ayrisdev/crawl4ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update:

Browse Source 
- Fix Spacy model issue
- Update Readme and requirements.txt
This commit is contained in:
unclecode
2024-05-16 19:50:20 +08:00
parent 6a6365ae0a
commit c8589f8da3
8 changed files with 137 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@@ -117,7 +117,10 @@ To install Crawl4AI as a library, follow these steps:
1. Install the package from GitHub:
```bash
virtualenv venv
source venv/bin/activate
pip install git+https://github.com/unclecode/crawl4ai.git
python docs/examples/quickstart.py
```
2. Alternatively, you can clone the repository and install the package locally:
@@ -192,6 +195,8 @@ For more information about the available parameters and their descriptions, refe
## Python Library Usage 🚀
🔥 A great way to try out Crawl4AI is to run `quickstart.py` in the `docs/examples` directory. This script demonstrates how to use Crawl4AI to crawl a website and extract content from it.
### Quickstart Guide
Create an instance of WebCrawler and call the `warmup()` function.

9
crawl4ai/chunking_strategy.py
View File

@@ -6,6 +6,7 @@ import re
# from nltk.tokenize import word_tokenize, TextTilingTokenizer
from collections import Counter
import string
from .model_loader import load_spacy_en_core_web_sm
# Define the abstract base class for chunking strategies
class ChunkingStrategy(ABC):
@@ -37,13 +38,7 @@ class RegexChunking(ChunkingStrategy):
class NlpSentenceChunking(ChunkingStrategy):
def __init__(self, model='en_core_web_sm'):
import spacy
try:
self.nlp = spacy.load(model)
except IOError:
spacy.cli.download("en_core_web_sm")
self.nlp = spacy.load(model)
# raise ImportError(f"Spacy model '{model}' not found. Please download the model using 'python -m spacy download {model}'")
self.nlp = load_spacy_en_core_web_sm()
def chunk(self, text: str) -> list:
doc = self.nlp(text)

2
crawl4ai/config.py
View File

@@ -5,7 +5,7 @@ load_dotenv() # Load environment variables from .env file
# Default provider, ONLY used when the extraction strategy is LLMExtractionStrategy
DEFAULT_PROVIDER = "openai/gpt-4-turbo"
MODEL_REPO_BRANCH = "new-release-0.0.2"
# Provider-model dictionary, ONLY used when the extraction strategy is LLMExtractionStrategy
PROVIDER_MODELS = {
"ollama/llama3": "no-token-needed", # Any model from Ollama no need for API token

72
crawl4ai/model_loader.py
View File

@@ -1,20 +1,86 @@
from functools import lru_cache
from transformers import BertTokenizer, BertModel, AutoTokenizer, AutoModel
import spacy
from .utils import get_home_folder
from pathlib import Path
import subprocess, os
import shutil
from .config import MODEL_REPO_BRANCH
@lru_cache()
def load_bert_base_uncased():
from transformers import BertTokenizer, BertModel, AutoTokenizer, AutoModel
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased', resume_download=None)
model = BertModel.from_pretrained('bert-base-uncased', resume_download=None)
return tokenizer, model
@lru_cache()
def load_bge_small_en_v1_5():
from transformers import BertTokenizer, BertModel, AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-small-en-v1.5', resume_download=None)
model = AutoModel.from_pretrained('BAAI/bge-small-en-v1.5', resume_download=None)
model.eval()
return tokenizer, model
@lru_cache()
def load_spacy_en_core_web_sm():
import spacy
try:
print("[LOG] Loading spaCy model")
nlp = spacy.load("en_core_web_sm")
except IOError:
print("[LOG] ⏬ Downloading spaCy model for the first time")
spacy.cli.download("en_core_web_sm")
nlp = spacy.load("en_core_web_sm")
print("[LOG] ✅ spaCy model loaded successfully")
return nlp
@lru_cache()
def load_spacy_model():
return spacy.load("models/reuters")
import spacy
name = "models/reuters"
home_folder = get_home_folder()
model_folder = os.path.join(home_folder, name)
# Check if the model directory already exists
if True or not (Path(model_folder).exists() and any(Path(model_folder).iterdir())):
repo_url = "https://github.com/unclecode/crawl4ai.git"
# branch = "main"
branch = MODEL_REPO_BRANCH
repo_folder = os.path.join(home_folder, "crawl4ai")
model_folder = os.path.join(home_folder, name)
print("[LOG] ⏬ Downloading model for the first time...")
# Remove existing repo folder if it exists
if Path(repo_folder).exists():
shutil.rmtree(repo_folder)
shutil.rmtree(model_folder)
try:
# Clone the repository
subprocess.run(
["git", "clone", "-b", branch, repo_url, repo_folder],
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
check=True
)
# Create the models directory if it doesn't exist
models_folder = os.path.join(home_folder, "models")
os.makedirs(models_folder, exist_ok=True)
# Copy the reuters model folder to the models directory
source_folder = os.path.join(repo_folder, "models/reuters")
shutil.copytree(source_folder, model_folder)
# Remove the cloned repository
shutil.rmtree(repo_folder)
# Print completion message
print("[LOG] ✅ Model downloaded successfully")
except subprocess.CalledProcessError as e:
print(f"An error occurred while cloning the repository: {e}")
except Exception as e:
print(f"An error occurred: {e}")
return spacy.load(model_folder)

9
crawl4ai/utils.py
View File

@@ -9,10 +9,19 @@ import os
from html2text import HTML2Text
from .prompts import PROMPT_EXTRACT_BLOCKS
from .config import *
from pathlib import Path
class InvalidCSSSelectorError(Exception):
pass
def get_home_folder():
home_folder = os.path.join(Path.home(), ".crawl4ai")
os.makedirs(home_folder, exist_ok=True)
os.makedirs(f"{home_folder}/cache", exist_ok=True)
os.makedirs(f"{home_folder}/models", exist_ok=True)
return home_folder
def beautify_html(escaped_html):
"""
Beautifies an escaped HTML string.

7
crawl4ai/web_crawler.py
View File

@@ -34,13 +34,16 @@ class WebCrawler:
# if not db_path:
# self.db_path = f"{self.crawl4ai_folder}/crawl4ai.db"
flush_db()
# flush_db()
init_db()
self.ready = False
def warmup(self):
print("[LOG] 🌤️ Warming up the WebCrawler")
print("[LOG] 🌤️ Warming up the WebCrawler")
result = self.run(
url='https://crawl4ai.uccode.io/',
word_count_threshold=5,

100
docs/quickstart.py → docs/examples/quickstart.py
View File

@@ -1,18 +1,26 @@
import os, time
import os
import time
from crawl4ai.web_crawler import WebCrawler
from crawl4ai.chunking_strategy import *
from crawl4ai.extraction_strategy import *
from crawl4ai.crawler_strategy import *
from rich import print
from rich.console import Console
from functools import lru_cache
console = Console()
@lru_cache()
def create_crawler():
crawler = WebCrawler()
crawler.warmup()
return crawler
def print_result(result):
# Print each key in one line and just the first 10 characters of each one's value and three dots
console.print(f"\t[bold]Result:[/bold]")
for key, value in result.model_dump().items():
if type(value) == str and value:
if isinstance(value, str) and value:
console.print(f"\t{key}: [green]{value[:20]}...[/green]")
def cprint(message, press_any_key=False):
@@ -21,26 +29,17 @@ def cprint(message, press_any_key=False):
console.print("Press any key to continue...", style="")
input()
def main():
# 🚀 Let's get started with the basics!
cprint("🌟 [bold green]Welcome to the Crawl4ai Quickstart Guide! Let's dive into some web crawling fun! 🌐[/bold green]")
# Basic usage: Just provide the URL
cprint("⛳️ [bold cyan]First Step: Create an instance of WebCrawler and call the `warmup()` function.[/bold cyan]")
cprint("If this is the first time you're running Crawl4ai, this might take a few seconds to lead required model files.", True)
crawler = WebCrawler()
crawler.warmup()
def basic_usage(crawler):
cprint("🛠️ [bold cyan]Basic Usage: Simply provide a URL and let Crawl4ai do the magic![/bold cyan]")
result = crawler.run(url="https://www.nbcnews.com/business")
cprint("[LOG] 📦 [bold yellow]Basic crawl result:[/bold yellow]")
print_result(result)
# Explanation of bypass_cache and include_raw_html
def understanding_parameters(crawler):
cprint("\n🧠 [bold cyan]Understanding 'bypass_cache' and 'include_raw_html' parameters:[/bold cyan]")
cprint("By default, Crawl4ai caches the results of your crawls. This means that subsequent crawls of the same URL will be much faster! Let's see this in action. Becuase we already crawled this URL, the result will be fetched from the cache. Let's try it out!")
cprint("By default, Crawl4ai caches the results of your crawls. This means that subsequent crawls of the same URL will be much faster! Let's see this in action.")
# Reads from cache
# First crawl (reads from cache)
cprint("1️⃣ First crawl (caches the result):", True)
start_time = time.time()
result = crawler.run(url="https://www.nbcnews.com/business")
@@ -57,16 +56,12 @@ def main():
print_result(result)
# Retrieve raw HTML content
cprint("\n🔄 [bold cyan]By default 'include_raw_html' is set to True, which includes the raw HTML content in the response.[/bold cyan]", True)
cprint("\n🔄 [bold cyan]'include_raw_html' parameter example:[/bold cyan]", True)
result = crawler.run(url="https://www.nbcnews.com/business", include_raw_html=False)
cprint("[LOG] 📦 [bold yellow]Craw result (without raw HTML content):[/bold yellow]")
cprint("[LOG] 📦 [bold yellow]Crawl result (without raw HTML content):[/bold yellow]")
print_result(result)
cprint("\n📄 The 'include_raw_html' parameter, when set to True, includes the raw HTML content in the response. By default is set to True. Let's move on to exploring different chunking strategies now!")
cprint("For the rest of this guide, I set crawler.always_by_pass_cache to True to force the crawler to bypass the cache. This is to ensure that we get fresh results for each run.", True)
crawler.always_by_pass_cache = True
def add_chunking_strategy(crawler):
# Adding a chunking strategy: RegexChunking
cprint("\n🧩 [bold cyan]Let's add a chunking strategy: RegexChunking![/bold cyan]", True)
cprint("RegexChunking is a simple chunking strategy that splits the text based on a given regex pattern. Let's see it in action!")
@@ -86,9 +81,8 @@ def main():
)
cprint("[LOG] 📦 [bold yellow]NlpSentenceChunking result:[/bold yellow]")
print_result(result)
cprint("There are more chunking strategies to explore, make sure to check document, but let's move on to extraction strategies now!")
def add_extraction_strategy(crawler):
# Adding an extraction strategy: CosineStrategy
cprint("\n🧠 [bold cyan]Let's get smarter with an extraction strategy: CosineStrategy![/bold cyan]", True)
cprint("CosineStrategy uses cosine similarity to extract semantically similar blocks of text. Let's see it in action!")
@@ -99,6 +93,7 @@ def main():
cprint("[LOG] 📦 [bold yellow]CosineStrategy result:[/bold yellow]")
print_result(result)
# Using semantic_filter with CosineStrategy
cprint("You can pass other parameters like 'semantic_filter' to the CosineStrategy to extract semantically similar blocks of text. Let's see it in action!")
result = crawler.run(
url="https://www.nbcnews.com/business",
@@ -106,10 +101,10 @@ def main():
semantic_filter="inflation rent prices",
)
)
cprint("[LOG] 📦 [bold yellow]CosineStrategy result with semantic filter:[/bold yellow]")
print_result(result)
print_result(result)
def add_llm_extraction_strategy(crawler):
# Adding an LLM extraction strategy without instructions
cprint("\n🤖 [bold cyan]Time to bring in the big guns: LLMExtractionStrategy without instructions![/bold cyan]", True)
cprint("LLMExtractionStrategy uses a large language model to extract relevant information from the web page. Let's see it in action!")
@@ -120,8 +115,6 @@ def main():
cprint("[LOG] 📦 [bold yellow]LLMExtractionStrategy (no instructions) result:[/bold yellow]")
print_result(result)
cprint("You can pass other providers like 'groq/llama3-70b-8192' or 'ollama/llama3' to the LLMExtractionStrategy.")
# Adding an LLM extraction strategy with instructions
cprint("\n📜 [bold cyan]Let's make it even more interesting: LLMExtractionStrategy with instructions![/bold cyan]", True)
cprint("Let's say we are only interested in financial news. Let's see how LLMExtractionStrategy performs with instructions!")
@@ -143,12 +136,11 @@ def main():
api_token=os.getenv('OPENAI_API_KEY'),
instruction="Extract only content related to technology"
)
)
cprint("You can pass other instructions like 'Extract only content related to technology' to the LLMExtractionStrategy.")
cprint("There are more extraction strategies to explore, make sure to check the documentation!")
)
cprint("[LOG] 📦 [bold yellow]LLMExtractionStrategy (with technology instruction) result:[/bold yellow]")
print_result(result)
def targeted_extraction(crawler):
# Using a CSS selector to extract only H2 tags
cprint("\n🎯 [bold cyan]Targeted extraction: Let's use a CSS selector to extract only H2 tags![/bold cyan]", True)
result = crawler.run(
@@ -158,6 +150,7 @@ def main():
cprint("[LOG] 📦 [bold yellow]CSS Selector (H2 tags) result:[/bold yellow]")
print_result(result)
def interactive_extraction(crawler):
# Passing JavaScript code to interact with the page
cprint("\n🖱️ [bold cyan]Let's get interactive: Passing JavaScript code to click 'Load More' button![/bold cyan]", True)
cprint("In this example we try to click the 'Load More' button on the page using JavaScript code.")
@@ -173,31 +166,26 @@ def main():
cprint("[LOG] 📦 [bold yellow]JavaScript Code (Load More button) result:[/bold yellow]")
print_result(result)
def main():
cprint("🌟 [bold green]Welcome to the Crawl4ai Quickstart Guide! Let's dive into some web crawling fun! 🌐[/bold green]")
cprint("⛳️ [bold cyan]First Step: Create an instance of WebCrawler and call the `warmup()` function.[/bold cyan]")
cprint("If this is the first time you're running Crawl4ai, this might take a few seconds to load required model files.")
crawler = create_crawler()
cprint("For the rest of this guide, I set crawler.always_by_pass_cache to True to force the crawler to bypass the cache. This is to ensure that we get fresh results for each run.", True)
crawler.always_by_pass_cache = True
basic_usage(crawler)
understanding_parameters(crawler)
add_chunking_strategy(crawler)
add_extraction_strategy(crawler)
add_llm_extraction_strategy(crawler)
targeted_extraction(crawler)
interactive_extraction(crawler)
cprint("\n🎉 [bold green]Congratulations! You've made it through the Crawl4ai Quickstart Guide! Now go forth and crawl the web like a pro! 🕸️[/bold green]")
if __name__ == "__main__":
main()
def old_main():
js_code = """const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();"""
# js_code = None
crawler = WebCrawler( crawler_strategy=LocalSeleniumCrawlerStrategy(use_cached_html=False, js_code=js_code))
crawler.warmup()
# Single page crawl
result = crawler.run(
url="https://www.nbcnews.com/business",
word_count_threshold=5, # Minimum word count for a HTML tag to be considered as a worthy block
chunking_strategy=RegexChunking(patterns=["\n\n"]), # Default is RegexChunking
# extraction_strategy=CosineStrategy(word_count_threshold=10, max_dist=0.2, linkage_method="ward", top_k=3), # Default is CosineStrategy
extraction_strategy= LLMExtractionStrategy(provider= "openai/gpt-4o", api_token = os.getenv('OPENAI_API_KEY'), instruction = "I am intrested in only financial news"),
bypass_cache=True,
extract_blocks=True, # Whether to extract semantical blocks of text from the HTML
css_selector="", # Eg: "div.article-body" or all H2 tags liek "h2"
verbose=True,
include_raw_html=True, # Whether to include the raw HTML content in the response
)
print("[LOG] 📦 Crawl result:")
print(result.model_dump())

3
requirements.txt
View File

@@ -14,4 +14,5 @@ python-dotenv
nltk
lazy_import
rich
# spacy
spacy
scikit-learn