TikTok scrapper

import os
import time
import csv
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options as ChromeOptions
from selenium.webdriver.common.by import By
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

def main():
    # Path to ChromeDriver
    chromedriver_path = r"D:\Scolarité\Droit\M1\RECHERCHE\DSA TRANSPARENCY\ROUMANIE\tiktokscrap\chromedriver.exe"

    # Chrome options
    options = ChromeOptions()
    options.add_argument("--disable-gpu")
    options.add_argument("--window-size=1920,1080")
    # options.add_argument("--headless")  # Uncomment to run without a GUI

    # Initialize WebDriver with Service
    service = Service(chromedriver_path)
    driver = webdriver.Chrome(service=service, options=options)

    # CSV file for saving data
    output_file = "tiktok_video_data.csv"
    if not os.path.exists(output_file):
        with open(output_file, mode="w", newline="", encoding="utf-8") as file:
            writer = csv.writer(file)
            writer.writerow(["Video Link", "Views", "Likes", "Comments", "Bookmarks", "Date"])

    try:
        # Access TikTok account page
        account_url = "https://www.tiktok.com/@calingeorgescuoficial"
        print(f"Navigating to TikTok account: {account_url}")
        driver.get(account_url)

        # Wait for the page to load and potentially solve CAPTCHA manually
        print("Waiting for you to resolve CAPTCHA (if needed).")
        WebDriverWait(driver, 60).until(EC.presence_of_element_located((By.TAG_NAME, "body")))  # Wait for body element to load

        # Scroll to load all videos
        print("Scrolling to ensure all videos load...")
        scroll_pause_time = 2
        last_height = driver.execute_script("return document.body.scrollHeight")

        while True:
            driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
            time.sleep(scroll_pause_time)
            new_height = driver.execute_script("return document.body.scrollHeight")
            if new_height == last_height:
                break
            last_height = new_height

        # Scroll back to the top
        print("Scrolling back to the top...")
        driver.execute_script("window.scrollTo(0, 0);")
        time.sleep(2)

        # Collect all video elements
        print("Collecting video elements...")
        video_containers = driver.find_elements(By.XPATH, '//div[contains(@class, "css-13fa1gi-DivWrapper")]//a[@href and contains(@class, "css-1g95xhm-AVideoContainer")]')

        if not video_containers:
            print("No videos found on the page.")
            return

        # Display available videos and ask user for a starting point
        print("Available videos:")
        video_links = [video.get_attribute("href") for video in video_containers]
        for idx, video_link in enumerate(video_links):
            print(f"{idx + 1}: {video_link}")

        choice = int(input("Enter the number of the video to start from: ")) - 1
        if choice < 0 or choice >= len(video_links):
            print("Invalid choice. Exiting.")
            return

        print(f"Starting from video: {video_links[choice]}")

        # Process the selected video and subsequent ones
        for video_element in video_containers[choice:]:
            try:
                # Scroll to the video
                ActionChains(driver).move_to_element(video_element).perform()
                time.sleep(2)

                # Collect video details
                video_link = video_element.get_attribute("href")
                print(f"Video Link: {video_link}")

                # Wait for views to be visible
                views_xpath = './/strong[@data-e2e="video-views" and contains(@class, "video-count")]'
                video_views_element = WebDriverWait(video_element, 10).until(EC.presence_of_element_located((By.XPATH, views_xpath)))
                video_views = video_views_element.text
                print(f"Views: {video_views}")

                # Click the video to get more details
                video_element.click()
                time.sleep(2)

                # Pause the video
                print("Pausing the video...")
                video_tag = WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.TAG_NAME, "video")))
                video_tag.click()
                time.sleep(1)

                # Collect likes, comments, bookmarks, and date
                like_count = driver.find_element(By.XPATH, '//strong[@data-e2e="browse-like-count" and contains(@class, "css-vc3yj-StrongText")]').text
                comment_count = driver.find_element(By.XPATH, '//strong[@data-e2e="browse-comment-count" and contains(@class, "css-vc3yj-StrongText")]').text
                bookmark_count = driver.find_element(By.XPATH, '//strong[@data-e2e="undefined-count" and contains(@class, "css-vc3yj-StrongText")]').text
                date = driver.find_element(By.XPATH, '//span[@data-e2e="browser-nickname"]/span[last()]').text

                print(f"Likes: {like_count}")
                print(f"Comments: {comment_count}")
                print(f"Bookmarks: {bookmark_count}")
                print(f"Date: {date}")

                # Write data to CSV
                with open(output_file, mode="a", newline="", encoding="utf-8") as file:
                    writer = csv.writer(file)
                    writer.writerow([video_link, video_views, like_count, comment_count, bookmark_count, date])

                print("Data saved to CSV.")

                # Return to the previous page
                driver.execute_script("window.history.go(-1)")
                time.sleep(2)

            except Exception as e:
                print(f"Error processing video: {e}")

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

    finally:
        # Close the browser
        driver.quit()
        print("Browser closed.")

if __name__ == "__main__":
    main()