Instagram scraping with Selenium

gistfile1.txt

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.edge.options import Options
from selenium.webdriver.chrome.options import Options
import time

# Path to the Chrome user profile directory
user_data_dir = "/tmp/"  # Replace with your profile path

# Set up Chrome options
chrome_options = Options()
chrome_options.add_argument(f"--user-data-dir={user_data_dir}")

chrome_options.add_argument("--headless")  # Uncomment for headless mode

driver = webdriver.Edge(options=chrome_options)

driver.get("https://www.instagram.com/")

time.sleep(2)

try:
    username = driver.find_element(By.XPATH, "//input[@name='username']")
    password = driver.find_element(By.XPATH, "//input[@name='password']")
    submit_button = driver.find_element(By.XPATH, "//button[@type='submit']")

    username.send_keys("testa_ccount7482")  # Replace with your username
    password.send_keys("BkYGMDNTa.+Lg4E")  # Replace with your password
    submit_button.click()
except Exception as e:
    print("already logged in or error finding elements")

time.sleep(5)

body = driver.find_element(By.TAG_NAME, "body")

urls = set()
for _ in range(10):
    body.send_keys(Keys.PAGE_DOWN)
    imgs = driver.find_elements(By.XPATH, "//img")
    try:
        for img in imgs:
            try:
                src = img.get_attribute("src")
                urls.add(src)
                # TODO: remove the following line
            except Exception as e:
                print(f"Error retrieving URL")
    except Exception as e:
        print(f"Error finding images")
    time.sleep(1)  # Adjust the sleep time as needed to load more content

print(f"Total unique URLs found: {len(urls)}")
with open("urls.txt", "a") as f:
    for url in list(urls):
        f.write(str(url) + "\n")

driver.quit()