ویب ڈیٹا کو کھرچتے ہوئے پراکسیوں کو کیسے گھومائیں

pip install requests beautifulSoup4 lxml

import requests
import threading
from requests.auth import HTTPProxyAuth
import json
from bs4 import BeautifulSoup
import lxml
import time

url_to_scrape = "https://books.toscrape.com"
valid_proxies = []
book_names = []
book_price = []
book_availability = []
next_button_link = ""

[
  {
    "proxy_address": "XX.X.XX.X:XX",
    "proxy_username": "",
    "proxy_password": ""
  },

  {
    "proxy_address": "XX.X.XX.X:XX",
    "proxy_username": "",
    "proxy_password": ""
  },
  {
    "proxy_address": "XX.X.XX.X:XX",
    "proxy_username": "",
    "proxy_password": ""
  },
  {
    "proxy_address": "XX.X.XX.X:XX",
    "proxy_username": "",
    "proxy_password": ""
  }
]

def verify_proxies(proxy:dict):
    try:
        if proxy['proxy_username'] != "" and  proxy['proxy_password'] != "":
            proxy_auth = HTTPProxyAuth(proxy['proxy_username'], proxy['proxy_password'])
            res = requests.get(
                url_to_scrape,
                auth = proxy_auth,
                proxies={
                "http" : proxy['proxy_address']
                }
            )
        else:
            res = requests.get(url_to_scrape, proxies={
                "http" : proxy['proxy_address'],
            })
        
        if res.status_code == 200:
            valid_proxies.append(proxy)
            print(f"Proxy Validated: {proxy['proxy_address']}")
            
    except:
        print("Proxy Invalidated, Moving on")

def request_function(url, proxy):
    try:
        if proxy['proxy_username'] != "" and  proxy['proxy_password'] != "":
            proxy_auth = HTTPProxyAuth(proxy['proxy_username'], proxy['proxy_password'])
            response = requests.get(
                url,
                auth = proxy_auth,
                proxies={
                "http" : proxy['proxy_address']
                }
            )
        else:
            response = requests.get(url, proxies={
                "http" : proxy['proxy_address']
            })
        
        if response.status_code == 200:
            return response.text

    except Exception as err:
        print(f"Switching Proxies, URL access was unsuccessful: {err}")
        return None

def data_extract(response):
    soup = BeautifulSoup(response, "lxml")
    books = soup.find_all("li", class_="col-xs-6 col-sm-4 col-md-3 col-lg-3")
    next_button_link = soup.find("li", class_="next").find('a').get('href')
    next_button_link=f"{url_to_scrape}/{next_button_link}" if "catalogue" in next_button_link else f"{url_to_scrape}/catalogue/{next_button_link}"

    for each in books:
        book_names.append(each.find("img").get("alt"))
        book_price.append(each.find("p", class_="price_color").text)
        book_availability.append(each.find("p", class_="instock availability").text.strip())

    return next_button_link

with open("proxy-list.json") as json_file:
    proxies = json.load(json_file)
    for each in proxies:
        threading.Thread(target=verify_proxies, args=(each, )).start() 


time.sleep(4)

for i in range(len(valid_proxies)):
    response = request_function(url_to_scrape, valid_proxies[i])
    if response != None:
        next_button_link = data_extract(response)
        break
    else:
        continue

for proxy in valid_proxies:
   print(f"Using Proxy: {proxy['proxy_address']}")
   response = request_function(next_button_link, proxy)
   if response is not None:
       next_button_link = data_extract(response)
   else:
       continue


for each in range(len(book_names)):
    print(f"No {each+1}: Book Name: {book_names[each]} Book Price: {book_price[each]} and Availability {book_availability[each]}")

import requests
import threading
from requests.auth import HTTPProxyAuth
import json
from bs4 import BeautifulSoup
import time

url_to_scrape = "https://books.toscrape.com"
valid_proxies = []
book_names = []
book_price = []
book_availability = []
next_button_link = ""


def verify_proxies(proxy: dict):
   try:
       if proxy['proxy_username'] != "" and proxy['proxy_password'] != "":
           proxy_auth = HTTPProxyAuth(proxy['proxy_username'], proxy['proxy_password'])
           res = requests.get(
               url_to_scrape,
               auth=proxy_auth,
               proxies={
                   "http": proxy['proxy_address'],
               }
           )
       else:
           res = requests.get(url_to_scrape, proxies={
               "http": proxy['proxy_address'],
           })

       if res.status_code == 200:
           valid_proxies.append(proxy)
           print(f"Proxy Validated: {proxy['proxy_address']}")

   except:
       print("Proxy Invalidated, Moving on")


# کسی صفحے کے HTML عنصر کو بازیافت کرتا ہے
def request_function(url, proxy):
   try:
       if proxy['proxy_username'] != "" and proxy['proxy_password'] != "":
           proxy_auth = HTTPProxyAuth(proxy['proxy_username'], proxy['proxy_password'])
           response = requests.get(
               url,
               auth=proxy_auth,
               proxies={
                   "http": proxy['proxy_address'],
               }
           )
       else:
           response = requests.get(url, proxies={
               "http": proxy['proxy_address'],
           })

       if response.status_code == 200:
           return response.text

   except Exception as err:
       print(f"Switching Proxies, URL access was unsuccessful: {err}")
       return None


# سکریپنگ
def data_extract(response):
   soup = BeautifulSoup(response, "lxml")
   books = soup.find_all("li", class_="col-xs-6 col-sm-4 col-md-3 col-lg-3")
   next_button_link = soup.find("li", class_="next").find('a').get('href')
   next_button_link = f"{url_to_scrape}/{next_button_link}" if "catalogue" in next_button_link else f"{url_to_scrape}/catalogue/{next_button_link}"

   for each in books:
       book_names.append(each.find("img").get("alt"))
       book_price.append(each.find("p", class_="price_color").text)
       book_availability.append(each.find("p", class_="instock availability").text.strip())

   return next_button_link


# Get proxy from JSON
with open("proxy-list.json") as json_file:
   proxies = json.load(json_file)
   for each in proxies:
       threading.Thread(target=verify_proxies, args=(each,)).start()

time.sleep(4)

for i in range(len(valid_proxies)):
   response = request_function(url_to_scrape, valid_proxies[i])
   if response is not None:
       next_button_link = data_extract(response)
       break
   else:
       continue

for proxy in valid_proxies:
   print(f"Using Proxy: {proxy['proxy_address']}")
   response = request_function(next_button_link, proxy)
   if response is not None:
       next_button_link = data_extract(response)
   else:
       continue

for each in range(len(book_names)):
   print(
       f"No {each + 1}: Book Name: {book_names[each]} Book Price: {book_price[each]} and Availability {book_availability[each]}")