Crawl4AI

scrapeless_params = {
    "token": "get your token from https://www.scrapeless.com",
    "sessionName": "Scrapeless browser",
    "sessionTTL": 1000,
}
 
query_string = urlencode(scrapeless_params)
scrapeless_connection_url = f"wss://browser.scrapeless.com/api/v2/browser?{query_string}"
 
AsyncWebCrawler(
    config=BrowserConfig(
        headless=False,
        browser_mode="cdp",
        cdp_url=scrapeless_connection_url
    )
)
 

import asyncio
from urllib.parse import urlencode
from crawl4ai import CrawlerRunConfig, BrowserConfig, AsyncWebCrawler
 
async def main():
    scrapeless_params = {
        "token": "your token",
        "sessionTTL": 1000,
        "sessionName": "Proxy Demo",
# Sets the target country/region for the proxy, sending requests via an IP address from that region. You can specify a country code (e.g., US for the United States, GB for the United Kingdom, ANY for any country). See country codes for all supported options."proxyCountry": "ANY",
    }
    query_string = urlencode(scrapeless_params)
    scrapeless_connection_url = f"wss://browser.scrapeless.com/api/v2/browser?{query_string}"async with AsyncWebCrawler(
        config=BrowserConfig(
            headless=False,
            browser_mode="cdp",
            cdp_url=scrapeless_connection_url,
        )
    ) as crawler:
        result = await crawler.arun(
            url="https://www.scrapeless.com/en",
            config=CrawlerRunConfig(
                wait_for="css:.content",
                scan_full_page=True,
            ),
        )
        print("-" * 20)
        print(f'Status Code: {result.status_code}')
        print("-" * 20)
        print(f'Title: {result.metadata["title"]}')
        print(f'Description: {result.metadata["description"]}')
        print("-" * 20)
asyncio.run(main())
 

import json
import asyncio
from urllib.parse import quote, urlencode
from crawl4ai import CrawlerRunConfig, BrowserConfig, AsyncWebCrawler
 
async def main():
# customize browser fingerprint
    fingerprint = {
        "userAgent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/134.1.2.3 Safari/537.36",
        "platform": "Windows",
        "screen": {
            "width": 1280, "height": 1024
        },
        "localization": {
            "languages": ["zh-HK", "en-US", "en"], "timezone": "Asia/Hong_Kong",
        }
    }
 
    fingerprint_json = json.dumps(fingerprint)
    encoded_fingerprint = quote(fingerprint_json)
 
    scrapeless_params = {
        "token": "your token",
        "sessionTTL": 1000,
        "sessionName": "Fingerprint Demo",
        "fingerprint": encoded_fingerprint,
    }
    query_string = urlencode(scrapeless_params)
    scrapeless_connection_url = f"wss://browser.scrapeless.com/api/v2/browser?{query_string}"async with AsyncWebCrawler(
        config=BrowserConfig(
            headless=False,
            browser_mode="cdp",
            cdp_url=scrapeless_connection_url,
        )
    ) as crawler:
        result = await crawler.arun(
            url="https://www.scrapeless.com/en",
            config=CrawlerRunConfig(
                wait_for="css:.content",
                scan_full_page=True,
            ),
        )
        print("-" * 20)
        print(f'Status Code: {result.status_code}')
        print("-" * 20)
        print(f'Title: {result.metadata["title"]}')
        print(f'Description: {result.metadata["description"]}')
        print("-" * 20)
asyncio.run(main())
 

import asyncio
from urllib.parse import urlencode
from crawl4ai import CrawlerRunConfig, BrowserConfig, AsyncWebCrawler
 
async def main():
    scrapeless_params = {
        "token": "your token",
        "sessionTTL": 1000,
        "sessionName": "Profile Demo",
        "profileId": "your profileId",# create profile on scrapeless
    }
    query_string = urlencode(scrapeless_params)
    scrapeless_connection_url = f"wss://browser.scrapeless.com/api/v2/browser?{query_string}"async with AsyncWebCrawler(
        config=BrowserConfig(
            headless=False,
            browser_mode="cdp",
            cdp_url=scrapeless_connection_url,
        )
    ) as crawler:
        result = await crawler.arun(
            url="https://www.scrapeless.com",
            config=CrawlerRunConfig(
                wait_for="css:.content",
                scan_full_page=True,
            ),
        )
        print("-" * 20)
        print(f'Status Code: {result.status_code}')
        print("-" * 20)
        print(f'Title: {result.metadata["title"]}')
        print(f'Description: {result.metadata["description"]}')
        print("-" * 20)
asyncio.run(main())