ازگر کا استعمال کرتے ہوئے ای بے ڈیٹا کو کھرچنے کا طریقہ

pip install requests lxml pandas

import requests
from lxml.html import fromstring

# Define headers to simulate a real browser
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-IN,en;q=0.9',
    'cache-control': 'no-cache',
    'dnt': '1',
    'pragma': 'no-cache',
    'priority': 'u=0, i',
    'sec-ch-ua': '"Google Chrome";v="129", "Not=A?Brand";v="8", "Chromium";v="129"',
    'sec-ch-ua-mobile': '?0',
    'sec-ch-ua-platform': '"Linux"',
    'sec-fetch-dest': 'document',
    'sec-fetch-mode': 'navigate',
    'sec-fetch-site': 'none',
    'sec-fetch-user': '?1',
    'upgrade-insecure-requests': '1',
    'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36',
}

# Request parameters for the search query
params = {
    '_nkw': 'laptop',
}

# Send a request to the eBay listing page
listing_page_response = requests.get('https link', params=params, headers=headers)
listing_parser = fromstring(listing_page_response.text)

# Parse the listing page to extract product links
links = listing_parser.xpath('//div[@class="s-item__info clearfix"]/a[@_sp="p2351460.m1686.l7400"]/@href')

# Output a sample of the links found
print("Product Links:", links[:5])  # Display the first five product links

product_data = []

for url in links:
    # Send a request to the product page
    product_page_response = requests.get(url, headers=headers)
    product_parser = fromstring(product_page_response.text)
    
    # Extract data using XPath
    try:
        product_title = product_parser.xpath('//h1[@class="x-item-title__mainTitle"]/span/text()')[0]
        price = product_parser.xpath('//div[@data-testid="x-price-primary"]/span/text()')[0]
        shipping_cost = product_parser.xpath('//div[@class="ux-labels-values col-12 ux-labels-values--shipping"]//div[@class="ux-labels-values__values-content"]/div/span/text()')[0]
        product_condition = product_parser.xpath('//div[@class="x-item-condition-text"]/div/span/span[2]/text()')[0]
        available_quantity = product_parser.xpath('//div[@class="x-quantity__availability"]/span/text()')[0]
        sold_quantity = product_parser.xpath('//div[@class="x-quantity__availability"]/span/text()')[1]
        payment_options = ', '.join(product_parser.xpath('//div[@class="ux-labels-values col-12 ux-labels-values__column-last-row ux-labels-values--payments"]/div[2]/div/div//span/@aria-label'))
        return_policy = product_parser.xpath('//div[@class="ux-layout-section ux-layout-section--returns"]//div[@class="ux-labels-values__values-content"]/div/span/text()')[0]
        
        # Store data in a dictionary
        product_info = {
            'Title': product_title,
            'Price': price,
            'Shipping Cost': shipping_cost,
            'Condition': product_condition,
            'Available Quantity': available_quantity,
            'Sold Quantity': sold_quantity,
            'Payment Options': payment_options,
            'Return Policy': return_policy,
        }
        product_data.append(product_info)
    
    except IndexError as e:
        print(f"An error occurred: {e}")

import pandas as pd

# Convert data to DataFrame
df = pd.DataFrame(product_data)

# Save to CSV
df.to_csv('ebay_product_data.csv', index=False)
print("Data saved to ebay_product_data.csv")

import requests
import random
from lxml.html import fromstring
import pandas as pd

useragents = ['Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36',
             'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36',
             'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36']

# Define headers for request
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-IN,en;q=0.9',
    'cache-control': 'no-cache',
    'dnt': '1',
    'pragma': 'no-cache',
    'priority': 'u=0, i',
    'sec-ch-ua': '"Google Chrome";v="129", "Not=A?Brand";v="8", "Chromium";v="129"',
    'sec-ch-ua-mobile': '?0',
    'sec-ch-ua-platform': '"Linux"',
    'sec-fetch-dest': 'document',
    'sec-fetch-mode': 'navigate',
    'sec-fetch-site': 'none',
    'sec-fetch-user': '?1',
    'upgrade-insecure-requests': '1',
    'user-agent': random.choice(useragents),
}

# Search query parameters
params = {'_nkw': 'laptop'}
proxies = {
    'http': 'IP:PORT',
    'https': 'IP:PORT'
}

# Fetch the listing page
listing_page_response = requests.get('https://www.ebay.com/sch/i.html', params=params, headers=headers, proxies=proxies)
listing_parser = fromstring(listing_page_response.text)
links = listing_parser.xpath('//div[@class="s-item__info clearfix"]/a[@_sp="p2351460.m1686.l7400"]/@href')

# Extract product data
product_data = []
for url in links:
    product_page_response = requests.get(url, headers=headers, proxies=proxies)
    product_parser = fromstring(product_page_response.text)
    try:
        product_info = {
            'Title': product_parser.xpath('//h1[@class="x-item-title__mainTitle"]/span/text()')[0],
            'Price': product_parser.xpath('//div[@data-testid="x-price-primary"]/span/text()')[0],
            'Shipping Cost': product_parser.xpath('//div[@class="ux-labels-values col-12 ux-labels-values--shipping"]//div[@class="ux-labels-values__values-content"]/div/span/text()')[0],
            'Condition': product_parser.xpath('//div[@class="x-item-condition-text"]/div/span/span[2]/text()')[0],
            'Available Quantity': product_parser.xpath('//div[@class="x-quantity__availability"]/span/text()')[0],
            'Sold Quantity': product_parser.xpath('//div[@class="x-quantity__availability"]/span/text()')[1],
            'Payment Options': ', '.join(product_parser.xpath('//div[@class="ux-labels-values col-12 ux-labels-values__column-last-row ux-labels-values--payments"]/div[2]/div/div//span/@aria-label')),
            'Return Policy': product_parser.xpath('//div[@class="ux-layout-section ux-layout-section--returns"]//div[@class="ux-labels-values__values-content"]/div/span/text()')[0]
        }
        product_data.append(product_info)
    except IndexError:
        continue

# Save to CSV
df = pd.DataFrame(product_data)
df.to_csv('ebay_product_data.csv', index=False)
print("Data saved to ebay_product_data.csv")