Remove old quickstart files
This commit is contained in:
UncleCode
@@ -1,675 +0,0 @@
|
|||||||
import os, sys
|
|
||||||
|
|
||||||
from crawl4ai import LLMConfig
|
|
||||||
|
|
||||||
# append parent directory to system path
|
|
||||||
sys.path.append(
|
|
||||||
os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
|
||||||
)
|
|
||||||
os.environ["FIRECRAWL_API_KEY"] = "fc-84b370ccfad44beabc686b38f1769692"
|
|
||||||
|
|
||||||
import asyncio
|
|
||||||
# import nest_asyncio
|
|
||||||
# nest_asyncio.apply()
|
|
||||||
|
|
||||||
import time
|
|
||||||
import json
|
|
||||||
import os
|
|
||||||
import re
|
|
||||||
from typing import Dict, List
|
|
||||||
from bs4 import BeautifulSoup
|
|
||||||
from pydantic import BaseModel, Field
|
|
||||||
from crawl4ai import AsyncWebCrawler, CacheMode
|
|
||||||
from crawl4ai.markdown_generation_strategy import DefaultMarkdownGenerator
|
|
||||||
from crawl4ai.content_filter_strategy import PruningContentFilter
|
|
||||||
from crawl4ai.extraction_strategy import (
|
|
||||||
JsonCssExtractionStrategy,
|
|
||||||
LLMExtractionStrategy,
|
|
||||||
)
|
|
||||||
|
|
||||||
__location__ = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))
|
|
||||||
|
|
||||||
print("Crawl4AI: Advanced Web Crawling and Data Extraction")
|
|
||||||
print("GitHub Repository: https://github.com/unclecode/crawl4ai")
|
|
||||||
print("Twitter: @unclecode")
|
|
||||||
print("Website: https://crawl4ai.com")
|
|
||||||
|
|
||||||
|
|
||||||
async def simple_crawl():
|
|
||||||
print("\n--- Basic Usage ---")
|
|
||||||
async with AsyncWebCrawler(verbose=True) as crawler:
|
|
||||||
result = await crawler.arun(
|
|
||||||
url="https://www.nbcnews.com/business", cache_mode=CacheMode.BYPASS
|
|
||||||
)
|
|
||||||
print(result.markdown[:500]) # Print first 500 characters
|
|
||||||
|
|
||||||
|
|
||||||
async def simple_example_with_running_js_code():
|
|
||||||
print("\n--- Executing JavaScript and Using CSS Selectors ---")
|
|
||||||
# New code to handle the wait_for parameter
|
|
||||||
wait_for = """() => {
|
|
||||||
return Array.from(document.querySelectorAll('article.tease-card')).length > 10;
|
|
||||||
}"""
|
|
||||||
|
|
||||||
# wait_for can be also just a css selector
|
|
||||||
# wait_for = "article.tease-card:nth-child(10)"
|
|
||||||
|
|
||||||
async with AsyncWebCrawler(verbose=True) as crawler:
|
|
||||||
js_code = [
|
|
||||||
"const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();"
|
|
||||||
]
|
|
||||||
result = await crawler.arun(
|
|
||||||
url="https://www.nbcnews.com/business",
|
|
||||||
js_code=js_code,
|
|
||||||
# wait_for=wait_for,
|
|
||||||
cache_mode=CacheMode.BYPASS,
|
|
||||||
)
|
|
||||||
print(result.markdown[:500]) # Print first 500 characters
|
|
||||||
|
|
||||||
|
|
||||||
async def simple_example_with_css_selector():
|
|
||||||
print("\n--- Using CSS Selectors ---")
|
|
||||||
async with AsyncWebCrawler(verbose=True) as crawler:
|
|
||||||
result = await crawler.arun(
|
|
||||||
url="https://www.nbcnews.com/business",
|
|
||||||
css_selector=".wide-tease-item__description",
|
|
||||||
cache_mode=CacheMode.BYPASS,
|
|
||||||
)
|
|
||||||
print(result.markdown[:500]) # Print first 500 characters
|
|
||||||
|
|
||||||
|
|
||||||
async def use_proxy():
|
|
||||||
print("\n--- Using a Proxy ---")
|
|
||||||
print(
|
|
||||||
"Note: Replace 'http://your-proxy-url:port' with a working proxy to run this example."
|
|
||||||
)
|
|
||||||
# Uncomment and modify the following lines to use a proxy
|
|
||||||
async with AsyncWebCrawler(
|
|
||||||
verbose=True, proxy="http://your-proxy-url:port"
|
|
||||||
) as crawler:
|
|
||||||
result = await crawler.arun(
|
|
||||||
url="https://www.nbcnews.com/business", cache_mode=CacheMode.BYPASS
|
|
||||||
)
|
|
||||||
if result.success:
|
|
||||||
print(result.markdown[:500]) # Print first 500 characters
|
|
||||||
|
|
||||||
|
|
||||||
async def capture_and_save_screenshot(url: str, output_path: str):
|
|
||||||
async with AsyncWebCrawler(verbose=True) as crawler:
|
|
||||||
result = await crawler.arun(
|
|
||||||
url=url, screenshot=True, cache_mode=CacheMode.BYPASS
|
|
||||||
)
|
|
||||||
|
|
||||||
if result.success and result.screenshot:
|
|
||||||
import base64
|
|
||||||
|
|
||||||
# Decode the base64 screenshot data
|
|
||||||
screenshot_data = base64.b64decode(result.screenshot)
|
|
||||||
|
|
||||||
# Save the screenshot as a JPEG file
|
|
||||||
with open(output_path, "wb") as f:
|
|
||||||
f.write(screenshot_data)
|
|
||||||
|
|
||||||
print(f"Screenshot saved successfully to {output_path}")
|
|
||||||
else:
|
|
||||||
print("Failed to capture screenshot")
|
|
||||||
|
|
||||||
|
|
||||||
class OpenAIModelFee(BaseModel):
|
|
||||||
model_name: str = Field(..., description="Name of the OpenAI model.")
|
|
||||||
input_fee: str = Field(..., description="Fee for input token for the OpenAI model.")
|
|
||||||
output_fee: str = Field(
|
|
||||||
..., description="Fee for output token for the OpenAI model."
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
async def extract_structured_data_using_llm(
|
|
||||||
provider: str, api_token: str = None, extra_headers: Dict[str, str] = None
|
|
||||||
):
|
|
||||||
print(f"\n--- Extracting Structured Data with {provider} ---")
|
|
||||||
|
|
||||||
if api_token is None and provider != "ollama":
|
|
||||||
print(f"API token is required for {provider}. Skipping this example.")
|
|
||||||
return
|
|
||||||
|
|
||||||
# extra_args = {}
|
|
||||||
extra_args = {
|
|
||||||
"temperature": 0,
|
|
||||||
"top_p": 0.9,
|
|
||||||
"max_tokens": 2000,
|
|
||||||
# any other supported parameters for litellm
|
|
||||||
}
|
|
||||||
if extra_headers:
|
|
||||||
extra_args["extra_headers"] = extra_headers
|
|
||||||
|
|
||||||
async with AsyncWebCrawler(verbose=True) as crawler:
|
|
||||||
result = await crawler.arun(
|
|
||||||
url="https://openai.com/api/pricing/",
|
|
||||||
word_count_threshold=1,
|
|
||||||
extraction_strategy=LLMExtractionStrategy(
|
|
||||||
llm_config=LLMConfig(provider=provider,api_token=api_token),
|
|
||||||
schema=OpenAIModelFee.model_json_schema(),
|
|
||||||
extraction_type="schema",
|
|
||||||
instruction="""From the crawled content, extract all mentioned model names along with their fees for input and output tokens.
|
|
||||||
Do not miss any models in the entire content. One extracted model JSON format should look like this:
|
|
||||||
{"model_name": "GPT-4", "input_fee": "US$10.00 / 1M tokens", "output_fee": "US$30.00 / 1M tokens"}.""",
|
|
||||||
extra_args=extra_args,
|
|
||||||
),
|
|
||||||
cache_mode=CacheMode.BYPASS,
|
|
||||||
)
|
|
||||||
print(result.extracted_content)
|
|
||||||
|
|
||||||
|
|
||||||
async def extract_structured_data_using_css_extractor():
|
|
||||||
print("\n--- Using JsonCssExtractionStrategy for Fast Structured Output ---")
|
|
||||||
schema = {
|
|
||||||
"name": "KidoCode Courses",
|
|
||||||
"baseSelector": "section.charge-methodology .w-tab-content > div",
|
|
||||||
"fields": [
|
|
||||||
{
|
|
||||||
"name": "section_title",
|
|
||||||
"selector": "h3.heading-50",
|
|
||||||
"type": "text",
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "section_description",
|
|
||||||
"selector": ".charge-content",
|
|
||||||
"type": "text",
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "course_name",
|
|
||||||
"selector": ".text-block-93",
|
|
||||||
"type": "text",
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "course_description",
|
|
||||||
"selector": ".course-content-text",
|
|
||||||
"type": "text",
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "course_icon",
|
|
||||||
"selector": ".image-92",
|
|
||||||
"type": "attribute",
|
|
||||||
"attribute": "src",
|
|
||||||
},
|
|
||||||
],
|
|
||||||
}
|
|
||||||
|
|
||||||
async with AsyncWebCrawler(headless=True, verbose=True) as crawler:
|
|
||||||
# Create the JavaScript that handles clicking multiple times
|
|
||||||
js_click_tabs = """
|
|
||||||
(async () => {
|
|
||||||
const tabs = document.querySelectorAll("section.charge-methodology .tabs-menu-3 > div");
|
|
||||||
|
|
||||||
for(let tab of tabs) {
|
|
||||||
// scroll to the tab
|
|
||||||
tab.scrollIntoView();
|
|
||||||
tab.click();
|
|
||||||
// Wait for content to load and animations to complete
|
|
||||||
await new Promise(r => setTimeout(r, 500));
|
|
||||||
}
|
|
||||||
})();
|
|
||||||
"""
|
|
||||||
|
|
||||||
result = await crawler.arun(
|
|
||||||
url="https://www.kidocode.com/degrees/technology",
|
|
||||||
extraction_strategy=JsonCssExtractionStrategy(schema, verbose=True),
|
|
||||||
js_code=[js_click_tabs],
|
|
||||||
cache_mode=CacheMode.BYPASS,
|
|
||||||
)
|
|
||||||
|
|
||||||
companies = json.loads(result.extracted_content)
|
|
||||||
print(f"Successfully extracted {len(companies)} companies")
|
|
||||||
print(json.dumps(companies[0], indent=2))
|
|
||||||
|
|
||||||
|
|
||||||
# Advanced Session-Based Crawling with Dynamic Content 🔄
|
|
||||||
async def crawl_dynamic_content_pages_method_1():
|
|
||||||
print("\n--- Advanced Multi-Page Crawling with JavaScript Execution ---")
|
|
||||||
first_commit = ""
|
|
||||||
|
|
||||||
async def on_execution_started(page):
|
|
||||||
nonlocal first_commit
|
|
||||||
try:
|
|
||||||
while True:
|
|
||||||
await page.wait_for_selector("li.Box-sc-g0xbh4-0 h4")
|
|
||||||
commit = await page.query_selector("li.Box-sc-g0xbh4-0 h4")
|
|
||||||
commit = await commit.evaluate("(element) => element.textContent")
|
|
||||||
commit = re.sub(r"\s+", "", commit)
|
|
||||||
if commit and commit != first_commit:
|
|
||||||
first_commit = commit
|
|
||||||
break
|
|
||||||
await asyncio.sleep(0.5)
|
|
||||||
except Exception as e:
|
|
||||||
print(f"Warning: New content didn't appear after JavaScript execution: {e}")
|
|
||||||
|
|
||||||
async with AsyncWebCrawler(verbose=True) as crawler:
|
|
||||||
crawler.crawler_strategy.set_hook("on_execution_started", on_execution_started)
|
|
||||||
|
|
||||||
url = "https://github.com/microsoft/TypeScript/commits/main"
|
|
||||||
session_id = "typescript_commits_session"
|
|
||||||
all_commits = []
|
|
||||||
|
|
||||||
js_next_page = """
|
|
||||||
(() => {
|
|
||||||
const button = document.querySelector('a[data-testid="pagination-next-button"]');
|
|
||||||
if (button) button.click();
|
|
||||||
})();
|
|
||||||
"""
|
|
||||||
|
|
||||||
for page in range(3): # Crawl 3 pages
|
|
||||||
result = await crawler.arun(
|
|
||||||
url=url,
|
|
||||||
session_id=session_id,
|
|
||||||
css_selector="li.Box-sc-g0xbh4-0",
|
|
||||||
js=js_next_page if page > 0 else None,
|
|
||||||
cache_mode=CacheMode.BYPASS,
|
|
||||||
js_only=page > 0,
|
|
||||||
headless=False,
|
|
||||||
)
|
|
||||||
|
|
||||||
assert result.success, f"Failed to crawl page {page + 1}"
|
|
||||||
|
|
||||||
soup = BeautifulSoup(result.cleaned_html, "html.parser")
|
|
||||||
commits = soup.select("li")
|
|
||||||
all_commits.extend(commits)
|
|
||||||
|
|
||||||
print(f"Page {page + 1}: Found {len(commits)} commits")
|
|
||||||
|
|
||||||
await crawler.crawler_strategy.kill_session(session_id)
|
|
||||||
print(f"Successfully crawled {len(all_commits)} commits across 3 pages")
|
|
||||||
|
|
||||||
|
|
||||||
async def crawl_dynamic_content_pages_method_2():
|
|
||||||
print("\n--- Advanced Multi-Page Crawling with JavaScript Execution ---")
|
|
||||||
|
|
||||||
async with AsyncWebCrawler(verbose=True) as crawler:
|
|
||||||
url = "https://github.com/microsoft/TypeScript/commits/main"
|
|
||||||
session_id = "typescript_commits_session"
|
|
||||||
all_commits = []
|
|
||||||
last_commit = ""
|
|
||||||
|
|
||||||
js_next_page_and_wait = """
|
|
||||||
(async () => {
|
|
||||||
const getCurrentCommit = () => {
|
|
||||||
const commits = document.querySelectorAll('li.Box-sc-g0xbh4-0 h4');
|
|
||||||
return commits.length > 0 ? commits[0].textContent.trim() : null;
|
|
||||||
};
|
|
||||||
|
|
||||||
const initialCommit = getCurrentCommit();
|
|
||||||
const button = document.querySelector('a[data-testid="pagination-next-button"]');
|
|
||||||
if (button) button.click();
|
|
||||||
|
|
||||||
// Poll for changes
|
|
||||||
while (true) {
|
|
||||||
await new Promise(resolve => setTimeout(resolve, 100)); // Wait 100ms
|
|
||||||
const newCommit = getCurrentCommit();
|
|
||||||
if (newCommit && newCommit !== initialCommit) {
|
|
||||||
break;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
})();
|
|
||||||
"""
|
|
||||||
|
|
||||||
schema = {
|
|
||||||
"name": "Commit Extractor",
|
|
||||||
"baseSelector": "li.Box-sc-g0xbh4-0",
|
|
||||||
"fields": [
|
|
||||||
{
|
|
||||||
"name": "title",
|
|
||||||
"selector": "h4.markdown-title",
|
|
||||||
"type": "text",
|
|
||||||
"transform": "strip",
|
|
||||||
},
|
|
||||||
],
|
|
||||||
}
|
|
||||||
extraction_strategy = JsonCssExtractionStrategy(schema, verbose=True)
|
|
||||||
|
|
||||||
for page in range(3): # Crawl 3 pages
|
|
||||||
result = await crawler.arun(
|
|
||||||
url=url,
|
|
||||||
session_id=session_id,
|
|
||||||
css_selector="li.Box-sc-g0xbh4-0",
|
|
||||||
extraction_strategy=extraction_strategy,
|
|
||||||
js_code=js_next_page_and_wait if page > 0 else None,
|
|
||||||
js_only=page > 0,
|
|
||||||
cache_mode=CacheMode.BYPASS,
|
|
||||||
headless=False,
|
|
||||||
)
|
|
||||||
|
|
||||||
assert result.success, f"Failed to crawl page {page + 1}"
|
|
||||||
|
|
||||||
commits = json.loads(result.extracted_content)
|
|
||||||
all_commits.extend(commits)
|
|
||||||
|
|
||||||
print(f"Page {page + 1}: Found {len(commits)} commits")
|
|
||||||
|
|
||||||
await crawler.crawler_strategy.kill_session(session_id)
|
|
||||||
print(f"Successfully crawled {len(all_commits)} commits across 3 pages")
|
|
||||||
|
|
||||||
|
|
||||||
async def crawl_dynamic_content_pages_method_3():
|
|
||||||
print(
|
|
||||||
"\n--- Advanced Multi-Page Crawling with JavaScript Execution using `wait_for` ---"
|
|
||||||
)
|
|
||||||
|
|
||||||
async with AsyncWebCrawler(verbose=True) as crawler:
|
|
||||||
url = "https://github.com/microsoft/TypeScript/commits/main"
|
|
||||||
session_id = "typescript_commits_session"
|
|
||||||
all_commits = []
|
|
||||||
|
|
||||||
js_next_page = """
|
|
||||||
const commits = document.querySelectorAll('li.Box-sc-g0xbh4-0 h4');
|
|
||||||
if (commits.length > 0) {
|
|
||||||
window.firstCommit = commits[0].textContent.trim();
|
|
||||||
}
|
|
||||||
const button = document.querySelector('a[data-testid="pagination-next-button"]');
|
|
||||||
if (button) button.click();
|
|
||||||
"""
|
|
||||||
|
|
||||||
wait_for = """() => {
|
|
||||||
const commits = document.querySelectorAll('li.Box-sc-g0xbh4-0 h4');
|
|
||||||
if (commits.length === 0) return false;
|
|
||||||
const firstCommit = commits[0].textContent.trim();
|
|
||||||
return firstCommit !== window.firstCommit;
|
|
||||||
}"""
|
|
||||||
|
|
||||||
schema = {
|
|
||||||
"name": "Commit Extractor",
|
|
||||||
"baseSelector": "li.Box-sc-g0xbh4-0",
|
|
||||||
"fields": [
|
|
||||||
{
|
|
||||||
"name": "title",
|
|
||||||
"selector": "h4.markdown-title",
|
|
||||||
"type": "text",
|
|
||||||
"transform": "strip",
|
|
||||||
},
|
|
||||||
],
|
|
||||||
}
|
|
||||||
extraction_strategy = JsonCssExtractionStrategy(schema, verbose=True)
|
|
||||||
|
|
||||||
for page in range(3): # Crawl 3 pages
|
|
||||||
result = await crawler.arun(
|
|
||||||
url=url,
|
|
||||||
session_id=session_id,
|
|
||||||
css_selector="li.Box-sc-g0xbh4-0",
|
|
||||||
extraction_strategy=extraction_strategy,
|
|
||||||
js_code=js_next_page if page > 0 else None,
|
|
||||||
wait_for=wait_for if page > 0 else None,
|
|
||||||
js_only=page > 0,
|
|
||||||
cache_mode=CacheMode.BYPASS,
|
|
||||||
headless=False,
|
|
||||||
)
|
|
||||||
|
|
||||||
assert result.success, f"Failed to crawl page {page + 1}"
|
|
||||||
|
|
||||||
commits = json.loads(result.extracted_content)
|
|
||||||
all_commits.extend(commits)
|
|
||||||
|
|
||||||
print(f"Page {page + 1}: Found {len(commits)} commits")
|
|
||||||
|
|
||||||
await crawler.crawler_strategy.kill_session(session_id)
|
|
||||||
print(f"Successfully crawled {len(all_commits)} commits across 3 pages")
|
|
||||||
|
|
||||||
|
|
||||||
async def crawl_custom_browser_type():
|
|
||||||
# Use Firefox
|
|
||||||
start = time.time()
|
|
||||||
async with AsyncWebCrawler(
|
|
||||||
browser_type="firefox", verbose=True, headless=True
|
|
||||||
) as crawler:
|
|
||||||
result = await crawler.arun(
|
|
||||||
url="https://www.example.com", cache_mode=CacheMode.BYPASS
|
|
||||||
)
|
|
||||||
print(result.markdown[:500])
|
|
||||||
print("Time taken: ", time.time() - start)
|
|
||||||
|
|
||||||
# Use WebKit
|
|
||||||
start = time.time()
|
|
||||||
async with AsyncWebCrawler(
|
|
||||||
browser_type="webkit", verbose=True, headless=True
|
|
||||||
) as crawler:
|
|
||||||
result = await crawler.arun(
|
|
||||||
url="https://www.example.com", cache_mode=CacheMode.BYPASS
|
|
||||||
)
|
|
||||||
print(result.markdown[:500])
|
|
||||||
print("Time taken: ", time.time() - start)
|
|
||||||
|
|
||||||
# Use Chromium (default)
|
|
||||||
start = time.time()
|
|
||||||
async with AsyncWebCrawler(verbose=True, headless=True) as crawler:
|
|
||||||
result = await crawler.arun(
|
|
||||||
url="https://www.example.com", cache_mode=CacheMode.BYPASS
|
|
||||||
)
|
|
||||||
print(result.markdown[:500])
|
|
||||||
print("Time taken: ", time.time() - start)
|
|
||||||
|
|
||||||
|
|
||||||
async def crawl_with_user_simultion():
|
|
||||||
async with AsyncWebCrawler(verbose=True, headless=True) as crawler:
|
|
||||||
url = "YOUR-URL-HERE"
|
|
||||||
result = await crawler.arun(
|
|
||||||
url=url,
|
|
||||||
cache_mode=CacheMode.BYPASS,
|
|
||||||
magic=True, # Automatically detects and removes overlays, popups, and other elements that block content
|
|
||||||
# simulate_user = True,# Causes a series of random mouse movements and clicks to simulate user interaction
|
|
||||||
# override_navigator = True # Overrides the navigator object to make it look like a real user
|
|
||||||
)
|
|
||||||
|
|
||||||
print(result.markdown)
|
|
||||||
|
|
||||||
|
|
||||||
async def speed_comparison():
|
|
||||||
# print("\n--- Speed Comparison ---")
|
|
||||||
# print("Firecrawl (simulated):")
|
|
||||||
# print("Time taken: 7.02 seconds")
|
|
||||||
# print("Content length: 42074 characters")
|
|
||||||
# print("Images found: 49")
|
|
||||||
# print()
|
|
||||||
# Simulated Firecrawl performance
|
|
||||||
from firecrawl import FirecrawlApp
|
|
||||||
|
|
||||||
app = FirecrawlApp(api_key=os.environ["FIRECRAWL_API_KEY"])
|
|
||||||
start = time.time()
|
|
||||||
scrape_status = app.scrape_url(
|
|
||||||
"https://www.nbcnews.com/business", params={"formats": ["markdown", "html"]}
|
|
||||||
)
|
|
||||||
end = time.time()
|
|
||||||
print("Firecrawl:")
|
|
||||||
print(f"Time taken: {end - start:.2f} seconds")
|
|
||||||
print(f"Content length: {len(scrape_status['markdown'])} characters")
|
|
||||||
print(f"Images found: {scrape_status['markdown'].count('cldnry.s-nbcnews.com')}")
|
|
||||||
print()
|
|
||||||
|
|
||||||
async with AsyncWebCrawler() as crawler:
|
|
||||||
# Crawl4AI simple crawl
|
|
||||||
start = time.time()
|
|
||||||
result = await crawler.arun(
|
|
||||||
url="https://www.nbcnews.com/business",
|
|
||||||
word_count_threshold=0,
|
|
||||||
cache_mode=CacheMode.BYPASS,
|
|
||||||
verbose=False,
|
|
||||||
)
|
|
||||||
end = time.time()
|
|
||||||
print("Crawl4AI (simple crawl):")
|
|
||||||
print(f"Time taken: {end - start:.2f} seconds")
|
|
||||||
print(f"Content length: {len(result.markdown)} characters")
|
|
||||||
print(f"Images found: {result.markdown.count('cldnry.s-nbcnews.com')}")
|
|
||||||
print()
|
|
||||||
|
|
||||||
# Crawl4AI with advanced content filtering
|
|
||||||
start = time.time()
|
|
||||||
result = await crawler.arun(
|
|
||||||
url="https://www.nbcnews.com/business",
|
|
||||||
word_count_threshold=0,
|
|
||||||
markdown_generator=DefaultMarkdownGenerator(
|
|
||||||
content_filter=PruningContentFilter(
|
|
||||||
threshold=0.48, threshold_type="fixed", min_word_threshold=0
|
|
||||||
)
|
|
||||||
# content_filter=BM25ContentFilter(user_query=None, bm25_threshold=1.0)
|
|
||||||
),
|
|
||||||
cache_mode=CacheMode.BYPASS,
|
|
||||||
verbose=False,
|
|
||||||
)
|
|
||||||
end = time.time()
|
|
||||||
print("Crawl4AI (Markdown Plus):")
|
|
||||||
print(f"Time taken: {end - start:.2f} seconds")
|
|
||||||
print(f"Content length: {len(result.markdown.raw_markdown)} characters")
|
|
||||||
print(f"Fit Markdown: {len(result.markdown.fit_markdown)} characters")
|
|
||||||
print(f"Images found: {result.markdown.raw_markdown.count('cldnry.s-nbcnews.com')}")
|
|
||||||
print()
|
|
||||||
|
|
||||||
# Crawl4AI with JavaScript execution
|
|
||||||
start = time.time()
|
|
||||||
result = await crawler.arun(
|
|
||||||
url="https://www.nbcnews.com/business",
|
|
||||||
js_code=[
|
|
||||||
"const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();"
|
|
||||||
],
|
|
||||||
word_count_threshold=0,
|
|
||||||
cache_mode=CacheMode.BYPASS,
|
|
||||||
markdown_generator=DefaultMarkdownGenerator(
|
|
||||||
content_filter=PruningContentFilter(
|
|
||||||
threshold=0.48, threshold_type="fixed", min_word_threshold=0
|
|
||||||
)
|
|
||||||
# content_filter=BM25ContentFilter(user_query=None, bm25_threshold=1.0)
|
|
||||||
),
|
|
||||||
verbose=False,
|
|
||||||
)
|
|
||||||
end = time.time()
|
|
||||||
print("Crawl4AI (with JavaScript execution):")
|
|
||||||
print(f"Time taken: {end - start:.2f} seconds")
|
|
||||||
print(f"Content length: {len(result.markdown.raw_markdown)} characters")
|
|
||||||
print(f"Fit Markdown: {len(result.markdown.fit_markdown)} characters")
|
|
||||||
print(f"Images found: {result.markdown.raw_markdown.count('cldnry.s-nbcnews.com')}")
|
|
||||||
|
|
||||||
print("\nNote on Speed Comparison:")
|
|
||||||
print("The speed test conducted here may not reflect optimal conditions.")
|
|
||||||
print("When we call Firecrawl's API, we're seeing its best performance,")
|
|
||||||
print("while Crawl4AI's performance is limited by the local network speed.")
|
|
||||||
print("For a more accurate comparison, it's recommended to run these tests")
|
|
||||||
print("on servers with a stable and fast internet connection.")
|
|
||||||
print("Despite these limitations, Crawl4AI still demonstrates faster performance.")
|
|
||||||
print("If you run these tests in an environment with better network conditions,")
|
|
||||||
print("you may observe an even more significant speed advantage for Crawl4AI.")
|
|
||||||
|
|
||||||
|
|
||||||
async def generate_knowledge_graph():
|
|
||||||
class Entity(BaseModel):
|
|
||||||
name: str
|
|
||||||
description: str
|
|
||||||
|
|
||||||
class Relationship(BaseModel):
|
|
||||||
entity1: Entity
|
|
||||||
entity2: Entity
|
|
||||||
description: str
|
|
||||||
relation_type: str
|
|
||||||
|
|
||||||
class KnowledgeGraph(BaseModel):
|
|
||||||
entities: List[Entity]
|
|
||||||
relationships: List[Relationship]
|
|
||||||
|
|
||||||
extraction_strategy = LLMExtractionStrategy(
|
|
||||||
llm_config=LLMConfig(provider="openai/gpt-4o-mini", api_token=os.getenv("OPENAI_API_KEY")), # In case of Ollama just pass "no-token"
|
|
||||||
schema=KnowledgeGraph.model_json_schema(),
|
|
||||||
extraction_type="schema",
|
|
||||||
instruction="""Extract entities and relationships from the given text.""",
|
|
||||||
)
|
|
||||||
async with AsyncWebCrawler() as crawler:
|
|
||||||
url = "https://paulgraham.com/love.html"
|
|
||||||
result = await crawler.arun(
|
|
||||||
url=url,
|
|
||||||
cache_mode=CacheMode.BYPASS,
|
|
||||||
extraction_strategy=extraction_strategy,
|
|
||||||
# magic=True
|
|
||||||
)
|
|
||||||
# print(result.extracted_content)
|
|
||||||
with open(os.path.join(__location__, "kb.json"), "w") as f:
|
|
||||||
f.write(result.extracted_content)
|
|
||||||
|
|
||||||
|
|
||||||
async def fit_markdown_remove_overlay():
|
|
||||||
async with AsyncWebCrawler(
|
|
||||||
headless=True, # Set to False to see what is happening
|
|
||||||
verbose=True,
|
|
||||||
user_agent_mode="random",
|
|
||||||
user_agent_generator_config={"device_type": "mobile", "os_type": "android"},
|
|
||||||
) as crawler:
|
|
||||||
result = await crawler.arun(
|
|
||||||
url="https://www.kidocode.com/degrees/technology",
|
|
||||||
cache_mode=CacheMode.BYPASS,
|
|
||||||
markdown_generator=DefaultMarkdownGenerator(
|
|
||||||
content_filter=PruningContentFilter(
|
|
||||||
threshold=0.48, threshold_type="fixed", min_word_threshold=0
|
|
||||||
),
|
|
||||||
options={"ignore_links": True},
|
|
||||||
),
|
|
||||||
# markdown_generator=DefaultMarkdownGenerator(
|
|
||||||
# content_filter=BM25ContentFilter(user_query="", bm25_threshold=1.0),
|
|
||||||
# options={
|
|
||||||
# "ignore_links": True
|
|
||||||
# }
|
|
||||||
# ),
|
|
||||||
)
|
|
||||||
|
|
||||||
if result.success:
|
|
||||||
print(len(result.markdown.raw_markdown))
|
|
||||||
print(len(result.markdown.markdown_with_citations))
|
|
||||||
print(len(result.markdown.fit_markdown))
|
|
||||||
|
|
||||||
# Save clean html
|
|
||||||
with open(os.path.join(__location__, "output/cleaned_html.html"), "w") as f:
|
|
||||||
f.write(result.cleaned_html)
|
|
||||||
|
|
||||||
with open(
|
|
||||||
os.path.join(__location__, "output/output_raw_markdown.md"), "w"
|
|
||||||
) as f:
|
|
||||||
f.write(result.markdown.raw_markdown)
|
|
||||||
|
|
||||||
with open(
|
|
||||||
os.path.join(__location__, "output/output_markdown_with_citations.md"),
|
|
||||||
"w",
|
|
||||||
) as f:
|
|
||||||
f.write(result.markdown.markdown_with_citations)
|
|
||||||
|
|
||||||
with open(
|
|
||||||
os.path.join(__location__, "output/output_fit_markdown.md"), "w"
|
|
||||||
) as f:
|
|
||||||
f.write(result.markdown.fit_markdown)
|
|
||||||
|
|
||||||
print("Done")
|
|
||||||
|
|
||||||
|
|
||||||
async def main():
|
|
||||||
# await extract_structured_data_using_llm("openai/gpt-4o", os.getenv("OPENAI_API_KEY"))
|
|
||||||
|
|
||||||
# await simple_crawl()
|
|
||||||
# await simple_example_with_running_js_code()
|
|
||||||
# await simple_example_with_css_selector()
|
|
||||||
# # await use_proxy()
|
|
||||||
# await capture_and_save_screenshot("https://www.example.com", os.path.join(__location__, "tmp/example_screenshot.jpg"))
|
|
||||||
# await extract_structured_data_using_css_extractor()
|
|
||||||
|
|
||||||
# LLM extraction examples
|
|
||||||
# await extract_structured_data_using_llm()
|
|
||||||
# await extract_structured_data_using_llm("huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct", os.getenv("HUGGINGFACE_API_KEY"))
|
|
||||||
# await extract_structured_data_using_llm("ollama/llama3.2")
|
|
||||||
|
|
||||||
# You always can pass custom headers to the extraction strategy
|
|
||||||
# custom_headers = {
|
|
||||||
# "Authorization": "Bearer your-custom-token",
|
|
||||||
# "X-Custom-Header": "Some-Value"
|
|
||||||
# }
|
|
||||||
# await extract_structured_data_using_llm(extra_headers=custom_headers)
|
|
||||||
|
|
||||||
# await crawl_dynamic_content_pages_method_1()
|
|
||||||
# await crawl_dynamic_content_pages_method_2()
|
|
||||||
await crawl_dynamic_content_pages_method_3()
|
|
||||||
|
|
||||||
# await crawl_custom_browser_type()
|
|
||||||
|
|
||||||
# await speed_comparison()
|
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
|
||||||
asyncio.run(main())
|
|
||||||
@@ -1,405 +0,0 @@
|
|||||||
import os
|
|
||||||
import time
|
|
||||||
from crawl4ai import LLMConfig
|
|
||||||
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(verbose=True)
|
|
||||||
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("\t[bold]Result:[/bold]")
|
|
||||||
for key, value in result.model_dump().items():
|
|
||||||
if isinstance(value, str) and value:
|
|
||||||
console.print(f"\t{key}: [green]{value[:20]}...[/green]")
|
|
||||||
if result.extracted_content:
|
|
||||||
items = json.loads(result.extracted_content)
|
|
||||||
print(f"\t[bold]{len(items)} blocks is extracted![/bold]")
|
|
||||||
|
|
||||||
|
|
||||||
def cprint(message, press_any_key=False):
|
|
||||||
console.print(message)
|
|
||||||
if press_any_key:
|
|
||||||
console.print("Press any key to continue...", style="")
|
|
||||||
input()
|
|
||||||
|
|
||||||
|
|
||||||
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", only_text=True)
|
|
||||||
cprint("[LOG] 📦 [bold yellow]Basic crawl result:[/bold yellow]")
|
|
||||||
print_result(result)
|
|
||||||
|
|
||||||
|
|
||||||
def basic_usage_some_params(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", word_count_threshold=1, only_text=True
|
|
||||||
)
|
|
||||||
cprint("[LOG] 📦 [bold yellow]Basic crawl result:[/bold yellow]")
|
|
||||||
print_result(result)
|
|
||||||
|
|
||||||
|
|
||||||
def screenshot_usage(crawler):
|
|
||||||
cprint("\n📸 [bold cyan]Let's take a screenshot of the page![/bold cyan]")
|
|
||||||
result = crawler.run(url="https://www.nbcnews.com/business", screenshot=True)
|
|
||||||
cprint("[LOG] 📦 [bold yellow]Screenshot result:[/bold yellow]")
|
|
||||||
# Save the screenshot to a file
|
|
||||||
with open("screenshot.png", "wb") as f:
|
|
||||||
f.write(base64.b64decode(result.screenshot))
|
|
||||||
cprint("Screenshot saved to 'screenshot.png'!")
|
|
||||||
print_result(result)
|
|
||||||
|
|
||||||
|
|
||||||
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."
|
|
||||||
)
|
|
||||||
|
|
||||||
# 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")
|
|
||||||
end_time = time.time()
|
|
||||||
cprint(
|
|
||||||
f"[LOG] 📦 [bold yellow]First crawl took {end_time - start_time} seconds and result (from cache):[/bold yellow]"
|
|
||||||
)
|
|
||||||
print_result(result)
|
|
||||||
|
|
||||||
# Force to crawl again
|
|
||||||
cprint("2️⃣ Second crawl (Force to crawl again):", True)
|
|
||||||
start_time = time.time()
|
|
||||||
result = crawler.run(url="https://www.nbcnews.com/business", bypass_cache=True)
|
|
||||||
end_time = time.time()
|
|
||||||
cprint(
|
|
||||||
f"[LOG] 📦 [bold yellow]Second crawl took {end_time - start_time} seconds and result (forced to crawl):[/bold yellow]"
|
|
||||||
)
|
|
||||||
print_result(result)
|
|
||||||
|
|
||||||
|
|
||||||
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!"
|
|
||||||
)
|
|
||||||
result = crawler.run(
|
|
||||||
url="https://www.nbcnews.com/business",
|
|
||||||
chunking_strategy=RegexChunking(patterns=["\n\n"]),
|
|
||||||
)
|
|
||||||
cprint("[LOG] 📦 [bold yellow]RegexChunking result:[/bold yellow]")
|
|
||||||
print_result(result)
|
|
||||||
|
|
||||||
# Adding another chunking strategy: NlpSentenceChunking
|
|
||||||
cprint(
|
|
||||||
"\n🔍 [bold cyan]Time to explore another chunking strategy: NlpSentenceChunking![/bold cyan]",
|
|
||||||
True,
|
|
||||||
)
|
|
||||||
cprint(
|
|
||||||
"NlpSentenceChunking uses NLP techniques to split the text into sentences. Let's see how it performs!"
|
|
||||||
)
|
|
||||||
result = crawler.run(
|
|
||||||
url="https://www.nbcnews.com/business", chunking_strategy=NlpSentenceChunking()
|
|
||||||
)
|
|
||||||
cprint("[LOG] 📦 [bold yellow]NlpSentenceChunking result:[/bold yellow]")
|
|
||||||
print_result(result)
|
|
||||||
|
|
||||||
|
|
||||||
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!"
|
|
||||||
)
|
|
||||||
result = crawler.run(
|
|
||||||
url="https://www.nbcnews.com/business",
|
|
||||||
extraction_strategy=CosineStrategy(
|
|
||||||
word_count_threshold=10,
|
|
||||||
max_dist=0.2,
|
|
||||||
linkage_method="ward",
|
|
||||||
top_k=3,
|
|
||||||
sim_threshold=0.3,
|
|
||||||
verbose=True,
|
|
||||||
),
|
|
||||||
)
|
|
||||||
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",
|
|
||||||
extraction_strategy=CosineStrategy(
|
|
||||||
semantic_filter="inflation rent prices",
|
|
||||||
),
|
|
||||||
)
|
|
||||||
cprint(
|
|
||||||
"[LOG] 📦 [bold yellow]CosineStrategy result with semantic filter:[/bold yellow]"
|
|
||||||
)
|
|
||||||
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!"
|
|
||||||
)
|
|
||||||
result = crawler.run(
|
|
||||||
url="https://www.nbcnews.com/business",
|
|
||||||
extraction_strategy=LLMExtractionStrategy(
|
|
||||||
llm_config = LLMConfig(provider="openai/gpt-4o", api_token=os.getenv("OPENAI_API_KEY"))
|
|
||||||
),
|
|
||||||
)
|
|
||||||
cprint(
|
|
||||||
"[LOG] 📦 [bold yellow]LLMExtractionStrategy (no instructions) result:[/bold yellow]"
|
|
||||||
)
|
|
||||||
print_result(result)
|
|
||||||
|
|
||||||
# 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!"
|
|
||||||
)
|
|
||||||
result = crawler.run(
|
|
||||||
url="https://www.nbcnews.com/business",
|
|
||||||
extraction_strategy=LLMExtractionStrategy(
|
|
||||||
llm_config=LLMConfig(provider="openai/gpt-4o",api_token=os.getenv("OPENAI_API_KEY")),
|
|
||||||
instruction="I am interested in only financial news",
|
|
||||||
),
|
|
||||||
)
|
|
||||||
cprint(
|
|
||||||
"[LOG] 📦 [bold yellow]LLMExtractionStrategy (with instructions) result:[/bold yellow]"
|
|
||||||
)
|
|
||||||
print_result(result)
|
|
||||||
|
|
||||||
result = crawler.run(
|
|
||||||
url="https://www.nbcnews.com/business",
|
|
||||||
extraction_strategy=LLMExtractionStrategy(
|
|
||||||
llm_config=LLMConfig(provider="openai/gpt-4o",api_token=os.getenv("OPENAI_API_KEY")),
|
|
||||||
instruction="Extract only content related to technology",
|
|
||||||
),
|
|
||||||
)
|
|
||||||
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(url="https://www.nbcnews.com/business", css_selector="h2")
|
|
||||||
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."
|
|
||||||
)
|
|
||||||
js_code = """
|
|
||||||
const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More'));
|
|
||||||
loadMoreButton && loadMoreButton.click();
|
|
||||||
"""
|
|
||||||
# crawler_strategy = LocalSeleniumCrawlerStrategy(js_code=js_code)
|
|
||||||
# crawler = WebCrawler(crawler_strategy=crawler_strategy, always_by_pass_cache=True)
|
|
||||||
result = crawler.run(url="https://www.nbcnews.com/business", js=js_code)
|
|
||||||
cprint(
|
|
||||||
"[LOG] 📦 [bold yellow]JavaScript Code (Load More button) result:[/bold yellow]"
|
|
||||||
)
|
|
||||||
print_result(result)
|
|
||||||
|
|
||||||
|
|
||||||
def multiple_scrip(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."
|
|
||||||
)
|
|
||||||
js_code = [
|
|
||||||
"""
|
|
||||||
const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More'));
|
|
||||||
loadMoreButton && loadMoreButton.click();
|
|
||||||
"""
|
|
||||||
] * 2
|
|
||||||
# crawler_strategy = LocalSeleniumCrawlerStrategy(js_code=js_code)
|
|
||||||
# crawler = WebCrawler(crawler_strategy=crawler_strategy, always_by_pass_cache=True)
|
|
||||||
result = crawler.run(url="https://www.nbcnews.com/business", js=js_code)
|
|
||||||
cprint(
|
|
||||||
"[LOG] 📦 [bold yellow]JavaScript Code (Load More button) result:[/bold yellow]"
|
|
||||||
)
|
|
||||||
print_result(result)
|
|
||||||
|
|
||||||
|
|
||||||
def using_crawler_hooks(crawler):
|
|
||||||
# Example usage of the hooks for authentication and setting a cookie
|
|
||||||
def on_driver_created(driver):
|
|
||||||
print("[HOOK] on_driver_created")
|
|
||||||
# Example customization: maximize the window
|
|
||||||
driver.maximize_window()
|
|
||||||
|
|
||||||
# Example customization: logging in to a hypothetical website
|
|
||||||
driver.get("https://example.com/login")
|
|
||||||
|
|
||||||
from selenium.webdriver.support.ui import WebDriverWait
|
|
||||||
from selenium.webdriver.common.by import By
|
|
||||||
from selenium.webdriver.support import expected_conditions as EC
|
|
||||||
|
|
||||||
WebDriverWait(driver, 10).until(
|
|
||||||
EC.presence_of_element_located((By.NAME, "username"))
|
|
||||||
)
|
|
||||||
driver.find_element(By.NAME, "username").send_keys("testuser")
|
|
||||||
driver.find_element(By.NAME, "password").send_keys("password123")
|
|
||||||
driver.find_element(By.NAME, "login").click()
|
|
||||||
WebDriverWait(driver, 10).until(
|
|
||||||
EC.presence_of_element_located((By.ID, "welcome"))
|
|
||||||
)
|
|
||||||
# Add a custom cookie
|
|
||||||
driver.add_cookie({"name": "test_cookie", "value": "cookie_value"})
|
|
||||||
return driver
|
|
||||||
|
|
||||||
def before_get_url(driver):
|
|
||||||
print("[HOOK] before_get_url")
|
|
||||||
# Example customization: add a custom header
|
|
||||||
# Enable Network domain for sending headers
|
|
||||||
driver.execute_cdp_cmd("Network.enable", {})
|
|
||||||
# Add a custom header
|
|
||||||
driver.execute_cdp_cmd(
|
|
||||||
"Network.setExtraHTTPHeaders", {"headers": {"X-Test-Header": "test"}}
|
|
||||||
)
|
|
||||||
return driver
|
|
||||||
|
|
||||||
def after_get_url(driver):
|
|
||||||
print("[HOOK] after_get_url")
|
|
||||||
# Example customization: log the URL
|
|
||||||
print(driver.current_url)
|
|
||||||
return driver
|
|
||||||
|
|
||||||
def before_return_html(driver, html):
|
|
||||||
print("[HOOK] before_return_html")
|
|
||||||
# Example customization: log the HTML
|
|
||||||
print(len(html))
|
|
||||||
return driver
|
|
||||||
|
|
||||||
cprint(
|
|
||||||
"\n🔗 [bold cyan]Using Crawler Hooks: Let's see how we can customize the crawler using hooks![/bold cyan]",
|
|
||||||
True,
|
|
||||||
)
|
|
||||||
|
|
||||||
crawler_strategy = LocalSeleniumCrawlerStrategy(verbose=True)
|
|
||||||
crawler_strategy.set_hook("on_driver_created", on_driver_created)
|
|
||||||
crawler_strategy.set_hook("before_get_url", before_get_url)
|
|
||||||
crawler_strategy.set_hook("after_get_url", after_get_url)
|
|
||||||
crawler_strategy.set_hook("before_return_html", before_return_html)
|
|
||||||
|
|
||||||
crawler = WebCrawler(verbose=True, crawler_strategy=crawler_strategy)
|
|
||||||
crawler.warmup()
|
|
||||||
result = crawler.run(url="https://example.com")
|
|
||||||
|
|
||||||
cprint("[LOG] 📦 [bold yellow]Crawler Hooks result:[/bold yellow]")
|
|
||||||
print_result(result=result)
|
|
||||||
|
|
||||||
|
|
||||||
def using_crawler_hooks_dleay_example(crawler):
|
|
||||||
def delay(driver):
|
|
||||||
print("Delaying for 5 seconds...")
|
|
||||||
time.sleep(5)
|
|
||||||
print("Resuming...")
|
|
||||||
|
|
||||||
def create_crawler():
|
|
||||||
crawler_strategy = LocalSeleniumCrawlerStrategy(verbose=True)
|
|
||||||
crawler_strategy.set_hook("after_get_url", delay)
|
|
||||||
crawler = WebCrawler(verbose=True, crawler_strategy=crawler_strategy)
|
|
||||||
crawler.warmup()
|
|
||||||
return crawler
|
|
||||||
|
|
||||||
cprint(
|
|
||||||
"\n🔗 [bold cyan]Using Crawler Hooks: Let's add a delay after fetching the url to make sure entire page is fetched.[/bold cyan]"
|
|
||||||
)
|
|
||||||
crawler = create_crawler()
|
|
||||||
result = crawler.run(url="https://google.com", bypass_cache=True)
|
|
||||||
|
|
||||||
cprint("[LOG] 📦 [bold yellow]Crawler Hooks 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()
|
|
||||||
|
|
||||||
crawler.always_by_pass_cache = True
|
|
||||||
basic_usage(crawler)
|
|
||||||
# basic_usage_some_params(crawler)
|
|
||||||
understanding_parameters(crawler)
|
|
||||||
|
|
||||||
crawler.always_by_pass_cache = True
|
|
||||||
screenshot_usage(crawler)
|
|
||||||
add_chunking_strategy(crawler)
|
|
||||||
add_extraction_strategy(crawler)
|
|
||||||
add_llm_extraction_strategy(crawler)
|
|
||||||
targeted_extraction(crawler)
|
|
||||||
interactive_extraction(crawler)
|
|
||||||
multiple_scrip(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()
|
|
||||||
@@ -1,735 +0,0 @@
|
|||||||
{
|
|
||||||
"cells": [
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {
|
|
||||||
"id": "6yLvrXn7yZQI"
|
|
||||||
},
|
|
||||||
"source": [
|
|
||||||
"# Crawl4AI: Advanced Web Crawling and Data Extraction\n",
|
|
||||||
"\n",
|
|
||||||
"Welcome to this interactive notebook showcasing Crawl4AI, an advanced asynchronous web crawling and data extraction library.\n",
|
|
||||||
"\n",
|
|
||||||
"- GitHub Repository: [https://github.com/unclecode/crawl4ai](https://github.com/unclecode/crawl4ai)\n",
|
|
||||||
"- Twitter: [@unclecode](https://twitter.com/unclecode)\n",
|
|
||||||
"- Website: [https://crawl4ai.com](https://crawl4ai.com)\n",
|
|
||||||
"\n",
|
|
||||||
"Let's explore the powerful features of Crawl4AI!"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {
|
|
||||||
"id": "KIn_9nxFyZQK"
|
|
||||||
},
|
|
||||||
"source": [
|
|
||||||
"## Installation\n",
|
|
||||||
"\n",
|
|
||||||
"First, let's install Crawl4AI from GitHub:"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": null,
|
|
||||||
"metadata": {
|
|
||||||
"id": "mSnaxLf3zMog"
|
|
||||||
},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"!sudo apt-get update && sudo apt-get install -y libwoff1 libopus0 libwebp6 libwebpdemux2 libenchant1c2a libgudev-1.0-0 libsecret-1-0 libhyphen0 libgdk-pixbuf2.0-0 libegl1 libnotify4 libxslt1.1 libevent-2.1-7 libgles2 libvpx6 libxcomposite1 libatk1.0-0 libatk-bridge2.0-0 libepoxy0 libgtk-3-0 libharfbuzz-icu0"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": null,
|
|
||||||
"metadata": {
|
|
||||||
"id": "xlXqaRtayZQK"
|
|
||||||
},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"!pip install crawl4ai\n",
|
|
||||||
"!pip install nest-asyncio\n",
|
|
||||||
"!playwright install"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {
|
|
||||||
"id": "qKCE7TI7yZQL"
|
|
||||||
},
|
|
||||||
"source": [
|
|
||||||
"Now, let's import the necessary libraries:"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 1,
|
|
||||||
"metadata": {
|
|
||||||
"id": "I67tr7aAyZQL"
|
|
||||||
},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"import asyncio\n",
|
|
||||||
"import nest_asyncio\n",
|
|
||||||
"from crawl4ai import AsyncWebCrawler\n",
|
|
||||||
"from crawl4ai.extraction_strategy import JsonCssExtractionStrategy, LLMExtractionStrategy\n",
|
|
||||||
"import json\n",
|
|
||||||
"import time\n",
|
|
||||||
"from pydantic import BaseModel, Field\n",
|
|
||||||
"\n",
|
|
||||||
"nest_asyncio.apply()"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {
|
|
||||||
"id": "h7yR_Rt_yZQM"
|
|
||||||
},
|
|
||||||
"source": [
|
|
||||||
"## Basic Usage\n",
|
|
||||||
"\n",
|
|
||||||
"Let's start with a simple crawl example:"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 2,
|
|
||||||
"metadata": {
|
|
||||||
"colab": {
|
|
||||||
"base_uri": "https://localhost:8080/"
|
|
||||||
},
|
|
||||||
"id": "yBh6hf4WyZQM",
|
|
||||||
"outputId": "0f83af5c-abba-4175-ed95-70b7512e6bcc"
|
|
||||||
},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"name": "stdout",
|
|
||||||
"output_type": "stream",
|
|
||||||
"text": [
|
|
||||||
"[LOG] 🌤️ Warming up the AsyncWebCrawler\n",
|
|
||||||
"[LOG] 🌞 AsyncWebCrawler is ready to crawl\n",
|
|
||||||
"[LOG] 🚀 Content extracted for https://www.nbcnews.com/business, success: True, time taken: 0.05 seconds\n",
|
|
||||||
"[LOG] 🚀 Extraction done for https://www.nbcnews.com/business, time taken: 0.05 seconds.\n",
|
|
||||||
"18102\n"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"async def simple_crawl():\n",
|
|
||||||
" async with AsyncWebCrawler(verbose=True) as crawler:\n",
|
|
||||||
" result = await crawler.arun(url=\"https://www.nbcnews.com/business\")\n",
|
|
||||||
" print(len(result.markdown))\n",
|
|
||||||
"await simple_crawl()"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {
|
|
||||||
"id": "9rtkgHI28uI4"
|
|
||||||
},
|
|
||||||
"source": [
|
|
||||||
"💡 By default, **Crawl4AI** caches the result of every URL, so the next time you call it, you’ll get an instant result. But if you want to bypass the cache, just set `bypass_cache=True`."
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {
|
|
||||||
"id": "MzZ0zlJ9yZQM"
|
|
||||||
},
|
|
||||||
"source": [
|
|
||||||
"## Advanced Features\n",
|
|
||||||
"\n",
|
|
||||||
"### Executing JavaScript and Using CSS Selectors"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 3,
|
|
||||||
"metadata": {
|
|
||||||
"colab": {
|
|
||||||
"base_uri": "https://localhost:8080/"
|
|
||||||
},
|
|
||||||
"id": "gHStF86xyZQM",
|
|
||||||
"outputId": "34d0fb6d-4dec-4677-f76e-85a1f082829b"
|
|
||||||
},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"name": "stdout",
|
|
||||||
"output_type": "stream",
|
|
||||||
"text": [
|
|
||||||
"[LOG] 🌤️ Warming up the AsyncWebCrawler\n",
|
|
||||||
"[LOG] 🌞 AsyncWebCrawler is ready to crawl\n",
|
|
||||||
"[LOG] 🕸️ Crawling https://www.nbcnews.com/business using AsyncPlaywrightCrawlerStrategy...\n",
|
|
||||||
"[LOG] ✅ Crawled https://www.nbcnews.com/business successfully!\n",
|
|
||||||
"[LOG] 🚀 Crawling done for https://www.nbcnews.com/business, success: True, time taken: 6.06 seconds\n",
|
|
||||||
"[LOG] 🚀 Content extracted for https://www.nbcnews.com/business, success: True, time taken: 0.10 seconds\n",
|
|
||||||
"[LOG] 🔥 Extracting semantic blocks for https://www.nbcnews.com/business, Strategy: AsyncWebCrawler\n",
|
|
||||||
"[LOG] 🚀 Extraction done for https://www.nbcnews.com/business, time taken: 0.11 seconds.\n",
|
|
||||||
"41135\n"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"async def js_and_css():\n",
|
|
||||||
" async with AsyncWebCrawler(verbose=True) as crawler:\n",
|
|
||||||
" js_code = [\"const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();\"]\n",
|
|
||||||
" result = await crawler.arun(\n",
|
|
||||||
" url=\"https://www.nbcnews.com/business\",\n",
|
|
||||||
" js_code=js_code,\n",
|
|
||||||
" # css_selector=\"YOUR_CSS_SELECTOR_HERE\",\n",
|
|
||||||
" bypass_cache=True\n",
|
|
||||||
" )\n",
|
|
||||||
" print(len(result.markdown))\n",
|
|
||||||
"\n",
|
|
||||||
"await js_and_css()"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {
|
|
||||||
"id": "cqE_W4coyZQM"
|
|
||||||
},
|
|
||||||
"source": [
|
|
||||||
"### Using a Proxy\n",
|
|
||||||
"\n",
|
|
||||||
"Note: You'll need to replace the proxy URL with a working proxy for this example to run successfully."
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": null,
|
|
||||||
"metadata": {
|
|
||||||
"id": "QjAyiAGqyZQM"
|
|
||||||
},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"async def use_proxy():\n",
|
|
||||||
" async with AsyncWebCrawler(verbose=True, proxy=\"http://your-proxy-url:port\") as crawler:\n",
|
|
||||||
" result = await crawler.arun(\n",
|
|
||||||
" url=\"https://www.nbcnews.com/business\",\n",
|
|
||||||
" bypass_cache=True\n",
|
|
||||||
" )\n",
|
|
||||||
" print(result.markdown[:500]) # Print first 500 characters\n",
|
|
||||||
"\n",
|
|
||||||
"# Uncomment the following line to run the proxy example\n",
|
|
||||||
"# await use_proxy()"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {
|
|
||||||
"id": "XTZ88lbayZQN"
|
|
||||||
},
|
|
||||||
"source": [
|
|
||||||
"### Extracting Structured Data with OpenAI\n",
|
|
||||||
"\n",
|
|
||||||
"Note: You'll need to set your OpenAI API key as an environment variable for this example to work."
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 14,
|
|
||||||
"metadata": {
|
|
||||||
"colab": {
|
|
||||||
"base_uri": "https://localhost:8080/"
|
|
||||||
},
|
|
||||||
"id": "fIOlDayYyZQN",
|
|
||||||
"outputId": "cb8359cc-dee0-4762-9698-5dfdcee055b8"
|
|
||||||
},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"name": "stdout",
|
|
||||||
"output_type": "stream",
|
|
||||||
"text": [
|
|
||||||
"[LOG] 🌤️ Warming up the AsyncWebCrawler\n",
|
|
||||||
"[LOG] 🌞 AsyncWebCrawler is ready to crawl\n",
|
|
||||||
"[LOG] 🕸️ Crawling https://openai.com/api/pricing/ using AsyncPlaywrightCrawlerStrategy...\n",
|
|
||||||
"[LOG] ✅ Crawled https://openai.com/api/pricing/ successfully!\n",
|
|
||||||
"[LOG] 🚀 Crawling done for https://openai.com/api/pricing/, success: True, time taken: 3.77 seconds\n",
|
|
||||||
"[LOG] 🚀 Content extracted for https://openai.com/api/pricing/, success: True, time taken: 0.21 seconds\n",
|
|
||||||
"[LOG] 🔥 Extracting semantic blocks for https://openai.com/api/pricing/, Strategy: AsyncWebCrawler\n",
|
|
||||||
"[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 0\n",
|
|
||||||
"[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 1\n",
|
|
||||||
"[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 2\n",
|
|
||||||
"[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 3\n",
|
|
||||||
"[LOG] Extracted 4 blocks from URL: https://openai.com/api/pricing/ block index: 3\n",
|
|
||||||
"[LOG] Call LLM for https://openai.com/api/pricing/ - block index: 4\n",
|
|
||||||
"[LOG] Extracted 5 blocks from URL: https://openai.com/api/pricing/ block index: 0\n",
|
|
||||||
"[LOG] Extracted 1 blocks from URL: https://openai.com/api/pricing/ block index: 4\n",
|
|
||||||
"[LOG] Extracted 8 blocks from URL: https://openai.com/api/pricing/ block index: 1\n",
|
|
||||||
"[LOG] Extracted 12 blocks from URL: https://openai.com/api/pricing/ block index: 2\n",
|
|
||||||
"[LOG] 🚀 Extraction done for https://openai.com/api/pricing/, time taken: 8.55 seconds.\n",
|
|
||||||
"5029\n"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"import os\n",
|
|
||||||
"from google.colab import userdata\n",
|
|
||||||
"os.environ['OPENAI_API_KEY'] = userdata.get('OPENAI_API_KEY')\n",
|
|
||||||
"\n",
|
|
||||||
"class OpenAIModelFee(BaseModel):\n",
|
|
||||||
" model_name: str = Field(..., description=\"Name of the OpenAI model.\")\n",
|
|
||||||
" input_fee: str = Field(..., description=\"Fee for input token for the OpenAI model.\")\n",
|
|
||||||
" output_fee: str = Field(..., description=\"Fee for output token for the OpenAI model.\")\n",
|
|
||||||
"\n",
|
|
||||||
"async def extract_openai_fees():\n",
|
|
||||||
" async with AsyncWebCrawler(verbose=True) as crawler:\n",
|
|
||||||
" result = await crawler.arun(\n",
|
|
||||||
" url='https://openai.com/api/pricing/',\n",
|
|
||||||
" word_count_threshold=1,\n",
|
|
||||||
" extraction_strategy=LLMExtractionStrategy(\n",
|
|
||||||
" provider=\"openai/gpt-4o\", api_token=os.getenv('OPENAI_API_KEY'),\n",
|
|
||||||
" schema=OpenAIModelFee.schema(),\n",
|
|
||||||
" extraction_type=\"schema\",\n",
|
|
||||||
" instruction=\"\"\"From the crawled content, extract all mentioned model names along with their fees for input and output tokens.\n",
|
|
||||||
" Do not miss any models in the entire content. One extracted model JSON format should look like this:\n",
|
|
||||||
" {\"model_name\": \"GPT-4\", \"input_fee\": \"US$10.00 / 1M tokens\", \"output_fee\": \"US$30.00 / 1M tokens\"}.\"\"\"\n",
|
|
||||||
" ),\n",
|
|
||||||
" bypass_cache=True,\n",
|
|
||||||
" )\n",
|
|
||||||
" print(len(result.extracted_content))\n",
|
|
||||||
"\n",
|
|
||||||
"# Uncomment the following line to run the OpenAI extraction example\n",
|
|
||||||
"await extract_openai_fees()"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {
|
|
||||||
"id": "BypA5YxEyZQN"
|
|
||||||
},
|
|
||||||
"source": [
|
|
||||||
"### Advanced Multi-Page Crawling with JavaScript Execution"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {
|
|
||||||
"id": "tfkcVQ0b7mw-"
|
|
||||||
},
|
|
||||||
"source": [
|
|
||||||
"## Advanced Multi-Page Crawling with JavaScript Execution\n",
|
|
||||||
"\n",
|
|
||||||
"This example demonstrates Crawl4AI's ability to handle complex crawling scenarios, specifically extracting commits from multiple pages of a GitHub repository. The challenge here is that clicking the \"Next\" button doesn't load a new page, but instead uses asynchronous JavaScript to update the content. This is a common hurdle in modern web crawling.\n",
|
|
||||||
"\n",
|
|
||||||
"To overcome this, we use Crawl4AI's custom JavaScript execution to simulate clicking the \"Next\" button, and implement a custom hook to detect when new data has loaded. Our strategy involves comparing the first commit's text before and after \"clicking\" Next, waiting until it changes to confirm new data has rendered. This showcases Crawl4AI's flexibility in handling dynamic content and its ability to implement custom logic for even the most challenging crawling tasks."
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 11,
|
|
||||||
"metadata": {
|
|
||||||
"colab": {
|
|
||||||
"base_uri": "https://localhost:8080/"
|
|
||||||
},
|
|
||||||
"id": "qUBKGpn3yZQN",
|
|
||||||
"outputId": "3e555b6a-ed33-42f4-cce9-499a923fbe17"
|
|
||||||
},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"name": "stdout",
|
|
||||||
"output_type": "stream",
|
|
||||||
"text": [
|
|
||||||
"[LOG] 🌤️ Warming up the AsyncWebCrawler\n",
|
|
||||||
"[LOG] 🌞 AsyncWebCrawler is ready to crawl\n",
|
|
||||||
"[LOG] 🕸️ Crawling https://github.com/microsoft/TypeScript/commits/main using AsyncPlaywrightCrawlerStrategy...\n",
|
|
||||||
"[LOG] ✅ Crawled https://github.com/microsoft/TypeScript/commits/main successfully!\n",
|
|
||||||
"[LOG] 🚀 Crawling done for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 5.16 seconds\n",
|
|
||||||
"[LOG] 🚀 Content extracted for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 0.28 seconds\n",
|
|
||||||
"[LOG] 🔥 Extracting semantic blocks for https://github.com/microsoft/TypeScript/commits/main, Strategy: AsyncWebCrawler\n",
|
|
||||||
"[LOG] 🚀 Extraction done for https://github.com/microsoft/TypeScript/commits/main, time taken: 0.28 seconds.\n",
|
|
||||||
"Page 1: Found 35 commits\n",
|
|
||||||
"[LOG] 🕸️ Crawling https://github.com/microsoft/TypeScript/commits/main using AsyncPlaywrightCrawlerStrategy...\n",
|
|
||||||
"[LOG] ✅ Crawled https://github.com/microsoft/TypeScript/commits/main successfully!\n",
|
|
||||||
"[LOG] 🚀 Crawling done for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 0.78 seconds\n",
|
|
||||||
"[LOG] 🚀 Content extracted for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 0.90 seconds\n",
|
|
||||||
"[LOG] 🔥 Extracting semantic blocks for https://github.com/microsoft/TypeScript/commits/main, Strategy: AsyncWebCrawler\n",
|
|
||||||
"[LOG] 🚀 Extraction done for https://github.com/microsoft/TypeScript/commits/main, time taken: 0.90 seconds.\n",
|
|
||||||
"Page 2: Found 35 commits\n",
|
|
||||||
"[LOG] 🕸️ Crawling https://github.com/microsoft/TypeScript/commits/main using AsyncPlaywrightCrawlerStrategy...\n",
|
|
||||||
"[LOG] ✅ Crawled https://github.com/microsoft/TypeScript/commits/main successfully!\n",
|
|
||||||
"[LOG] 🚀 Crawling done for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 2.00 seconds\n",
|
|
||||||
"[LOG] 🚀 Content extracted for https://github.com/microsoft/TypeScript/commits/main, success: True, time taken: 0.74 seconds\n",
|
|
||||||
"[LOG] 🔥 Extracting semantic blocks for https://github.com/microsoft/TypeScript/commits/main, Strategy: AsyncWebCrawler\n",
|
|
||||||
"[LOG] 🚀 Extraction done for https://github.com/microsoft/TypeScript/commits/main, time taken: 0.75 seconds.\n",
|
|
||||||
"Page 3: Found 35 commits\n",
|
|
||||||
"Successfully crawled 105 commits across 3 pages\n"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"import re\n",
|
|
||||||
"from bs4 import BeautifulSoup\n",
|
|
||||||
"\n",
|
|
||||||
"async def crawl_typescript_commits():\n",
|
|
||||||
" first_commit = \"\"\n",
|
|
||||||
" async def on_execution_started(page):\n",
|
|
||||||
" nonlocal first_commit\n",
|
|
||||||
" try:\n",
|
|
||||||
" while True:\n",
|
|
||||||
" await page.wait_for_selector('li.Box-sc-g0xbh4-0 h4')\n",
|
|
||||||
" commit = await page.query_selector('li.Box-sc-g0xbh4-0 h4')\n",
|
|
||||||
" commit = await commit.evaluate('(element) => element.textContent')\n",
|
|
||||||
" commit = re.sub(r'\\s+', '', commit)\n",
|
|
||||||
" if commit and commit != first_commit:\n",
|
|
||||||
" first_commit = commit\n",
|
|
||||||
" break\n",
|
|
||||||
" await asyncio.sleep(0.5)\n",
|
|
||||||
" except Exception as e:\n",
|
|
||||||
" print(f\"Warning: New content didn't appear after JavaScript execution: {e}\")\n",
|
|
||||||
"\n",
|
|
||||||
" async with AsyncWebCrawler(verbose=True) as crawler:\n",
|
|
||||||
" crawler.crawler_strategy.set_hook('on_execution_started', on_execution_started)\n",
|
|
||||||
"\n",
|
|
||||||
" url = \"https://github.com/microsoft/TypeScript/commits/main\"\n",
|
|
||||||
" session_id = \"typescript_commits_session\"\n",
|
|
||||||
" all_commits = []\n",
|
|
||||||
"\n",
|
|
||||||
" js_next_page = \"\"\"\n",
|
|
||||||
" const button = document.querySelector('a[data-testid=\"pagination-next-button\"]');\n",
|
|
||||||
" if (button) button.click();\n",
|
|
||||||
" \"\"\"\n",
|
|
||||||
"\n",
|
|
||||||
" for page in range(3): # Crawl 3 pages\n",
|
|
||||||
" result = await crawler.arun(\n",
|
|
||||||
" url=url,\n",
|
|
||||||
" session_id=session_id,\n",
|
|
||||||
" css_selector=\"li.Box-sc-g0xbh4-0\",\n",
|
|
||||||
" js=js_next_page if page > 0 else None,\n",
|
|
||||||
" bypass_cache=True,\n",
|
|
||||||
" js_only=page > 0\n",
|
|
||||||
" )\n",
|
|
||||||
"\n",
|
|
||||||
" assert result.success, f\"Failed to crawl page {page + 1}\"\n",
|
|
||||||
"\n",
|
|
||||||
" soup = BeautifulSoup(result.cleaned_html, 'html.parser')\n",
|
|
||||||
" commits = soup.select(\"li\")\n",
|
|
||||||
" all_commits.extend(commits)\n",
|
|
||||||
"\n",
|
|
||||||
" print(f\"Page {page + 1}: Found {len(commits)} commits\")\n",
|
|
||||||
"\n",
|
|
||||||
" await crawler.crawler_strategy.kill_session(session_id)\n",
|
|
||||||
" print(f\"Successfully crawled {len(all_commits)} commits across 3 pages\")\n",
|
|
||||||
"\n",
|
|
||||||
"await crawl_typescript_commits()"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {
|
|
||||||
"id": "EJRnYsp6yZQN"
|
|
||||||
},
|
|
||||||
"source": [
|
|
||||||
"### Using JsonCssExtractionStrategy for Fast Structured Output"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {
|
|
||||||
"id": "1ZMqIzB_8SYp"
|
|
||||||
},
|
|
||||||
"source": [
|
|
||||||
"The JsonCssExtractionStrategy is a powerful feature of Crawl4AI that allows for precise, structured data extraction from web pages. Here's how it works:\n",
|
|
||||||
"\n",
|
|
||||||
"1. You define a schema that describes the pattern of data you're interested in extracting.\n",
|
|
||||||
"2. The schema includes a base selector that identifies repeating elements on the page.\n",
|
|
||||||
"3. Within the schema, you define fields, each with its own selector and type.\n",
|
|
||||||
"4. These field selectors are applied within the context of each base selector element.\n",
|
|
||||||
"5. The strategy supports nested structures, lists within lists, and various data types.\n",
|
|
||||||
"6. You can even include computed fields for more complex data manipulation.\n",
|
|
||||||
"\n",
|
|
||||||
"This approach allows for highly flexible and precise data extraction, transforming semi-structured web content into clean, structured JSON data. It's particularly useful for extracting consistent data patterns from pages like product listings, news articles, or search results.\n",
|
|
||||||
"\n",
|
|
||||||
"For more details and advanced usage, check out the full documentation on the Crawl4AI website."
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 12,
|
|
||||||
"metadata": {
|
|
||||||
"colab": {
|
|
||||||
"base_uri": "https://localhost:8080/"
|
|
||||||
},
|
|
||||||
"id": "trCMR2T9yZQN",
|
|
||||||
"outputId": "718d36f4-cccf-40f4-8d8c-c3ba73524d16"
|
|
||||||
},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"name": "stdout",
|
|
||||||
"output_type": "stream",
|
|
||||||
"text": [
|
|
||||||
"[LOG] 🌤️ Warming up the AsyncWebCrawler\n",
|
|
||||||
"[LOG] 🌞 AsyncWebCrawler is ready to crawl\n",
|
|
||||||
"[LOG] 🕸️ Crawling https://www.nbcnews.com/business using AsyncPlaywrightCrawlerStrategy...\n",
|
|
||||||
"[LOG] ✅ Crawled https://www.nbcnews.com/business successfully!\n",
|
|
||||||
"[LOG] 🚀 Crawling done for https://www.nbcnews.com/business, success: True, time taken: 7.00 seconds\n",
|
|
||||||
"[LOG] 🚀 Content extracted for https://www.nbcnews.com/business, success: True, time taken: 0.32 seconds\n",
|
|
||||||
"[LOG] 🔥 Extracting semantic blocks for https://www.nbcnews.com/business, Strategy: AsyncWebCrawler\n",
|
|
||||||
"[LOG] 🚀 Extraction done for https://www.nbcnews.com/business, time taken: 0.48 seconds.\n",
|
|
||||||
"Successfully extracted 11 news teasers\n",
|
|
||||||
"{\n",
|
|
||||||
" \"category\": \"Business News\",\n",
|
|
||||||
" \"headline\": \"NBC ripped up its Olympics playbook for 2024 \\u2014 so far, the new strategy paid off\",\n",
|
|
||||||
" \"summary\": \"The Olympics have long been key to NBCUniversal. Paris marked the 18th Olympic Games broadcast by NBC in the U.S.\",\n",
|
|
||||||
" \"time\": \"13h ago\",\n",
|
|
||||||
" \"image\": {\n",
|
|
||||||
" \"src\": \"https://media-cldnry.s-nbcnews.com/image/upload/t_focal-200x100,f_auto,q_auto:best/rockcms/2024-09/240903-nbc-olympics-ch-1344-c7a486.jpg\",\n",
|
|
||||||
" \"alt\": \"Mike Tirico.\"\n",
|
|
||||||
" },\n",
|
|
||||||
" \"link\": \"https://www.nbcnews.com/business\"\n",
|
|
||||||
"}\n"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"async def extract_news_teasers():\n",
|
|
||||||
" schema = {\n",
|
|
||||||
" \"name\": \"News Teaser Extractor\",\n",
|
|
||||||
" \"baseSelector\": \".wide-tease-item__wrapper\",\n",
|
|
||||||
" \"fields\": [\n",
|
|
||||||
" {\n",
|
|
||||||
" \"name\": \"category\",\n",
|
|
||||||
" \"selector\": \".unibrow span[data-testid='unibrow-text']\",\n",
|
|
||||||
" \"type\": \"text\",\n",
|
|
||||||
" },\n",
|
|
||||||
" {\n",
|
|
||||||
" \"name\": \"headline\",\n",
|
|
||||||
" \"selector\": \".wide-tease-item__headline\",\n",
|
|
||||||
" \"type\": \"text\",\n",
|
|
||||||
" },\n",
|
|
||||||
" {\n",
|
|
||||||
" \"name\": \"summary\",\n",
|
|
||||||
" \"selector\": \".wide-tease-item__description\",\n",
|
|
||||||
" \"type\": \"text\",\n",
|
|
||||||
" },\n",
|
|
||||||
" {\n",
|
|
||||||
" \"name\": \"time\",\n",
|
|
||||||
" \"selector\": \"[data-testid='wide-tease-date']\",\n",
|
|
||||||
" \"type\": \"text\",\n",
|
|
||||||
" },\n",
|
|
||||||
" {\n",
|
|
||||||
" \"name\": \"image\",\n",
|
|
||||||
" \"type\": \"nested\",\n",
|
|
||||||
" \"selector\": \"picture.teasePicture img\",\n",
|
|
||||||
" \"fields\": [\n",
|
|
||||||
" {\"name\": \"src\", \"type\": \"attribute\", \"attribute\": \"src\"},\n",
|
|
||||||
" {\"name\": \"alt\", \"type\": \"attribute\", \"attribute\": \"alt\"},\n",
|
|
||||||
" ],\n",
|
|
||||||
" },\n",
|
|
||||||
" {\n",
|
|
||||||
" \"name\": \"link\",\n",
|
|
||||||
" \"selector\": \"a[href]\",\n",
|
|
||||||
" \"type\": \"attribute\",\n",
|
|
||||||
" \"attribute\": \"href\",\n",
|
|
||||||
" },\n",
|
|
||||||
" ],\n",
|
|
||||||
" }\n",
|
|
||||||
"\n",
|
|
||||||
" extraction_strategy = JsonCssExtractionStrategy(schema, verbose=True)\n",
|
|
||||||
"\n",
|
|
||||||
" async with AsyncWebCrawler(verbose=True) as crawler:\n",
|
|
||||||
" result = await crawler.arun(\n",
|
|
||||||
" url=\"https://www.nbcnews.com/business\",\n",
|
|
||||||
" extraction_strategy=extraction_strategy,\n",
|
|
||||||
" bypass_cache=True,\n",
|
|
||||||
" )\n",
|
|
||||||
"\n",
|
|
||||||
" assert result.success, \"Failed to crawl the page\"\n",
|
|
||||||
"\n",
|
|
||||||
" news_teasers = json.loads(result.extracted_content)\n",
|
|
||||||
" print(f\"Successfully extracted {len(news_teasers)} news teasers\")\n",
|
|
||||||
" print(json.dumps(news_teasers[0], indent=2))\n",
|
|
||||||
"\n",
|
|
||||||
"await extract_news_teasers()"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {
|
|
||||||
"id": "FnyVhJaByZQN"
|
|
||||||
},
|
|
||||||
"source": [
|
|
||||||
"## Speed Comparison\n",
|
|
||||||
"\n",
|
|
||||||
"Let's compare the speed of Crawl4AI with Firecrawl, a paid service. Note that we can't run Firecrawl in this Colab environment, so we'll simulate its performance based on previously recorded data."
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {
|
|
||||||
"id": "agDD186f3wig"
|
|
||||||
},
|
|
||||||
"source": [
|
|
||||||
"💡 **Note on Speed Comparison:**\n",
|
|
||||||
"\n",
|
|
||||||
"The speed test conducted here is running on Google Colab, where the internet speed and performance can vary and may not reflect optimal conditions. When we call Firecrawl's API, we're seeing its best performance, while Crawl4AI's performance is limited by Colab's network speed.\n",
|
|
||||||
"\n",
|
|
||||||
"For a more accurate comparison, it's recommended to run these tests on your own servers or computers with a stable and fast internet connection. Despite these limitations, Crawl4AI still demonstrates faster performance in this environment.\n",
|
|
||||||
"\n",
|
|
||||||
"If you run these tests locally, you may observe an even more significant speed advantage for Crawl4AI compared to other services."
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": null,
|
|
||||||
"metadata": {
|
|
||||||
"id": "F7KwHv8G1LbY"
|
|
||||||
},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"!pip install firecrawl"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 4,
|
|
||||||
"metadata": {
|
|
||||||
"colab": {
|
|
||||||
"base_uri": "https://localhost:8080/"
|
|
||||||
},
|
|
||||||
"id": "91813zILyZQN",
|
|
||||||
"outputId": "663223db-ab89-4976-b233-05ceca62b19b"
|
|
||||||
},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"name": "stdout",
|
|
||||||
"output_type": "stream",
|
|
||||||
"text": [
|
|
||||||
"Firecrawl (simulated):\n",
|
|
||||||
"Time taken: 4.38 seconds\n",
|
|
||||||
"Content length: 41967 characters\n",
|
|
||||||
"Images found: 49\n",
|
|
||||||
"\n",
|
|
||||||
"Crawl4AI (simple crawl):\n",
|
|
||||||
"Time taken: 4.22 seconds\n",
|
|
||||||
"Content length: 18221 characters\n",
|
|
||||||
"Images found: 49\n",
|
|
||||||
"\n",
|
|
||||||
"Crawl4AI (with JavaScript execution):\n",
|
|
||||||
"Time taken: 9.13 seconds\n",
|
|
||||||
"Content length: 34243 characters\n",
|
|
||||||
"Images found: 89\n"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"import os\n",
|
|
||||||
"from google.colab import userdata\n",
|
|
||||||
"os.environ['FIRECRAWL_API_KEY'] = userdata.get('FIRECRAWL_API_KEY')\n",
|
|
||||||
"import time\n",
|
|
||||||
"from firecrawl import FirecrawlApp\n",
|
|
||||||
"\n",
|
|
||||||
"async def speed_comparison():\n",
|
|
||||||
" # Simulated Firecrawl performance\n",
|
|
||||||
" app = FirecrawlApp(api_key=os.environ['FIRECRAWL_API_KEY'])\n",
|
|
||||||
" start = time.time()\n",
|
|
||||||
" scrape_status = app.scrape_url(\n",
|
|
||||||
" 'https://www.nbcnews.com/business',\n",
|
|
||||||
" params={'formats': ['markdown', 'html']}\n",
|
|
||||||
" )\n",
|
|
||||||
" end = time.time()\n",
|
|
||||||
" print(\"Firecrawl (simulated):\")\n",
|
|
||||||
" print(f\"Time taken: {end - start:.2f} seconds\")\n",
|
|
||||||
" print(f\"Content length: {len(scrape_status['markdown'])} characters\")\n",
|
|
||||||
" print(f\"Images found: {scrape_status['markdown'].count('cldnry.s-nbcnews.com')}\")\n",
|
|
||||||
" print()\n",
|
|
||||||
"\n",
|
|
||||||
" async with AsyncWebCrawler() as crawler:\n",
|
|
||||||
" # Crawl4AI simple crawl\n",
|
|
||||||
" start = time.time()\n",
|
|
||||||
" result = await crawler.arun(\n",
|
|
||||||
" url=\"https://www.nbcnews.com/business\",\n",
|
|
||||||
" word_count_threshold=0,\n",
|
|
||||||
" bypass_cache=True,\n",
|
|
||||||
" verbose=False\n",
|
|
||||||
" )\n",
|
|
||||||
" end = time.time()\n",
|
|
||||||
" print(\"Crawl4AI (simple crawl):\")\n",
|
|
||||||
" print(f\"Time taken: {end - start:.2f} seconds\")\n",
|
|
||||||
" print(f\"Content length: {len(result.markdown)} characters\")\n",
|
|
||||||
" print(f\"Images found: {result.markdown.count('cldnry.s-nbcnews.com')}\")\n",
|
|
||||||
" print()\n",
|
|
||||||
"\n",
|
|
||||||
" # Crawl4AI with JavaScript execution\n",
|
|
||||||
" start = time.time()\n",
|
|
||||||
" result = await crawler.arun(\n",
|
|
||||||
" url=\"https://www.nbcnews.com/business\",\n",
|
|
||||||
" js_code=[\"const loadMoreButton = Array.from(document.querySelectorAll('button')).find(button => button.textContent.includes('Load More')); loadMoreButton && loadMoreButton.click();\"],\n",
|
|
||||||
" word_count_threshold=0,\n",
|
|
||||||
" bypass_cache=True,\n",
|
|
||||||
" verbose=False\n",
|
|
||||||
" )\n",
|
|
||||||
" end = time.time()\n",
|
|
||||||
" print(\"Crawl4AI (with JavaScript execution):\")\n",
|
|
||||||
" print(f\"Time taken: {end - start:.2f} seconds\")\n",
|
|
||||||
" print(f\"Content length: {len(result.markdown)} characters\")\n",
|
|
||||||
" print(f\"Images found: {result.markdown.count('cldnry.s-nbcnews.com')}\")\n",
|
|
||||||
"\n",
|
|
||||||
"await speed_comparison()"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {
|
|
||||||
"id": "OBFFYVJIyZQN"
|
|
||||||
},
|
|
||||||
"source": [
|
|
||||||
"If you run on a local machine with a proper internet speed:\n",
|
|
||||||
"- Simple crawl: Crawl4AI is typically over 3-4 times faster than Firecrawl.\n",
|
|
||||||
"- With JavaScript execution: Even when executing JavaScript to load more content (potentially doubling the number of images found), Crawl4AI is still faster than Firecrawl's simple crawl.\n",
|
|
||||||
"\n",
|
|
||||||
"Please note that actual performance may vary depending on network conditions and the specific content being crawled."
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "markdown",
|
|
||||||
"metadata": {
|
|
||||||
"id": "A6_1RK1_yZQO"
|
|
||||||
},
|
|
||||||
"source": [
|
|
||||||
"## Conclusion\n",
|
|
||||||
"\n",
|
|
||||||
"In this notebook, we've explored the powerful features of Crawl4AI, including:\n",
|
|
||||||
"\n",
|
|
||||||
"1. Basic crawling\n",
|
|
||||||
"2. JavaScript execution and CSS selector usage\n",
|
|
||||||
"3. Proxy support\n",
|
|
||||||
"4. Structured data extraction with OpenAI\n",
|
|
||||||
"5. Advanced multi-page crawling with JavaScript execution\n",
|
|
||||||
"6. Fast structured output using JsonCssExtractionStrategy\n",
|
|
||||||
"7. Speed comparison with other services\n",
|
|
||||||
"\n",
|
|
||||||
"Crawl4AI offers a fast, flexible, and powerful solution for web crawling and data extraction tasks. Its asynchronous architecture and advanced features make it suitable for a wide range of applications, from simple web scraping to complex, multi-page data extraction scenarios.\n",
|
|
||||||
"\n",
|
|
||||||
"For more information and advanced usage, please visit the [Crawl4AI documentation](https://docs.crawl4ai.com/).\n",
|
|
||||||
"\n",
|
|
||||||
"Happy crawling!"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"metadata": {
|
|
||||||
"colab": {
|
|
||||||
"provenance": []
|
|
||||||
},
|
|
||||||
"kernelspec": {
|
|
||||||
"display_name": "venv",
|
|
||||||
"language": "python",
|
|
||||||
"name": "python3"
|
|
||||||
},
|
|
||||||
"language_info": {
|
|
||||||
"codemirror_mode": {
|
|
||||||
"name": "ipython",
|
|
||||||
"version": 3
|
|
||||||
},
|
|
||||||
"file_extension": ".py",
|
|
||||||
"mimetype": "text/x-python",
|
|
||||||
"name": "python",
|
|
||||||
"nbconvert_exporter": "python",
|
|
||||||
"pygments_lexer": "ipython3",
|
|
||||||
"version": "3.10.13"
|
|
||||||
}
|
|
||||||
},
|
|
||||||
"nbformat": 4,
|
|
||||||
"nbformat_minor": 0
|
|
||||||
}
|
|
||||||
Reference in New Issue
Block a user