ازگر کا استعمال کرتے ہوئے ییلپ کو کھرچنے کا طریقہ

pip install requests
pip install lxml

import requests

# Yelp search page URL
url = "https://www.yelp.com/search?find_desc=restaurants&find_loc=San+Francisco%2C+CA"

# Send a GET request to fetch the HTML content
response = requests.get(url)

# Check if the request was successful
if response.status_code == 200:
    print("Successfully fetched the page content")
else:
    print("Failed to retrieve the page content")

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': '"Not)A;Brand";v="99", "Google Chrome";v="127", "Chromium";v="127"',
    '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/127.0.0.0 Safari/537.36',
}

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

proxies = {
    'http': 'http://username:password@proxy-server:port',
    'https': 'https://username:password@proxy-server:port'
}

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

from lxml import html

# LXML کا استعمال کرتے ہوئے HTML مواد کی تجزیہ کریں
parser = html.fromstring(response.content)

# Extract individual restaurant elements
elements = parser.xpath('//div[@data-testid="serp-ia-card"]')[2:-1]

restaurants_data = []

# Iterate over each restaurant element
for element in elements:
    # Extract the restaurant name
    name = element.xpath('.//div[@class="businessName__09f24__HG_pC y-css-ohs7lg"]/div/h3/a/text()')[0]

    # Extract the restaurant URL
    url = element.xpath('.//div[@class="businessName__09f24__HG_pC y-css-ohs7lg"]/div/h3/a/@href')[0]

    # Extract the cuisines
    cuisines = element.xpath('.//div[@class="priceCategory__09f24___4Wsg iaPriceCategory__09f24__x9YrM y-css-2hdccn"]/div/div/div/a/button/span/text()')

    # Extract the rating
    rating = element.xpath('.//div[@class="y-css-9tnml4"]/@aria-label')[0]

    # Create a dictionary to store the data
    restaurant_info = {
        "name": name,
        "url": url,
        "cuisines": cuisines,
        "rating": rating
    }

    # Add the restaurant info to the list
    restaurants_data.append(restaurant_info)

import json

# Save the data to a JSON file
with open('yelp_restaurants.json', 'w') as f:
    json.dump(restaurants_data, f, indent=4)

print("Data extraction complete. Saved to yelp_restaurants.json")

import requests
from lxml import html
import json

# Yelp search page URL
url = "https://www.yelp.com/search?find_desc=restaurants&find_loc=San+Francisco%2C+CA"

# Set up headers to mimic a browser request
headers = {
    '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',
    'Accept-Language': 'en-US,en;q=0.5'
}

# Set up proxies if required
proxies = {
    'http': 'http://username:password@proxy-server:port',
    'https': 'https://username:password@proxy-server:port'
}

# Send a GET request to fetch the HTML content
response = requests.get(url, headers=headers, proxies=proxies)

# Check if the request was successful
if response.status_code == 200:
    print("Successfully fetched the page content")
else:
    print("Failed to retrieve the page content")

# Parse the HTML content using lxml
parser = html.fromstring(response.content)

# Extract individual restaurant elements
elements = parser.xpath('//div[@data-testid="serp-ia-card"]')[2:-1]

# Initialize a list to hold the extracted data
restaurants_data = []

# Iterate over each restaurant element
for element in elements:
    # Extract the restaurant name
    name = element.xpath('.//div[@class="businessName__09f24__HG_pC y-css-ohs7lg"]/div/h3/a/text()')[0]

    # Extract the restaurant URL
    url = element.xpath('.//div[@class="businessName__09f24__HG_pC y-css-ohs7lg"]/div/h3/a/@href')[0]

    # Extract the cuisines
    cuisines = element.xpath('.//div[@class="priceCategory__09f24___4Wsg iaPriceCategory__09f24__x9YrM y-css-2hdccn"]/div/div/div/a/button/span/text()')

    # Extract the rating
    rating = element.xpath('.//div[@class="y-css-9tnml4"]/@aria-label')[0]

    # Create a dictionary to store the data
    restaurant_info = {
        "name": name,
        "url": url,
        "cuisines": cuisines,
        "rating": rating
    }

    # Add the restaurant info to the list
    restaurants_data.append(restaurant_info)

# Save the data to a JSON file
with open('yelp_restaurants.json', 'w') as f:
    json.dump(restaurants_data, f, indent=4)

print("Data extraction complete. Saved to yelp_restaurants.json")