ازگر کا استعمال کرتے ہوئے ایمیزون جائزوں کو کھرچنے کے لئے رہنما

pip install requests
pip install beautifulsoup4

import requests

url = "https://www.amazon.com/Portable-Mechanical-Keyboard-MageGee-Backlit/product-reviews/B098LG3N6R/ref=cm_cr_dp_d_show_all_btm?ie=UTF8&reviewerType=all_reviews"

# Example of a proxy provided by the proxy service
proxy = {
    'http': 'http://your_proxy_ip:your_proxy_port',
    'https': 'https://your_proxy_ip:your_proxy_port'
}

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',
}

# Send HTTP GET request to the URL with headers and proxy
try:
    response = requests.get(url, headers=headers, proxies=proxy, timeout=10)
    response.raise_for_status()  # Raise an exception for bad response status
except requests.exceptions.RequestException as e:
    print(f"Error: {e}")

from bs4 import BeautifulSoup

soup = BeautifulSoup(response.content, 'html.parser')

# Extracting common product details
product_url = soup.find('a', {'data-hook': 'product-link'}).get('href', '')
product_title = soup.find('a', {'data-hook': 'product-link'}).get_text(strip=True)
total_rating = soup.find('span', {'data-hook': 'rating-out-of-text'}).get_text(strip=True)

reviews = []
review_elements = soup.find_all('div', {'data-hook': 'review'})
for review in review_elements:
    author_name = review.find('span', class_='a-profile-name').get_text(strip=True)
    rating_given = review.find('i', class_='review-rating').get_text(strip=True)
    comment = review.find('span', class_='review-text').get_text(strip=True)

    reviews.append({
        'Product URL': product_url,
        'Product Title': product_title,
        'Total Rating': total_rating,
        'Author': author_name,
        'Rating': rating_given,
        'Comment': comment,
    })

import csv

# Define CSV file path
csv_file = 'amazon_reviews.csv'

# Define CSV fieldnames
fieldnames = ['Product URL', 'Product Title', 'Total Rating', 'Author', 'Rating', 'Comment']

# Writing data to CSV file
with open(csv_file, mode='w', newline='', encoding='utf-8') as file:
    writer = csv.DictWriter(file, fieldnames=fieldnames)
    writer.writeheader()
    for review in reviews:
        writer.writerow(review)

print(f"Data saved to {csv_file}")

import requests
from bs4 import BeautifulSoup
import csv
import urllib3

urllib3.disable_warnings()

# URL of the Amazon product reviews page
url = "https://www.amazon.com/Portable-Mechanical-Keyboard-MageGee-Backlit/product-reviews/B098LG3N6R/ref=cm_cr_dp_d_show_all_btm?ie=UTF8&reviewerType=all_reviews"

# Proxy provided by the proxy service with IP-authorization
path_proxy = 'your_proxy_ip:your_proxy_port'
proxy = {
   'http': f'http://{path_proxy}',
   'https': f'https://{path_proxy}'
}

# Headers for the HTTP 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-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',
}

# Send HTTP GET request to the URL with headers and handle exceptions
try:
   response = requests.get(url, headers=headers, timeout=10, proxies=proxy, verify=False)
   response.raise_for_status()  # Raise an exception for bad response status
except requests.exceptions.RequestException as e:
   print(f"Error: {e}")

# Parse the HTML content using BeautifulSoup
soup = BeautifulSoup(response.content, 'html.parser')

# Extracting common product details
product_url = soup.find('a', {'data-hook': 'product-link'}).get('href', '')  # Extract product URL
product_title = soup.find('a', {'data-hook': 'product-link'}).get_text(strip=True)  # Extract product title
total_rating = soup.find('span', {'data-hook': 'rating-out-of-text'}).get_text(strip=True)  # Extract total rating

# Extracting individual reviews
reviews = []
review_elements = soup.find_all('div', {'data-hook': 'review'})
for review in review_elements:
   author_name = review.find('span', class_='a-profile-name').get_text(strip=True)  # Extract author name
   rating_given = review.find('i', class_='review-rating').get_text(strip=True)  # Extract rating given
   comment = review.find('span', class_='review-text').get_text(strip=True)  # Extract review comment

   # Store each review in a dictionary
   reviews.append({
       'Product URL': product_url,
       'Product Title': product_title,
       'Total Rating': total_rating,
       'Author': author_name,
       'Rating': rating_given,
       'Comment': comment,
   })

# Define CSV file path
csv_file = 'amazon_reviews.csv'

# Define CSV fieldnames
fieldnames = ['Product URL', 'Product Title', 'Total Rating', 'Author', 'Rating', 'Comment']

# Writing data to CSV file
with open(csv_file, mode='w', newline='', encoding='utf-8') as file:
   writer = csv.DictWriter(file, fieldnames=fieldnames)
   writer.writeheader()
   for review in reviews:
       writer.writerow(review)

# Print confirmation message
print(f"Data saved to {csv_file}")