How to Use curl_cffi for Web Scraping

sudo apt-get install libcurl4-openssl-dev

pip install curl_cffi

from curl_cffi import requests

# Perform a GET request
response = requests.get('https://httpbin.org/get')

# Check the status code
print(f'Status Code: {response.status_code}')

# Print the response content
print('Response Body:', response.text)

from curl_cffi import requests
from bs4 import BeautifulSoup

# URL to scrape
url = 'http://quotes.toscrape.com/'

# Perform a GET request
response = requests.get(url)

# Parse the HTML content using BeautifulSoup
soup = BeautifulSoup(response.content, 'html.parser')

# Find all quote elements
quotes = soup.find_all('div', class_='quote')

# Extract and display the quotes and authors
for quote in quotes:
    text = quote.find('span', class_='text').get_text()
    author = quote.find('small', class_='author').get_text()
    print(f'{text} — {author}')

“The world as we have created it is a process of our thinking. It cannot be changed without changing our thinking.” — Albert Einstein
“It is our choices, Harry, that show what we truly are, far more than our abilities.” — J.K. Rowling
... (additional quotes)

import os
import capsolver
from curl_cffi import requests

# Consider using environment variables for sensitive information
capsolver.api_key = os.getenv("CAPSOLVER_API_KEY", "Your CapSolver API Key")
PAGE_URL = os.getenv("PAGE_URL", "https://example.com")  # URL of the page with the captcha
PAGE_KEY = os.getenv("PAGE_SITE_KEY", "SITE_KEY")        # Site key for the captcha

def solve_recaptcha_v2(url, site_key):
    solution = capsolver.solve({
        "type": "ReCaptchaV2TaskProxyless",
        "websiteURL": url,
        "websiteKey": site_key,
        "proxy": PROXY
    })
    return solution['solution']['gRecaptchaResponse']

def main():
    print("Solving reCaptcha V2...")
    captcha_solution = solve_recaptcha_v2(PAGE_URL, PAGE_KEY)
    print("Captcha Solved!")

if __name__ == "__main__":
    main()

from curl_cffi import requests

# Define the proxy settings
proxies = {
    'http': 'http://username:password@proxyserver:port',
    'https': 'https://username:password@proxyserver:port',
}

# Perform a GET request using the proxy
response = requests.get('https://httpbin.org/ip', proxies=proxies)

# Print the response content
print('Response Body:', response.text)

from curl_cffi import requests
from http.cookiejar import CookieJar

# Create a CookieJar instance
cookie_jar = CookieJar()

# Create a session with the cookie jar
session = requests.Session()
session.cookies = cookie_jar

# Perform a GET request
response = session.get('https://httpbin.org/cookies/set?name=value')

# Display the cookies
for cookie in session.cookies:
    print(f'{cookie.name}: {cookie.value}')

from curl_cffi import requests

# Define custom headers
headers = {
    'User-Agent': 'Mozilla/5.0 (compatible)',
    'Accept-Language': 'en-US,en;q=0.5',
}

# Data to send in the POST request
data = {
    'username': 'testuser',
    'password': 'testpass',
}

# Perform a POST request
response = requests.post('https://httpbin.org/post', headers=headers, data=data)

# Print the JSON response
print('Response JSON:', response.json())