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():
    # Chemin vers ChromeDriver
    chromedriver_path = r"D:\Scolarité\Droit\M1\RECHERCHE\DSA TRANSPARENCY\ROUMANIE\tiktokscrap\chromedriver.exe"  # Remplacez par le chemin exact

    # Options pour Chrome
    options = ChromeOptions()
    options.add_argument("--disable-gpu")
    options.add_argument("--window-size=1920,1080")
    # Supprimez "--headless" pour voir le navigateur
    # options.add_argument("--headless")

    # Initialisation du WebDriver avec Service
    service = Service(chromedriver_path)
    driver = webdriver.Chrome(service=service, options=options)

    # Fichier CSV pour enregistrer les données
    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:
        # Accéder au compte TikTok spécifique
        account_url = "https://www.tiktok.com/@calingeorgescuoficial"
        print(f"Navigating to TikTok account: {account_url}")
        driver.get(account_url)

        # Attendre que la page charge
        print("Waiting for page to load...")
        WebDriverWait(driver, 30).until(EC.presence_of_element_located((By.XPATH, '//div[contains(@class, "tiktok-1dykci5-DivWrapper")]')))

        # Scrolling pour charger toutes les vidéos
        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

        # Scrolling vers le haut après avoir chargé toutes les vidéos
        print("Scrolling back to the top...")
        driver.execute_script("window.scrollTo(0, 0);")
        time.sleep(2)

        # Collecter les vidéos
        video_containers = driver.find_elements(By.XPATH, '//div[contains(@class, "tiktok-1dykci5-DivWrapper")]//a[@href and contains(@class, "tiktok-1ghj7dv-AVideoContainer")]')

        if video_containers:
            for video_element in video_containers:
                try:
                    # Faire défiler jusqu'à l'élément
                    ActionChains(driver).move_to_element(video_element).perform()
                    time.sleep(2)

                    # Collecter le lien de la vidéo
                    video_link = video_element.get_attribute("href")
                    print(f"Video Link: {video_link}")

                    # Cliquer sur la vidéo pour ouvrir la page de détails
                    video_element.click()
                    WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.TAG_NAME, "video")))

                    # Mettre la vidéo en pause
                    video_tag = driver.find_element(By.TAG_NAME, "video")
                    video_tag.click()
                    time.sleep(1)

                    # Collecter les autres données
                    like_xpath = '//strong[@data-e2e="browse-like-count"]'
                    comment_xpath = '//strong[@data-e2e="browse-comment-count"]'
                    bookmark_xpath = '//strong[@data-e2e="undefined-count"]'
                    date_xpath = '//span[@data-e2e="browser-nickname"]/span[last()]'

                    like_count = driver.find_element(By.XPATH, like_xpath).text
                    comment_count = driver.find_element(By.XPATH, comment_xpath).text
                    bookmark_count = driver.find_element(By.XPATH, bookmark_xpath).text
                    date = driver.find_element(By.XPATH, date_xpath).text

                    # Sauvegarder les données dans le fichier CSV
                    with open(output_file, mode="a", newline="", encoding="utf-8") as file:
                        writer = csv.writer(file)
                        writer.writerow([video_link, "", like_count, comment_count, bookmark_count, date])

                    print("Data saved to CSV.")
                    driver.back()
                    WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.XPATH, '//div[contains(@class, "tiktok-1dykci5-DivWrapper")]')))

                except Exception as e:
                    print(f"Error processing video: {e}")
        else:
            print("No videos found on the page.")

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

    finally:
        # Fermer le navigateur
        driver.quit()
        print("Browser closed.")

if __name__ == "__main__":
    main()