Reply to thread

Message: <blockquote data-quote="VimangaLK" data-source="post: 30656699" data-attributes="member: 587054">[CODE=python]from selenium import webdriverfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.chrome.options import Optionsfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.webdriver.support import expected_conditions as ECfrom selenium.common.exceptions import TimeoutException, NoSuchElementExceptionimport timeimport csv# TikTok video URLurl = "https://www.tiktok.com/@rizzcado/photo/7491129701956652306"# Configure Chrome options for headless browsingchrome_options = Options()# Comment out headless mode for debugging if needed# chrome_options.add_argument("--headless")chrome_options.add_argument("--disable-gpu")chrome_options.add_argument("--mute-audio")chrome_options.add_argument("--window-size=1920,1080") # Set window sizechrome_options.add_argument("--user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36")# Initialize the Chrome driverdriver = webdriver.Chrome(options=chrome_options)# Set page load timeoutdriver.set_page_load_timeout(30)# Navigate to the URLprint(f"Opening TikTok URL: {url}")driver.get(url)# Wait for page to load properlytime.sleep(5)# Function to scroll down to load more commentsdef scroll_to_load_comments(driver, max_scrolls=15):print("Starting to scroll to load comments...")last_height = driver.execute_script("return document.body.scrollHeight")scroll_count = 0while scroll_count < max_scrolls:# Scroll down to bottomdriver.execute_script("window.scrollTo(0, document.body.scrollHeight);")# Wait to load pagetime.sleep(3)# Calculate new scroll height and compare with last scroll heightnew_height = driver.execute_script("return document.body.scrollHeight")if new_height == last_height:# Try clicking "load more" if it existstry:load_buttons = driver.find_elements(By.XPATH, "//*[contains(text(), 'Load more') or contains(text(), 'View more')]")if load_buttons:for button in load_buttons:try:print("Clicking load more button...")driver.execute_script("arguments[0].click();", button)time.sleep(2)except:passelse:# If we scrolled a few times and no new content, breakif scroll_count > 3:breakexcept:if scroll_count > 3:breaklast_height = new_heightscroll_count += 1print(f"Completed scroll {scroll_count}/{max_scrolls}")# Try to handle cookie consent if it appearstry:cookie_buttons = driver.find_elements(By.XPATH, "//*[contains(text(), 'Accept') or contains(text(), 'Accept all')]")if cookie_buttons:for button in cookie_buttons:try:button.click()print("Clicked cookie consent button")time.sleep(1)except:passexcept:pass# Scroll to load commentsscroll_to_load_comments(driver)# Try different CSS selectors for commentspossible_comment_selectors = [".tiktok-x6o8yi-DivCommentItem","[data-e2e='comment-item']",".comment-item",".tiktok-comment-item","div[class*='CommentItem']"]comments = []used_selector = Nonefor selector in possible_comment_selectors:print(f"Trying to find comments with selector: {selector}")comment_elements = driver.find_elements(By.CSS_SELECTOR, selector)if comment_elements:used_selector = selectorprint(f"Found {len(comment_elements)} comments using selector: {selector}")breakif used_selector:comment_elements = driver.find_elements(By.CSS_SELECTOR, used_selector)for element in comment_elements:try:# Try different selectors for username and comment textusername_selectors = ['a[data-e2e="comment-username"]','span[data-e2e="comment-username"]','.nickname','a.user-nickname','div[class*="Author"] span']comment_selectors = ['p[data-e2e="comment-level"]','span[data-e2e="comment-text"]','.comment-text','div[class*="CommentText"]']user_name = Nonefor username_selector in username_selectors:try:user_name_element = element.find_element(By.CSS_SELECTOR, username_selector)user_name = user_name_element.text.strip()if user_name:breakexcept:continuecomment_text = Nonefor comment_selector in comment_selectors:try:comment_text_element = element.find_element(By.CSS_SELECTOR, comment_selector)comment_text = comment_text_element.text.strip()if comment_text:breakexcept:continueif user_name and comment_text:comments.append([user_name, comment_text])print(f"Extracted comment from {user_name}: {comment_text[:30]}...")except Exception as e:print(f"Error extracting comment: {e}")else:# If no comments found with CSS selectors, try XPath as a fallbackprint("No comments found with CSS selectors, trying XPath...")try:comment_elements = driver.find_elements(By.XPATH, "//div[contains(@class, 'Comment') or contains(@class, 'comment')]")print(f"Found {len(comment_elements)} comments using XPath")for element in comment_elements:try:full_text = element.text# Simple text processing to extract username and commentif ":" in full_text:parts = full_text.split(":", 1)user_name = parts[0].strip()comment_text = parts[1].strip()comments.append([user_name, comment_text])print(f"Extracted comment via text processing: {user_name}: {comment_text[:30]}...")except Exception as e:print(f"Error extracting comment with XPath: {e}")except Exception as e:print(f"Error with XPath approach: {e}")# Take a screenshot for debugging purposesscreenshot_file = "tiktok_screenshot.png"driver.save_screenshot(screenshot_file)print(f"Saved screenshot to {screenshot_file} for debugging")# Print summaryprint(f"Total comments extracted: {len(comments)}")# Close the driverdriver.quit()# Write comments to CSV filecsv_file = "tiktok_comments.csv"with open(csv_file, mode='w', newline='', encoding='utf-8') as file:writer = csv.writer(file)writer.writerow(["Username", "Comment"]) # Write headerwriter.writerows(comments) # Write commentsprint(f"Comments saved to {csv_file}")[/CODE]</blockquote>

Verification: Haya warak paha keeyada? (haya wadi kireema paha)

Top Bottom

Search

Latest ads

Reply to thread