I am trying to create a Python script that navigates to a YouTube video and scrapes the transcript and saves it locally.

The stages involved are: Navigate to video (url) -> click “more” -> “Show transcript” and then scrape the transcript and dump it in a JSON file.

Step 1: Click more (Completed)

Step 2: Click Show transcript (to be completed)

Step 3: Scrape transcript (to be completed).

Transcript window will then appear and load on the right side of the description window.

At the moment I can expand the description but can’t seem to find a way to click “Show transcript” and then scrape/save the transcript. This is what I need help with.

Here’s my code so far:

SBR_WEBDRIVER = ''
URL = 'https://www.youtube.com/watch?v=yKXk7L2RzLI'

logging.basicConfig(level=logging.INFO)

def expand_description(driver):
    wait = WebDriverWait(driver, 10)
    try:
        element = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, '#expand')))
        element.click()
        logging.info("Description expanded successfully")
    except Exception as e:
        logging.error("Error occurred while expanding description: %s", e)

#TODO
def click_show_transcript(driver):
    wait = WebDriverWait(driver, 10)
    try:
        element = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'#primary-button.style-scope.ytd-video-description-transcript-section-renderer')))
        driver.execute_script("arguments[0].scrollIntoView();", element)
        time.sleep(2)
        element.click()
        logging.info("Show transcript clicked successfully")
        time.sleep(10)
    except Exception as e:
        logging.error("Error occurred while clicking show transcript: %s", e)

# TODO
# def scrape_transcript(driver):
#     try:
#         extract full transcript into variable
#         return transcript
#     except NoSuchElementException as e:
#         logging.error("Error occurred while scraping transcript: %s", e)
    
def save_transcript_to_json(transcript):
    with open('transcript_dump.json', 'w') as file:
        json.dump(transcript, file, indent=4)
    logging.info("Transcript saved to transcript_dump.json")

logging.info('Connecting to Scraping Browser...')
with Remote(SBR_WEBDRIVER, options=ChromeOptions()) as driver:
    logging.info("Getting url: %s", URL)
    driver.get(URL)
    logging.info("Successfully connected to Scraping Browser...")
    try:
        logging.info("Waiting for the video to load...")
        WebDriverWait(driver, 10).until(EC.visibility_of_element_located((By.CSS_SELECTOR, 'h1.ytd-watch-metadata')))
        logging.info("Video loaded")
        expand_description(driver)
        click_show_transcript(driver)
        # transcript = scrape_transcript(driver)
        # save_transcript_to_json(transcript)
        logging.info("Scraping complete")
    except Exception as e:
        logging.error("Error occurred during scraping: %s", e)

Thanks.