ازگر کے ساتھ YouTube کے اہم ڈیٹا کو کھرچنے کا طریقہ

pip install selenium-wire selenium blinker==1.7.0

from selenium.webdriver.chrome.options import Options
from seleniumwire import webdriver as wiredriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.action_chains import ActionChains
import json
import time

# صارف نام اور پاس ورڈ کے ساتھ پراکسی سرور ایڈریس کی وضاحت کریں
proxy_address = ""
proxy_username = ""
proxy_password = ""
# پراکسی اور توثیق کے ساتھ کروم کے اختیارات مرتب کریں
chrome_options = Options()
chrome_options.add_argument(f'--proxy-server={proxy_address}')
chrome_options.add_argument(f'--proxy-auth={proxy_username}:{proxy_password}')
# سیلینیم وائر کے ساتھ ویب ڈرایور مثال بنائیں
driver = wiredriver.Chrome(options=chrome_options)

youtube_url_to_scrape = ""
# سیلینیم وائر کی بہتر صلاحیتوں کے ساتھ اپنے سیلینیم آٹومیشن کو انجام دیں
driver.get(youtube_url_to_scrape)

def extract_information() -> dict:
   try:
       element = WebDriverWait(driver, 15).until(
           EC.presence_of_element_located((By.XPATH, '//*[@id="expand"]'))
       )

       element.click()

       time.sleep(10)
       actions = ActionChains(driver)
       actions.send_keys(Keys.END).perform()
       time.sleep(10)
       actions.send_keys(Keys.END).perform()
       time.sleep(10)

 video_title = driver.find_elements(By.XPATH, '//*[@id="title"]/h1')[0].text

   owner = driver.find_elements(By.XPATH, '//*[@id="text"]/a')[0].text

   total_number_of_subscribers = \
       driver.find_elements(By.XPATH, "//div[@id='upload-info']//yt-formatted-string[@id='owner-sub-count']")[
           0].text

   video_description = driver.find_elements(By.XPATH,                                  '//*[@id="description-inline-expander"]/yt-attributed-string/span/span')
   result = []
   for i in video_description:
       result.append(i.text)
   description = ''.join(result)

   publish_date = driver.find_elements(By.XPATH, '//*[@id="info"]/span')[2].text
   total_views = driver.find_elements(By.XPATH, '//*[@id="info"]/span')[0].text

   number_of_likes = driver.find_elements(By.XPATH,                                   '//*[@id="top-level-buttons-computed"]/segmented-like-dislike-button-view-model/yt-smartimation/div/div/like-button-view-model/toggle-button-view-model/button-view-model/button/div')[
       1].text

   comment_names = driver.find_elements(By.XPATH, '//*[@id="author-text"]/span')
   comment_content = driver.find_elements(By.XPATH, '//*[@id="content-text"]/span')
   comment_library = []

   for each in range(len(comment_names)):
       name = comment_names[each].text
       content = comment_content[each].text
       indie_comment = {
           'name': name,
           'comment': content
       }
       comment_library.append(indie_comment)

   data = {
       'owner': owner,
       'subscribers': total_number_of_subscribers,
       'video_title': video_title,
       'description': description,
       'date': publish_date,
       'views': total_views,
       'likes': number_of_likes,
       'comments': comment_library
   }

   return data

except Exception as err:
   print(f"Error: {err}")

def organize_write_data(data:dict):
    output = json.dumps(data, indent=2, ensure_ascii=False).encode("ascii", "ignore").decode("utf-8")
    try:
        with open("output.json", 'w', encoding='utf-8') as file:
            file.write(output)
    except Exception as err:
        print(f"Error encountered: {err}")

from selenium.webdriver.chrome.options import Options
from seleniumwire import webdriver as wiredriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.action_chains import ActionChains
import json
import time

# صارف نام اور پاس ورڈ کے ساتھ پراکسی سرور ایڈریس کی وضاحت کریں
proxy_address = ""
proxy_username = ""
proxy_password = ""

# پراکسی اور توثیق کے ساتھ کروم کے اختیارات مرتب کریں
chrome_options = Options()
chrome_options.add_argument(f'--proxy-server={proxy_address}')
chrome_options.add_argument(f'--proxy-auth={proxy_username}:{proxy_password}')

# سیلینیم وائر کے ساتھ ویب ڈرایور مثال بنائیں
driver = wiredriver.Chrome(options=chrome_options)

youtube_url_to_scrape = ""

# سیلینیم وائر کی بہتر صلاحیتوں کے ساتھ اپنے سیلینیم آٹومیشن کو انجام دیں
driver.get(youtube_url_to_scrape)


def extract_information() -> dict:
   try:
       element = WebDriverWait(driver, 15).until(
           EC.presence_of_element_located((By.XPATH, '//*[@id="expand"]'))
       )
       element.click()

       time.sleep(10)
       actions = ActionChains(driver)
       actions.send_keys(Keys.END).perform()
       time.sleep(10)
       actions.send_keys(Keys.END).perform()
       time.sleep(10)

       video_title = driver.find_elements(By.XPATH, '//*[@id="title"]/h1')[0].text

       owner = driver.find_elements(By.XPATH, '//*[@id="text"]/a')[0].text
       total_number_of_subscribers = \
           driver.find_elements(By.XPATH, "//div[@id='upload-info']//yt-formatted-string[@id='owner-sub-count']")[
               0].text

       video_description = driver.find_elements(By.XPATH,
                                                '//*[@id="description-inline-expander"]/yt-attributed-string/span/span')
       result = []
       for i in video_description:
           result.append(i.text)
       description = ''.join(result)

       publish_date = driver.find_elements(By.XPATH, '//*[@id="info"]/span')[2].text
       total_views = driver.find_elements(By.XPATH, '//*[@id="info"]/span')[0].text

       number_of_likes = driver.find_elements(By.XPATH,
                                              '//*[@id="top-level-buttons-computed"]/segmented-like-dislike-button-view-model/yt-smartimation/div/div/like-button-view-model/toggle-button-view-model/button-view-model/button/div')[
           1].text

       comment_names = driver.find_elements(By.XPATH, '//*[@id="author-text"]/span')
       comment_content = driver.find_elements(By.XPATH,
                                              '//*[@id="content-text"]/span')
       comment_library = []

       for each in range(len(comment_names)):
           name = comment_names[each].text
           content = comment_content[each].text
           indie_comment = {
               'name': name,
               'comment': content
           }
           comment_library.append(indie_comment)

       data = {
           'owner': owner,
           'subscribers': total_number_of_subscribers,
           'video_title': video_title,
           'description': description,
           'date': publish_date,
           'views': total_views,
           'likes': number_of_likes,
           'comments': comment_library
       }

       return data

   except Exception as err:
       print(f"Error: {err}")


# JSON کو ڈیٹا ریکارڈ کریں
def organize_write_data(data: dict):
   output = json.dumps(data, indent=2, ensure_ascii=False).encode("ascii", "ignore").decode("utf-8")
   try:
       with open("output.json", 'w', encoding='utf-8') as file:
           file.write(output)
   except Exception as err:
       print(f"Error encountered: {err}")


organize_write_data(extract_information())
driver.quit()