from typing import List, Optional
 from crawl4ai.web_crawler import WebCrawler
 from crawl4ai.database import get_total_count, clear_db
 
-import time
-from slowapi import Limiter, _rate_limit_exceeded_handler
-from slowapi.util import get_remote_address
-from slowapi.errors import RateLimitExceeded
-
-# load .env file
-from dotenv import load_dotenv
-load_dotenv()
-
 # Configuration
 __location__ = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))
 MAX_CONCURRENT_REQUESTS = 10  # Adjust this to change the maximum concurrent requests
@@ -39,78 +30,6 @@ lock = asyncio.Lock()
 
 app = FastAPI()
 
-# Initialize rate limiter
-def rate_limit_key_func(request: Request):
-    access_token = request.headers.get("access-token")
-    if access_token == os.environ.get('ACCESS_TOKEN'):
-        return None
-    return get_remote_address(request)
-
-limiter = Limiter(key_func=rate_limit_key_func)
-app.state.limiter = limiter
-
-# Dictionary to store last request times for each client
-last_request_times = {}
-last_rate_limit = {}
-
-
-def get_rate_limit():
-    limit = os.environ.get('ACCESS_PER_MIN', "5")
-    return f"{limit}/minute"
-
-# Custom rate limit exceeded handler
-async def custom_rate_limit_exceeded_handler(request: Request, exc: RateLimitExceeded) -> JSONResponse:
-    if request.client.host not in last_rate_limit or time.time() - last_rate_limit[request.client.host] > 60:
-        last_rate_limit[request.client.host] = time.time()
-    retry_after = 60 - (time.time() - last_rate_limit[request.client.host])
-    reset_at = time.time() + retry_after
-    return JSONResponse(
-        status_code=429,
-        content={
-            "detail": "Rate limit exceeded",
-            "limit": str(exc.limit.limit),
-            "retry_after": retry_after,
-            'reset_at': reset_at,
-            "message": f"You have exceeded the rate limit of {exc.limit.limit}."
-        }
-    )
-    
-app.add_exception_handler(RateLimitExceeded, custom_rate_limit_exceeded_handler)
-
-
-# Middleware for token-based bypass and per-request limit
-class RateLimitMiddleware(BaseHTTPMiddleware):
-    async def dispatch(self, request: Request, call_next):
-        SPAN = int(os.environ.get('ACCESS_TIME_SPAN', 10))
-        access_token = request.headers.get("access-token")
-        if access_token == os.environ.get('ACCESS_TOKEN'):
-            return await call_next(request)
-        
-        path = request.url.path
-        if path in ["/crawl", "/old"]:
-            client_ip = request.client.host
-            current_time = time.time()
-            
-            # Check time since last request
-            if client_ip in last_request_times:
-                time_since_last_request = current_time - last_request_times[client_ip]
-                if time_since_last_request < SPAN:
-                    return JSONResponse(
-                        status_code=429,
-                        content={
-                            "detail": "Too many requests",
-                            "message": "Rate limit exceeded. Please wait 10 seconds between requests.",
-                            "retry_after": max(0, SPAN - time_since_last_request),
-                            "reset_at": current_time + max(0, SPAN - time_since_last_request),
-                        }
-                    )
-            
-            last_request_times[client_ip] = current_time
-
-        return await call_next(request)
-
-app.add_middleware(RateLimitMiddleware)
-
 # CORS configuration
 origins = ["*"]  # Allow all origins
 app.add_middleware(
@@ -154,7 +73,6 @@ def read_root():
     return RedirectResponse(url="/mkdocs")
 
 @app.get("/old", response_class=HTMLResponse)
-@limiter.limit(get_rate_limit())
 async def read_index(request: Request):
     partials_dir = os.path.join(__location__, "pages", "partial")
     partials = {}
@@ -189,7 +107,6 @@ def import_strategy(module_name: str, class_name: str, *args, **kwargs):
         raise HTTPException(status_code=400, detail=f"Class {class_name} not found in {module_name}.")
 
 @app.post("/crawl")
-@limiter.limit(get_rate_limit())
 async def crawl_urls(crawl_request: CrawlRequest, request: Request):
     logging.debug(f"[LOG] Crawl request for URL: {crawl_request.urls}")
     global current_requests

setup.py

@@ -1,18 +1,18 @@
 from setuptools import setup, find_packages
 import os
 from pathlib import Path
-import shutil
+import subprocess
+from setuptools.command.install import install
 
 # Create the .crawl4ai folder in the user's home directory if it doesn't exist
 # If the folder already exists, remove the cache folder
-crawl4ai_folder = Path.home() / ".crawl4ai"
-cache_folder = crawl4ai_folder / "cache"
+crawl4ai_folder = os.path.join(Path.home(), ".crawl4ai")
+if os.path.exists(f"{crawl4ai_folder}/cache"):
+    subprocess.run(["rm", "-rf", f"{crawl4ai_folder}/cache"])
+os.makedirs(crawl4ai_folder, exist_ok=True)
+os.makedirs(f"{crawl4ai_folder}/cache", exist_ok=True)
 
-if cache_folder.exists():
-    shutil.rmtree(cache_folder)
 
-crawl4ai_folder.mkdir(exist_ok=True)
-cache_folder.mkdir(exist_ok=True)
 
 # Read the requirements from requirements.txt
 with open("requirements.txt") as f: