ازگر کے ساتھ ای کامرس ویب سائٹوں کو کھرچنے کا طریقہ

pip install requests
pip install lxml

import requests

# List of product URLs to scrape
urls = [
    "https://www.costco.com/kirkland-signature-men's-sneaker.product.4000216649.html",
    "https://www.costco.com/adidas-ladies'-puremotion-shoe.product.4000177646.html"
]

headers = {
    'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
    'accept-language': 'en-US,en;q=0.9',
    'cache-control': 'no-cache',
    'dnt': '1',
    'pragma': 'no-cache',
    'sec-ch-ua': '"Not/A)Brand";v="99", "Google Chrome";v="91", "Chromium";v="91"',
    'sec-ch-ua-mobile': '?0',
    'sec-fetch-dest': 'document',
    'sec-fetch-mode': 'navigate',
    'sec-fetch-site': 'same-origin',
    'sec-fetch-user': '?1',
    'upgrade-insecure-requests': '1',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
}

# Loop through each URL and send a GET request
for url in urls:
    response = requests.get(url, headers=headers)
    if response.status_code == 200:
        html_content = response.text
        # Further processing will be added in subsequent steps
    else:
        print(f"Failed to retrieve {url}. Status code: {response.status_code}")

from lxml import html

# List to store scraped data
scraped_data = []

# Loop through each URL and send a GET request
for url in urls:
    response = requests.get(url)
    if response.status_code == 200:
        html_content = response.content
        # Parse HTML content with lxml
        tree = html.fromstring(html_content)
        
        # Extract data using XPath

        product_name = tree.xpath('//h1[@automation-id="productName"]/text()')[0].strip()
        product_feature = tree.xpath('//ul[@class="pdp-features"]//li//text()')
        product_brand = tree.xpath('//div[@itemprop="brand"]/text()')[0].strip()
        
        # Append extracted data to the list
        scraped_data.append({'Product Name': product_name, 'Product Feature': product_feature, 'Brand': product_brand})
    else:
        print(f"Failed to retrieve {url}. Status code: {response.status_code}")

# Print the scraped data
for item in scraped_data:
    print(item)

proxies = {
    'http': 'http://your_proxy_ip:your_proxy_port',
    'https': 'https://your_proxy_ip:your_proxy_port'
}
response = requests.get(url, proxies=proxies)

import random

user_agents = [
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
    # Add more user agents as needed
]

headers['user-agent'] = random.choice(user_agents)

response = requests.get(url, headers=headers)

import csv

csv_file = 'costco_products.csv'
fieldnames = ['Product Name', 'Product Feature', 'Brand']

# Writing data to CSV file
try:
    with open(csv_file, mode='w', newline='', encoding='utf-8') as file:
        writer = csv.DictWriter(file, fieldnames=fieldnames)
        writer.writeheader()
        for item in scraped_data:
            writer.writerow(item)
    print(f"Data saved to {csv_file}")
except IOError:
    print(f"Error occurred while writing data to {csv_file}")

import requests
import urllib3
from lxml import html
import csv
import random
import ssl

ssl._create_default_https_context = ssl._create_stdlib_context
urllib3.disable_warnings()

# List of product URLs to scrape
urls = [
   "https://www.costco.com/kirkland-signature-men's-sneaker.product.4000216649.html",
   "https://www.costco.com/adidas-ladies'-puremotion-shoe.product.4000177646.html"
]

# headers
headers = {
   'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
   'accept-language': 'en-US,en;q=0.9',
   'cache-control': 'no-cache',
   'dnt': '1',
   'pragma': 'no-cache',
   'sec-ch-ua': '"Not/A)Brand";v="99", "Google Chrome";v="91", "Chromium";v="91"',
   'sec-ch-ua-mobile': '?0',
   'sec-fetch-dest': 'document',
   'sec-fetch-mode': 'navigate',
   'sec-fetch-site': 'same-origin',
   'sec-fetch-user': '?1',
   'upgrade-insecure-requests': '1',
   'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
}

# List of user agents for rotating requests
user_agents = [
   'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
   'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
   # Add more user agents as needed
]


# List of proxies for rotating requests
proxies = [
    {'http': 'http://your_proxy_ip:your_proxy_port', 'https': 'https://your_proxy_ip:your_proxy_port'},
    {'http': 'http://your_proxy_ip2:your_proxy_port2', 'https': 'https://your_proxy_ip2:your_proxy_port2'},
    # Add more proxies as needed
]

# List to store scraped data
scraped_data = []

# Loop through each URL and send a GET request
for url in urls:
   # Choose a random user agent for the request headers
   headers['user-agent'] = random.choice(user_agents)
   # Choose a random proxy for the request
   proxy = random.choice(proxies)

   # Send HTTP GET request to the URL with headers and proxy
   response = requests.get(url, headers=headers, proxies=proxy, verify=False)
   if response.status_code == 200:
       # Store the HTML content from the response
       html_content = response.content
       # Parse HTML content with lxml
       tree = html.fromstring(html_content)

       # Extract data using XPath
       product_name = tree.xpath('//h1[@automation-id="productName"]/text()')[0].strip()
       product_feature = tree.xpath('//ul[@class="pdp-features"]//li//text()')
       product_brand = tree.xpath('//div[@itemprop="brand"]/text()')[0].strip()

       # Append extracted data to the list
       scraped_data.append({'Product Name': product_name, 'Product Feature': product_feature, 'Brand': product_brand})
   else:
       # Print error message if request fails
       print(f"Failed to retrieve {url}. Status code: {response.status_code}")

# CSV file setup
csv_file = 'costco_products.csv'
fieldnames = ['Product Name', 'Product Feature', 'Brand']

# Writing data to CSV file
try:
   with open(csv_file, mode='w', newline='', encoding='utf-8') as file:
       writer = csv.DictWriter(file, fieldnames=fieldnames)
       writer.writeheader()
       for item in scraped_data:
           writer.writerow(item)
   print(f"Data saved to {csv_file}")
except IOError:
   # Print error message if writing to file fails
   print(f"Error occurred while writing data to {csv_file}")