I have a Python script that visits a website every 30 sec, and I would need to have a different IP address each time.
What would be the best/most time effective solution?
scraping free proxies online? Do you know a python script that gather proxies from many sources?
use Tor browser to have a different IP each time (I'm using selenium on an aws ec2 instance, you guys know a tutorial on how to use Tor browser on Ubuntu server?)
other methods?
A rotating proxy is a proxy server that assigns a new IP address from the proxy pool for every connection. That means you can launch a script to send 10,000 requests to any number of sites and get 10,000 different IP addresses.
To gather and use different proxies a robust solution would be to make proxied requests to the website using the newly active proxies which gets listed within the Free Proxy List using the following solution:
Code Block:
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
options = webdriver.ChromeOptions()
options.add_argument("start-maximized")
options.add_experimental_option("excludeSwitches", ["enable-automation"])
options.add_experimental_option('useAutomationExtension', False)
driver = webdriver.Chrome(chrome_options=options, executable_path=r'C:\WebDrivers\chromedriver.exe')
driver.get("https://sslproxies.org/")
driver.execute_script("return arguments[0].scrollIntoView(true);", WebDriverWait(driver, 20).until(EC.visibility_of_element_located((By.XPATH, "//table[@class='table table-striped table-bordered dataTable']//th[contains(., 'IP Address')]"))))
ips = [my_elem.get_attribute("innerHTML") for my_elem in WebDriverWait(driver, 5).until(EC.visibility_of_all_elements_located((By.XPATH, "//table[@class='table table-striped table-bordered dataTable']//tbody//tr[@role='row']/td[position() = 1]")))]
ports = [my_elem.get_attribute("innerHTML") for my_elem in WebDriverWait(driver, 5).until(EC.visibility_of_all_elements_located((By.XPATH, "//table[@class='table table-striped table-bordered dataTable']//tbody//tr[@role='row']/td[position() = 2]")))]
driver.quit()
proxies = []
for i in range(0, len(ips)):
proxies.append(ips[i]+':'+ports[i])
print(proxies)
for i in range(0, len(proxies)):
try:
print("Proxy selected: {}".format(proxies[i]))
options = webdriver.ChromeOptions()
options.add_argument('--proxy-server={}'.format(proxies[i]))
driver = webdriver.Chrome(options=options, executable_path=r'C:\WebDrivers\chromedriver.exe')
driver.get("https://www.whatismyip.com/proxy-check/?iref=home")
if "Proxy Type" in WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.CSS_SELECTOR, "p.card-text"))):
break
except Exception:
driver.quit()
print("Proxy Invoked")
Console Output:
['190.7.158.58:39871', '175.139.179.65:54980', '186.225.45.146:45672', '185.41.99.100:41258', '43.230.157.153:52986', '182.23.32.66:30898', '36.37.160.253:31450', '93.170.15.214:56305', '36.67.223.67:43628', '78.26.172.44:52490', '36.83.135.183:3128', '34.74.180.144:3128', '206.189.122.177:3128', '103.194.192.42:55546', '70.102.86.204:8080', '117.254.216.97:23500', '171.100.221.137:8080', '125.166.176.153:8080', '185.146.112.24:8080', '35.237.104.97:3128']
Proxy selected: 190.7.158.58:39871
Proxy selected: 175.139.179.65:54980
Proxy selected: 186.225.45.146:45672
Proxy selected: 185.41.99.100:41258
The site 'https://sslproxies.org/' seems got updated. Here is an updated code -
from selenium import webdriver
from selenium.webdriver.common.by import By
import chromedriver_autoinstaller # pip install chromedriver-autoinstaller
chromedriver_autoinstaller.install() # To update your chromedriver automatically
driver = webdriver.Chrome()
# Get free proxies for rotating
def get_free_proxies(driver):
driver.get('https://sslproxies.org')
table = driver.find_element(By.TAG_NAME, 'table')
thead = table.find_element(By.TAG_NAME, 'thead').find_elements(By.TAG_NAME, 'th')
tbody = table.find_element(By.TAG_NAME, 'tbody').find_elements(By.TAG_NAME, 'tr')
headers = []
for th in thead:
headers.append(th.text.strip())
proxies = []
for tr in tbody:
proxy_data = {}
tds = tr.find_elements(By.TAG_NAME, 'td')
for i in range(len(headers)):
proxy_data[headers[i]] = tds[i].text.strip()
proxies.append(proxy_data)
return proxies
free_proxies = get_free_proxies(driver)
print(free_proxies)
You'll get an output in python dictionary like this -
[{'IP Address': '200.85.169.18',
'Port': '47548',
'Code': 'NI',
'Country': 'Nicaragua',
'Anonymity': 'elite proxy',
'Google': 'no',
'Https': 'yes',
'Last Checked': '8 secs ago'},
{'IP Address': '191.241.226.230',
'Port': '53281',
'Code': 'BR',
'Country': 'Brazil',
'Anonymity': 'elite proxy',
'Google': 'no',
'Https': 'yes',
'Last Checked': '8 secs ago'},
.
.
.
}]
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With