ازگر کا استعمال کرتے ہوئے بکنگ ڈاٹ کام کو کھرچنے کا طریقہ

pip install requests lxml

import requests
from lxml.html import fromstring

urls_list = ["https links"]

for url in urls_list:
    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': '"Chromium";v="130", "Google Chrome";v="130", "Not?A_Brand";v="99"',
        '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/130.0.0.0 Safari/537.36',
    }

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

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

parser = fromstring(response.text)

# Extract embedded JSON data
embeded_jsons = parser.xpath('//script[@type="application/ld+json"]/text()')
json_data = json.loads(embeded_jsons[0])

name = json_data['name']
location = json_data['hasMap']
priceRange = json_data['priceRange']
description = json_data['description']
url = json_data['url']
ratingValue = json_data['aggregateRating']['ratingValue']
reviewCount = json_data['aggregateRating']['reviewCount']
type_ = json_data['@type']
postalCode = json_data['address']['postalCode']
addressLocality = json_data['address']['addressLocality']
addressCountry = json_data['address']['addressCountry']
addressRegion = json_data['address']['addressRegion']
streetAddress = json_data['address']['streetAddress']
image_url = json_data['image']
room_types = parser.xpath("//a[contains(@href, '#RD')]/span/text()")

# Append the data to the all_data list
all_data.append({
    "Name": name,
    "Location": location,
    "Price Range": priceRange,
    "Rating": ratingValue,
    "Review Count": reviewCount,
    "Type": type_,
    "Postal Code": postalCode,
    "Address Locality": addressLocality,
    "Country": addressCountry,
    "Region": addressRegion,
    "Street Address": streetAddress,
    "URL": url,
    "Image URL": image_url,
    "Room Types": room_types
})

# After all URLs are processed, write the data into a CSV file
with open('booking_data.csv', 'w', newline='') as csvfile:
    fieldnames = ["Name", "Location", "Price Range", "Rating", "Review Count", "Type", "Postal Code", 
                  "Address Locality", "Country", "Region", "Street Address", "URL", "Image URL", "Room Types"]
    
    writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
    
    # Write the header
    writer.writeheader()
    
    # Write the rows of data
    writer.writerows(all_data)

import requests
from lxml.html import fromstring
import json
import csv

# List of hotel URLs to scrape
urls_list = [
    "Https link", 
    "Https link"
]

# Initialize an empty list to hold all the scraped data
all_data = []

proxies = {
    'http': ''
}

# Loop through each URL to scrape data
for url in urls_list:
    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': '"Chromium";v="130", "Google Chrome";v="130", "Not?A_Brand";v="99"',
        '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/130.0.0.0 Safari/537.36',
    }

    # Sending the request to the website
    response = requests.get(url, headers=headers, proxies=proxies)
    
    # Parsing the HTML content
    parser = fromstring(response.text)
    
    # Extract embedded JSON data
    embeded_jsons = parser.xpath('//script[@type="application/ld+json"]/text()')
    json_data = json.loads(embeded_jsons[0])

    # Extract all hotel details from JSON
    name = json_data['name']
    location = json_data['hasMap']
    priceRange = json_data['priceRange']
    description = json_data['description']
    url = json_data['url']
    ratingValue = json_data['aggregateRating']['ratingValue']
    reviewCount = json_data['aggregateRating']['reviewCount']
    type_ = json_data['@type']
    postalCode = json_data['address']['postalCode']
    addressLocality = json_data['address']['addressLocality']
    addressCountry = json_data['address']['addressCountry']
    addressRegion = json_data['address']['addressRegion']
    streetAddress = json_data['address']['streetAddress']
    image_url = json_data['image']

    room_types = parser.xpath("//a[contains(@href, '#RD')]/span/text()")
    
    # Append the data to the all_data list
    all_data.append({
        "Name": name,
        "Location": location,
        "Price Range": priceRange,
        "Rating": ratingValue,
        "Review Count": reviewCount,
        "Type": type_,
        "Postal Code": postalCode,
        "Address Locality": addressLocality,
        "Country": addressCountry,
        "Region": addressRegion,
        "Street Address": streetAddress,
        "URL": url,
        "Image URL": image_url,
        "Room Types": room_types
    })

# After all URLs are processed, write the data into a CSV file
with open('booking_data.csv', 'w', newline='') as csvfile:
    fieldnames = ["Name", "Location", "Price Range", "Rating", "Review Count", "Type", "Postal Code", 
                  "Address Locality", "Country", "Region", "Street Address", "URL", "Image URL", "Room Types"]
    
    writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
    
    # Write the header
    writer.writeheader()
    
    # Write the rows of data
    writer.writerows(all_data)

print("Data successfully saved to booking_data.csv")