ازگر کا استعمال کرتے ہوئے Aliexpress ڈیٹا کو کھرچنے کا طریقہ

# Install Playwright
pip install playwright


# Install Requests
pip install requests


# Install lxml for parsing HTML
pip install lxml


# Install Pandas for data manipulation and saving
pip install pandas

playwright install

from playwright.async_api import async_playwright

async def get_page_content(url):
    async with async_playwright() as p:
        # Launch the browser with a proxy if needed (can be removed if not using proxy)
        browser = await p.firefox.launch(
            headless=False,
            proxy={"server": '', 'username': '', 'password': ''}
        )
        page = await browser.new_page()
        await page.goto(url, timeout=60000)

        # Extract page content
        content = await page.content()
        await browser.close()
        
        return content

# Example URL
url = 'https://www.aliexpress.com/item/3256805354456256.html'

from lxml.html import fromstring

def extract_product_data(content):
    parser = fromstring(content)
    
    # Extract product details using XPath
    title = parser.xpath('//h1[@data-pl="product-title"]/text()')[0].strip()
    price = parser.xpath('//div[@class="price--current--I3Zeidd product-price-current"]/span/text()')[0].strip()
    rating = ' '.join(parser.xpath('//a[@class="reviewer--rating--xrWWFzx"]/strong/text()')).strip()
    total_reviews = parser.xpath('//a[@class="reviewer--reviews--cx7Zs_V"]/text()')[0].strip()
    sold_count = parser.xpath('//span[@class="reviewer--sold--ytPeoEy"]/text()')[0].strip()

    product_data = {
        'title': title,
        'price': price,
        'rating': rating,
        'total_reviews': total_reviews,
        'sold_count': sold_count
    }

    return product_data

import requests

def extract_product_id(url):
    # Extract product ID from the URL
    product_id = url.split('/')[-1].split('.')[0]
    return product_id

def scrape_reviews(product_id, page_num=1, page_size=10):
    headers = {
        'accept': 'application/json, text/plain, */*',
        'accept-language': 'en-IN,en;q=0.9',
        'referer': f'https://www.aliexpress.com/item/{product_id}.html',
        'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36',
    }

    params = {
        'productId': product_id,
        'lang': 'en_US',
        'country': 'US',
        'page': str(page_num),
        'pageSize': str(page_size),
        'filter': 'all',
        'sort': 'complex_default',
    }

    response = requests.get('https://feedback.aliexpress.com/pc/searchEvaluation.do', params=params, headers=headers)
    reviews = response.json()['data']['evaViewList']

    # Extract review text only
    review_texts = [review['buyerFeedback'] for review in reviews]
    
    return review_texts

import pandas as pd

def save_to_csv(product_data, reviews, product_id):
    # Save product details to CSV
    df_product = pd.DataFrame([product_data])
    df_product.to_csv(f'product_{product_id}_data.csv', index=False)

    # Save reviews to CSV
    df_reviews = pd.DataFrame({'reviews': reviews})
    df_reviews.to_csv(f'product_{product_id}_reviews.csv', index=False)
    
    print(f"Data saved for product {product_id}.")

# Extract product ID from the URL
def extract_product_id(url):
    return url.split('/')[-1].split('.')[0]

from playwright.async_api import async_playwright
from lxml.html import fromstring
import requests
import pandas as pd

# Get page content using Playwright
async def get_page_content(url):
    async with async_playwright() as p:
        browser = await p.firefox.launch(
            headless=False,
            proxy={"server": '', 'username': '', 'password': ''}
        )
        page = await browser.new_page()
        await page.goto(url, timeout=60000)
        content = await page.content()
        await browser.close()
        return content

# Extract product data
def extract_product_data(content):
    parser = fromstring(content)
    title = parser.xpath('//h1[@data-pl="product-title"]/text()')[0].strip()
    price = parser.xpath('//div[@class="price--current--I3Zeidd product-price-current"]/span/text()')[0].strip()
    rating = ' '.join(parser.xpath('//a[@class="reviewer--rating--xrWWFzx"]/strong/text()')).strip()
    total_reviews = parser.xpath('//a[@class="reviewer--reviews--cx7Zs_V"]/text()')[0].strip()
    sold_count = parser.xpath('//span[@class="reviewer--sold--ytPeoEy"]/text()')[0].strip()

    return {
        'title': title,
        'price': price,
        'rating': rating,
        'total_reviews': total_reviews,
        'sold_count': sold_count
    }

# Extract product ID from the URL
def extract_product_id(url):
    return url.split('/')[-1].split('.')[0]

# Scrape reviews
def scrape_reviews(product_id, page_num=1, page_size=10):
    headers = {
        'accept': 'application/json, text/plain, */*',
        'referer': f'https://www.aliexpress.com/item/{product_id}.html',
        'user-agent': 'Mozilla/5.0'
    }
    params = {
        'productId': product_id,
        'lang': 'en_US',
        'page': str(page_num),
        'pageSize': str(page_size),
    }
    response = requests.get('https://feedback.aliexpress.com/pc/searchEvaluation.do', params=params, headers=headers)
    reviews = response.json()['data']['evaViewList']
    return [review['buyerFeedback'] for review in reviews]

# Save product data and reviews to CSV
def save_to_csv(product_data, reviews, product_id):
    pd.DataFrame([product_data]).to_csv(f'product_{product_id}_data.csv', index=False)
    pd.DataFrame({'reviews': reviews}).to_csv(f'product_{product_id}_reviews.csv', index=False)
    print(f'Saved into: product_{product_id}_data.csv')
    print(f'Saved into: product_{product_id}_reviews.csv')

# Main function
async def main(url):
    content = await get_page_content(url)
    product_data = extract_product_data(content)
    product_id = extract_product_id(url)
    reviews = scrape_reviews(product_id)
    save_to_csv(product_data, reviews, product_id)

# Run the scraper
import asyncio
url = 'https://www.aliexpress.com/item/3256805354456256.html'
asyncio.run(main(url))