Personal Video Database

# Function to download a page and handle "See more" clicks for specific pages
def download_page(download_url, output_path, port, retries=3):
    time.sleep(random.uniform(1.0, 3.0))
    logging.debug(f"Starting download for URL: {download_url} on port {port}")
    logging.debug(f"Output path: {output_path}")

    marker_file_path = os.path.splitext(output_path)[0] + "_status.txt"  # Define marker file path
    attempt = 0
    success = False

    try:
        while attempt < retries:
            attempt += 1
            logging.debug(f"Attempt {attempt} for URL: {download_url}")

            try:
                # Attach to existing Chrome instance on given port
                service = Service(chrome_path)
                chrome_options = webdriver.ChromeOptions()
                chrome_options.add_experimental_option("debuggerAddress", f"127.0.0.1:{port}")
                driver = webdriver.Chrome(service=service, options=chrome_options)

                logging.info(f"Attached to Chrome on port {port}")

                try:
                    # Navigate to the target page
                    driver.get(download_url)
                    logging.info(f"Page {download_url} loaded successfully.")

                    # Wait for the page to load
                    WebDriverWait(driver, 3).until(
                        EC.presence_of_element_located((By.TAG_NAME, "body"))
                    )

                    # Click all "See more" buttons only for specific pages
                    if any(keyword in download_url for keyword in [
                        'fullcredits', 'awards', 'keywords', 'releaseinfo', 'plotsummary',
                        'reviews', 'companycredits', 'locations', 'technical',
                        'externalsites', 'movieconnections'
                    ]):

                        def click_all_or_more_buttons():
                            """
                            Clicks every 'See all' or 'X more' button on the page,
                            starting from the bottom to handle pages like Movie Connections.
                            Waits for content to load after each click.
                            """
                            while True:
                                try:
                                    # Find all current see-more buttons
                                    buttons = driver.find_elements(
                                        By.XPATH, "//button[contains(@class, 'ipc-see-more__button')]"
                                    )
                                    if not buttons:
                                        break

                                    # Reverse order: start from bottom-most button
                                    buttons = list(reversed(buttons))
                                    clicked_any = False

                                    for button in buttons:
                                        try:
                                            text = button.text.strip().lower()
                                            if "all" in text or "more" in text:
                                                logging.info(f"Clicking button with text: {text}")
                                                driver.execute_script("arguments[0].scrollIntoView(true);", button)
                                                time.sleep(0.5)
                                                driver.execute_script("arguments[0].click();", button)
                                                # Wait until the button becomes stale (DOM updated)
                                                WebDriverWait(driver, 10).until(EC.staleness_of(button))
                                                clicked_any = True
                                                break  # re-find buttons after DOM update
                                        except Exception as e:
                                            logging.warning(f"Could not click button: {e}")

                                    if not clicked_any:
                                        break

                                except Exception:
                                    break

                        click_all_or_more_buttons()

                    # Retrieve the full source HTML of the page after all "More" buttons are clicked
                    html_source = driver.page_source
                    logging.debug(f"HTML source length: {len(html_source)}")

                    # Detect AWS WAF challenge page before saving
                    if "challenge-container" in html_source or "awswaf.com" in html_source:
                        logging.warning(f"IMDb WAF challenge detected for {download_url}. Skipping normal save.")
                        # Append the skipped URL to imdb_skipped_urls.log (one per line)
                        with open("imdb_skipped_urls.log", "a", encoding="utf-8") as skip_log:
                            skip_log.write(download_url + "\n")
                        success = False  # mark as failed so marker file shows FAILED
                    else:
                        # Save the HTML using helper (sets success via try/except)
                        try:
                            save_artifacts(driver, output_path)
                            success = True
                            logging.info(f"HTML saved to file: {output_path}")
                        except Exception as e:
                            logging.error(f"Failed to save artifacts for {download_url}: {e}")
                            success = False

                    # If successful, set the success flag and break
                    if success:
                        break

                except WebDriverException as e:
                    logging.error(f"An error occurred while processing {download_url}: {e}")

            except Exception as e:
                logging.error(f"An error occurred: {e}")
            finally:
                try:
                    # Reset the window instead of closing it
                    driver.get("about:blank")
                    logging.info("Reset Chrome window to blank, still running.")
                except Exception as e:
                    logging.warning(f"Could not reset window: {e}")

    finally:
        # Always create the marker file, even if everything failed
        with open(marker_file_path, "w") as marker_file:
            if success and os.path.exists(output_path):
                marker_file.write("SUCCESS")
                logging.info(f"Marker file created: {marker_file_path} with status SUCCESS")
            elif not success:
                marker_file.write("FAILED")
                logging.info(f"Marker file created: {marker_file_path} with status FAILED")
            else:
                marker_file.write("NOT_FOUND")
                logging.info(f"Marker file created: {marker_file_path} with status NOT_FOUND")

from concurrent.futures import ThreadPoolExecutor, as_completed

# Define the ports for the Chrome instances you started manually
ports = [9222, 9223, 9224, 9225]

# Main script execution - use ThreadPoolExecutor for clean concurrency
try:
    # Adjust max_workers to control how many browser sessions run in parallel
    with ThreadPoolExecutor(max_workers=4) as executor:
        # Submit all download tasks, assigning ports round-robin
        futures = {
            executor.submit(download_page, url, save_path, ports[i % len(ports)]): (url, save_path)[/i]
            for i, (url, save_path) in enumerate(URLS_AND_PATHS.items())
        }

        # Wait for all tasks to complete
        for future in as_completed(futures):
            url, save_path = futures[future]
            try:
                future.result()  # raises exception if download_page failed
                logging.info(f"Download task finished for {url}")
            except Exception as e:
                logging.error(f"Download task failed for {url}: {e}")

    # Build list of marker files for all processed URLs
    marker_files = [os.path.splitext(save_path)[0] + "_status.txt"
                    for save_path in URLS_AND_PATHS.values()]

    # Check markers to decide final status
    if all(os.path.exists(path) and "SUCCESS" in open(path).read()
           for path in marker_files):
        logging.info("All pages have been saved successfully.")
    else:
        logging.warning("Some pages failed. Check marker files for details.")

except Exception as e:
    logging.error(f"An error occurred during threading: {e}")
    sys.exit(1)  # Exit the script with an error code

# Exit the script successfully
sys.exit(0)  # Exit successfully

This just sleeps between 8 and 12 seconds and it could be very fragile. Also, it makes whole process longer 1-2 minutes per title?

Quote from: jondak on January 22, 2026, 08:44:31 pm

Just in case other people get this to fix it in Selenium_Chrome_Movie_Additional_pages_v4:

after driver.get(download_url)

i added:

time.sleep(random.uniform(8, 12))

This change does not work because it blocks the download of Additional pages.

Just in case other people get this to fix it in Selenium_Chrome_Movie_Additional_pages_v4:

after driver.get(download_url)

i added:

time.sleep(random.uniform(8, 12))