main.py

from typing import List
from time import sleep
from selenium.webdriver.common.by import By
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.chrome.options import Options


class Scraper:

    @staticmethod
    def _chrome_driver_configuration() -> Options:
        chrome_options = Options()
        chrome_options.add_argument("--disable-notifications")
        chrome_options.add_argument("--disable-extensions")
        chrome_options.add_argument("--disable-popup-blocking")
        chrome_options.add_argument("--disable-default-apps")
        chrome_options.add_argument("--disable-infobars")
        chrome_options.add_argument("--disable-web-security")
        chrome_options.add_argument(
            "--disable-features=IsolateOrigins,site-per-process"
        )
        chrome_options.add_argument(
            "--enable-features=NetworkService,NetworkServiceInProcess"
        )
        chrome_options.add_argument("--profile-directory=Default")
        chrome_options.add_experimental_option("excludeSwitches", ["enable-logging"])
        return chrome_options



class BaseInstagramScraper(Scraper):
    def __init__(self, user_id: str, base_url: str) -> None:
        super().__init__()
        self._user_id = user_id
        self._base_url = base_url.format(self._user_id)
        self._driver = webdriver.Chrome(options=self._chrome_driver_configuration())
        self._driver.get(self._base_url)
        self._wait = WebDriverWait(self._driver, 10)



def scroll_page_callback(driver, callback) -> None:
    """
    Scrolls the page to load more data from a website
    """
    try:
        last_height = driver.execute_script("return document.body.scrollHeight")
        consecutive_scrolls = 0

        while consecutive_scrolls < 3:
            driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")

            sleep(3)
            new_height = driver.execute_script("return document.body.scrollHeight")

            if new_height == last_height:
                consecutive_scrolls += 1
            else:
                consecutive_scrolls = 0

            last_height = new_height

            callback(driver)

    except Exception as e:
        logs.log_error(f"Error occurred while scrolling: {e}")

class ProfileScraper(BaseInstagramScraper):
    def __init__(self, user_id: str) -> None:
        super().__init__(user_id, base_url=f"https://www.instagram.com/{user_id}/")
        self._driver.add_cookie(
            {
                "name": "sessionid",
                "value": "PUTITHERE",
                "domain": ".instagram.com",
            }
        )
        self._refresh_driver()

    def _refresh_driver(self) -> None:
        self._driver.refresh()

    def extract_images(self):
        extracted_image_urls = []
        try:

            def extract_callback(driver):
                img_elements = self._driver.find_elements(
                    By.CLASS_NAME,
                    "x5yr21d.xu96u03.x10l6tqk.x13vifvy.x87ps6o.xh8yej3",
                )
                for img_element in img_elements:
                    src_attribute = img_element.get_attribute("src")
                    if src_attribute and src_attribute not in extracted_image_urls:
                        extracted_image_urls.append(src_attribute)

            scroll_page_callback(self._driver, extract_callback)

        except Exception as e:
            print(f"An  error occurred while extracting images: {e}")

        return extracted_image_urls


if __name__ == "__main__":
    scraper = ProfileScraper("sawardega_wataha")
    data = scraper.extract_images()
    print(len(data))
    print(data[0])