ازگر اسکرپٹ کا استعمال کرتے ہوئے ٹویٹر ڈیٹا کو کھرچنے کا طریقہ

pip install selenium-wire selenium undetected-chromedriver

ایک بار تنصیب مکمل ہونے کے بعد ، آپ کو ان پیکیجوں کو اپنی ازگر فائل میں درآمد کرنا ہوگا جیسا کہ ذیل میں دکھایا گیا ہے۔

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

# پراکسی سرور ایڈریس کو صارف نام اور پاس ورڈ کے ساتھ پراکسیوں کی فہرست میں بتائیں
proxies = [
    "proxy_username:proxy_password@proxy_address:port_number",
]




# بے ترتیب پراکسی حاصل کرنے کے لئے فنکشن
def get_proxy():
    return random.choice(proxies)


# پراکسی اور توثیق کے ساتھ کروم کے اختیارات مرتب کریں
chrome_options = Options()
chrome_options.add_argument("--headless")


proxy = get_proxy()
proxy_options = {
    "proxy": {
        "http": f"http://{proxy}",
        "https": f"https://{proxy}",
    }
}

search_keyword = input("What topic on X/Twitter would you like to gather data on?\n").replace(' ', '%20')
constructed_url = f"https://twitter.com/search?q={search_keyword}&src=typed_query&f=top"


# اپنے X/ٹویٹر کا صارف نام اور پاس ورڈ یہاں فراہم کریں
x_username = "" 
x_password = ""


print(f'Opening {constructed_url} in Chrome...')


# بغیر پائے جانے والے کروم ڈرائیور کے ساتھ ویب ڈرایور مثال بنائیں
driver = uc.Chrome(options=chrome_options, seleniumwire_options=proxy_options)


driver.get(constructed_url)


try:
    element = WebDriverWait(driver, 20).until(
        EC.presence_of_element_located((By.XPATH, "//div[@class='css-175oi2r r-1mmae3n r-1e084wir-13qz1uu']"))
    )
except Exception as err:
    print(f'WebDriver Wait Error: Most likely Network TimeOut: Details\n{err}')
    driver.quit()


#سائن ان کریں
if element:
    username_field = driver.find_element(By.XPATH, "//input[@class='r-30o5oe r-1dz5y72 r-13qz1uu r-1niwhzg r-17gur6a r-1yadl64 r-deolkf r-homxoj r-poiln3 r-7cikom r-1ny4l3l r-t60dpp r-fdjqy7']")
    username_field.send_keys(x_username)
    username_field..send_keys(Keys.ENTER)


    password_field = WebDriverWait(driver, 10).until(
        EC.presence_of_element_located((By.XPATH, "//input[@class='r-30o5oe r-1dz5y72 r-13qz1uu r-1niwhzg r-17gur6a r-1yadl64 r-deolkf r-homxoj r-poiln3 r-7cikom r-1ny4l3l r-t60dpp r-fdjqy7']"))
    )
    password_field.send_keys(x_password)
    password_field.send_keys(Keys.ENTER)


    print("Sign In Successful...\n")


    sleep(10)

results = []


# کھرچنی
def scrape():
   display_names = driver.find_elements(By.XPATH,
                                        '//*[@class="css-175oi2r r-1wbh5a2 r-dnmrzs r-1ny4l3l r-1awozwy r-18u37iz"]/div[1]/div/a/div/div[1]/span/span')
   usernames = driver.find_elements(By.XPATH,
                                    '//*[@class="css-175oi2r r-1wbh5a2 r-dnmrzs r-1ny4l3l r-1awozwy r-18u37iz"]/div[2]/div/div[1]/a/div/span')
   posts = driver.find_elements(By.XPATH,
                                '//*[@class="css-146c3p1 r-8akbws r-krxsd3 r-dnmrzs r-1udh08x r-bcqeeo r-1ttztb7 r-qvutc0 r-37j5jr r-a023e6 r-rjixqe r-16dba41 r-bnwqim"]/span')
   comments = driver.find_elements(By.XPATH,
                                   '//*[@class="css-175oi2r r-1kbdv8c r-18u37iz r-1wtj0ep r-1ye8kvj r-1s2bzr4"]/div[1]/button/div/div[2]/span/span/span')
   retweets = driver.find_elements(By.XPATH,
                                   '//*[@class="css-175oi2r r-1kbdv8c r-18u37iz r-1wtj0ep r-1ye8kvj r-1s2bzr4"]/div[2]/button/div/div[2]/span/span/span')
   likes = driver.find_elements(By.XPATH,
                                '//*[@class="css-175oi2r r-1kbdv8c r-18u37iz r-1wtj0ep r-1ye8kvj r-1s2bzr4"]/div[3]/button/div/div[2]/span/span/span')
   impressions = driver.find_elements(By.XPATH,
                                      '//*[@class="css-175oi2r r-1kbdv8c r-18u37iz r-1wtj0ep r-1ye8kvj r-1s2bzr4"]/div[4]/a/div/div[2]/span/span/span')

   min_length = min(len(display_names), len(usernames), len(posts), len(comments), len(retweets), len(likes),
                    len(impressions))

   for each in range(min_length):
       results.append({
           'Username': usernames[each].text,
           'displayName': display_names[each].text,
           'Post': posts[each].text.rstrip("Show more"),
           'Comments': 0 if comments[each].text == "" else convert_to_numeric(comments[each].text),
           'Retweets': 0 if retweets[each].text == "" else convert_to_numeric(retweets[each].text),
           'Likes': 0 if likes[each].text == "" else convert_to_numeric(likes[each].text),
           'Impressions': 0 if impressions[each].text == "" else convert_to_numeric(impressions[each].text)
       })


def reorder_json_by_impressions(json_data):
   # نزول ترتیب میں 'تاثرات' پر مبنی JSON لسٹ کو جگہ جگہ ترتیب دیں
   json_data.sort(key=lambda x: int(x['Impressions']), reverse=True)


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


def convert_to_numeric(value):
   multipliers = {'K': 10 ** 3, 'M': 10 ** 6, 'B': 10 ** 9}

   try:
       if value[-1] in multipliers:
           return int(float(value[:-1]) * multipliers[value[-1]])
       else:
           return int(value)
   except ValueError:
      # اس معاملے کو سنبھالیں جہاں تبادلوں میں ناکام ہوجاتا ہے
       return None

def reorder_json_by_impressions(json_data):
    # نزول ترتیب میں 'تاثرات' پر مبنی JSON لسٹ کو جگہ جگہ ترتیب دیں
    json_data.sort(key=lambda x:int(x['Impressions']), reverse=True)

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

actions = ActionChains(driver)
for i in range(5):
    actions.send_keys(Keys.END).perform()
    sleep(5)
    scrape()


reorder_json_by_impressions(results)
organize_write_data(results)


print(f"Scraping Information on {search_keyword} is done.")


driver.quit()

from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.action_chains import ActionChains
from time import sleep
import json
import undetected_chromedriver as uc
import random
import ssl

ssl._create_default_https_context = ssl._create_stdlib_context


search_keyword = input("What topic on X/Twitter would you like to gather data on?\n").replace(' ', '%20')
constructed_url = f"https://twitter.com/search?q={search_keyword}&src=typed_query&f=top"

# اپنے X/ٹویٹر کا صارف نام اور پاس ورڈ یہاں فراہم کریں
x_username = ""
x_password = ""

print(f'Opening {constructed_url} in Chrome...')

# پراکسی سرور ایڈریس کو صارف نام اور پاس ورڈ کے ساتھ پراکسیوں کی فہرست میں بتائیں
proxies = [
   "USERNAME:PASSWORD@IP:PORT",
]


# بے ترتیب پراکسی حاصل کرنے کے لئے فنکشن
def get_proxy():
   return random.choice(proxies)


# پراکسی اور توثیق کے ساتھ کروم کے اختیارات مرتب کریں
chrome_options = Options()
chrome_options.add_argument("--headless")
chrome_options.add_argument('--ignore-certificate-errors')
chrome_options.add_argument('--ignore-ssl-errors')

proxy = get_proxy()
proxy_options = {
   "proxy": {
       "http": f"http://{proxy}",
       "https": f"https://{proxy}",
   }
}

# بغیر پائے جانے والے کروم ڈرائیور کے ساتھ ویب ڈرایور مثال بنائیں
driver = uc.Chrome(options=chrome_options, seleniumwire_options=proxy_options)

driver.get(constructed_url)

try:
   element = WebDriverWait(driver, 20).until(
       EC.presence_of_element_located((By.XPATH, "//div[@class='css-175oi2r r-1mmae3n r-1e084wi r-13qz1uu']"))
   )
except Exception as err:
   print(f'WebDriver Wait Error: Most likely Network TimeOut: Details\n{err}')
   driver.quit()

# سائن ان کریں
if element:
   username_field = driver.find_element(By.XPATH,
                                        "//input[@class='r-30o5oe r-1dz5y72 r-13qz1uu r-1niwhzg r-17gur6a r-1yadl64 r-deolkf r-homxoj r-poiln3 r-7cikom r-1ny4l3l r-t60dpp r-fdjqy7']")
   username_field.send_keys(x_username)
   username_field.send_keys(Keys.ENTER)

   password_field = WebDriverWait(driver, 10).until(
       EC.presence_of_element_located((By.XPATH,
                                       "//input[@class='r-30o5oe r-1dz5y72 r-13qz1uu r-1niwhzg r-17gur6a r-1yadl64 r-deolkf r-homxoj r-poiln3 r-7cikom r-1ny4l3l r-t60dpp r-fdjqy7']"))
   )
   password_field.send_keys(x_password)
   password_field.send_keys(Keys.ENTER)

   print("Sign In Successful...\n")

   sleep(10)

results = []


# کھرچنی
def scrape():
   display_names = driver.find_elements(By.XPATH,
                                        '//*[@class="css-175oi2r r-1wbh5a2 r-dnmrzs r-1ny4l3l r-1awozwy r-18u37iz"]/div[1]/div/a/div/div[1]/span/span')
   usernames = driver.find_elements(By.XPATH,
                                    '//*[@class="css-175oi2r r-1wbh5a2 r-dnmrzs r-1ny4l3l r-1awozwy r-18u37iz"]/div[2]/div/div[1]/a/div/span')
   posts = driver.find_elements(By.XPATH,
                                '//*[@class="css-146c3p1 r-8akbws r-krxsd3 r-dnmrzs r-1udh08x r-bcqeeo r-1ttztb7 r-qvutc0 r-37j5jr r-a023e6 r-rjixqe r-16dba41 r-bnwqim"]/span')
   comments = driver.find_elements(By.XPATH,
                                   '//*[@class="css-175oi2r r-1kbdv8c r-18u37iz r-1wtj0ep r-1ye8kvj r-1s2bzr4"]/div[1]/button/div/div[2]/span/span/span')
   retweets = driver.find_elements(By.XPATH,
                                   '//*[@class="css-175oi2r r-1kbdv8c r-18u37iz r-1wtj0ep r-1ye8kvj r-1s2bzr4"]/div[2]/button/div/div[2]/span/span/span')
   likes = driver.find_elements(By.XPATH,
                                '//*[@class="css-175oi2r r-1kbdv8c r-18u37iz r-1wtj0ep r-1ye8kvj r-1s2bzr4"]/div[3]/button/div/div[2]/span/span/span')
   impressions = driver.find_elements(By.XPATH,
                                      '//*[@class="css-175oi2r r-1kbdv8c r-18u37iz r-1wtj0ep r-1ye8kvj r-1s2bzr4"]/div[4]/a/div/div[2]/span/span/span')

   min_length = min(len(display_names), len(usernames), len(posts), len(comments), len(retweets), len(likes),
                    len(impressions))

   for each in range(min_length):
       results.append({
           'Username': usernames[each].text,
           'displayName': display_names[each].text,
           'Post': posts[each].text.rstrip("Show more"),
           'Comments': 0 if comments[each].text == "" else convert_to_numeric(comments[each].text),
           'Retweets': 0 if retweets[each].text == "" else convert_to_numeric(retweets[each].text),
           'Likes': 0 if likes[each].text == "" else convert_to_numeric(likes[each].text),
           'Impressions': 0 if impressions[each].text == "" else convert_to_numeric(impressions[each].text)
       })


def reorder_json_by_impressions(json_data):
   # نزول ترتیب میں 'تاثرات' پر مبنی JSON لسٹ کو جگہ جگہ ترتیب دیں
   json_data.sort(key=lambda x: int(x['Impressions']), reverse=True)


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


def convert_to_numeric(value):
   multipliers = {'K': 10 ** 3, 'M': 10 ** 6, 'B': 10 ** 9}

   try:
       if value[-1] in multipliers:
           return int(float(value[:-1]) * multipliers[value[-1]])
       else:
           return int(value)
   except ValueError:
       # اس معاملے کو سنبھالیں جہاں تبادلوں میں ناکام ہوجاتا ہے
       return None


actions = ActionChains(driver)
for i in range(5):
   actions.send_keys(Keys.END).perform()
   sleep(5)
   scrape()

reorder_json_by_impressions(results)
organize_write_data(results)

print(f"Scraping Information on {search_keyword} is done.")

driver.quit()

[
  {
    "Username": "@LindaEvelyn_N",
    "displayName": "Linda Evelyn Namulindwa",
    "Post": "Still getting used to Ugandan local foods so I had Glovo deliver me a KFC Streetwise Spicy rice meal (2 pcs of chicken & jollof rice at Ugx 18,000)\n\nNot only was it fast but it also accepts all payment methods.\n\n#GlovoDeliversKFC\n#ItsFingerLinkingGood",
    "Comments": 105,
    "Retweets": 148,
    "Likes": 1500,
    "Impressions": 66000
  },
  {
    "Username": "@GymCheff",
    "displayName": "The Gym Chef",
    "Post": "Delicious High Protein KFC Zinger Rice Box!",
    "Comments": 1,
    "Retweets": 68,
    "Likes": 363,
    "Impressions": 49000
  }
]