گوگل پروازوں کے لئے گائیڈ کے ساتھ رہنمائی کریں ڈیٹا سکریپنگ کے ساتھ

pip install playwright
Pip install lxml

playwright install chromium

From Location: //input[@aria-label="Where from?"]/@value
To Location: //input[@aria-label="Where to?"]/@value
Departure Date: //input[@placeholder="Departure"]/@value
Return Date: //input[@placeholder="Return"]/@value

Flight Elements: //li[@class="pIav2d"]
Airway: .//div[@class="sSHqwe tPgKwe ogfYpf"]/span/text()
Details: .//span[@class="mv1WYe"]/@aria-label
Departure Time: .//span[@aria-describedby="gEvJbfc1583"]/span/text()
Arrival Time: .//span[@aria-describedby="gEvJbfc1584"]/span/text()
Travel Time: .//div[@class="gvkrdb AdWm1c tPgKwe ogfYpf"]/text()
Price: .//div[@class="YMlIz FpEdX"]/span/text()

from playwright.sync_api import sync_playwright

# URL for the Google Flights search page
url = "https link"

def get_page_content(url):
    """Fetches the HTML content of the given URL using Playwright."""
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)  # Launch browser in headless mode
        context = browser.new_context()  # Create a new browser context
        page = context.new_page()  # Open a new page
        page.goto(url)  # Navigate to the specified URL
        content = page.content()  # Get the page content
        browser.close()  # Close the browser
    return content

# Fetch the page content
page_content = get_page_content(url)

from lxml import html

# Creating the parser
tree = html.fromstring(page_content)

# Extracting common flight details using XPath
from_location = tree.xpath('//input[@aria-label="Where from?"]/@value')[0]  # Get the 'from' location
to_location = tree.xpath('//input[@aria-label="Where to?"]/@value')[0]  # Get the 'to' location
departure_date = tree.xpath('//input[@placeholder="Departure"]/@value')[0]  # Get the departure date
return_date = tree.xpath('//input[@placeholder="Return"]/@value')[0]  # Get the return date

# Initialize an empty list to store flight details
flights = []

# Extract flight elements from the parsed HTML using XPath
flight_elements = tree.xpath('//li[@class="pIav2d"]')

# Loop through each flight element and extract details
for flight in flight_elements:
    # Extract the airline name
    airway = flight.xpath('.//div[@class="sSHqwe tPgKwe ogfYpf"]/span/text()')[0].strip()
    
    # Extract flight details such as layovers
    details = flight.xpath('.//span[@class="mv1WYe"]/@aria-label')[0]
    
    # Extract the departure time
    departure = flight.xpath('.//span[@jscontroller="cNtv4b"]/span/text()')[0].strip()
    
    # Extract the arrival time
    arrival = flight.xpath('.//span[@jscontroller="cNtv4b"]/span/text()')[1].strip()
    
    # Extract the total travel time
    travel_time = flight.xpath('.//div[@class="gvkrdb AdWm1c tPgKwe ogfYpf"]/text()')[0].strip()
    
    # Extract the price of the flight
    price = flight.xpath('.//div[@class="U3gSDe"]/div/div[2]/span/text()')[0].strip()

    # Append the extracted details to the flights list as a dictionary
    flights.append({
        'Airway': airway,
        'Details': details,
        'Departure': departure,
        'Arrival': arrival,
        'Travel Time': travel_time,
        'Price': price,
        'From': from_location,
        'To': to_location,
        'Departure Date': departure_date,
        'Return Date': return_date
    })

import csv

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

# Define CSV fieldnames
fieldnames = ['Airway', 'Details', 'Departure', 'Arrival', 'Travel Time', 'Price', 'From', 'To', 'Departure Date', 'Return Date']

# 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 flight in flights:
        writer.writerow(flight)

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

from playwright.sync_api import sync_playwright
from lxml import html
import csv

# URL for the Google Flights search page
url = "https link"

def get_page_content(url):
    """Fetches the HTML content of the given URL using Playwright."""
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=False)  # Launch browser in headful mode
        context = browser.new_context()  # Create a new browser context
        page = context.new_page()  # Open a new page
        page.goto(url)  # Navigate to the specified URL
        page.wait_for_timeout(10000)  # Wait for 10 seconds to ensure the page loads completely
        content = page.content()  # Get the page content
        browser.close()  # Close the browser
    return content

# Fetch the page content
page_content = get_page_content(url)

# Parse the HTML content using lxml
tree = html.fromstring(page_content)

# Extracting flight search details
from_location = tree.xpath('//input[@aria-label="Where from?"]/@value')[0]
to_location = tree.xpath('//input[@aria-label="Where to?"]/@value')[0]
departure_date = tree.xpath('//input[@placeholder="Departure"]/@value')[0]
return_date = tree.xpath('//input[@placeholder="Return"]/@value')[0]

# Initialize a list to store flight details
flights = []

# Extract flight elements from the parsed HTML
flight_elements = tree.xpath('//li[@class="pIav2d"]')
for flight in flight_elements:
    airway = flight.xpath('.//div[@class="sSHqwe tPgKwe ogfYpf"]/span/text()')[0].strip()
    details = flight.xpath('.//span[@class="mv1WYe"]/@aria-label')[0]
    departure = flight.xpath('.//span[@jscontroller="cNtv4b"]/span/text()')[0].strip()
    arrival = flight.xpath('.//span[@jscontroller="cNtv4b"]/span/text()')[1].strip()
    travel_time = flight.xpath('.//div[@class="gvkrdb AdWm1c tPgKwe ogfYpf"]/text()')[0].strip()
    price = flight.xpath('.//div[@class="U3gSDe"]/div/div[2]/span/text()')[0].strip()

    # Append flight details to the list
    flights.append({
        'Airway': airway,
        'Details': details,
        'Departure': departure,
        'Arrival': arrival,
        'Travel Time': travel_time,
        'Price': price,
        'From': from_location,
        'To': to_location,
        'Departure Date': departure_date,
        'Return Date': return_date
    })

# Define the CSV file path
csv_file = 'google_flights.csv'

# Define CSV fieldnames
fieldnames = ['Airway', 'Details', 'Departure', 'Arrival', 'Travel Time', 'Price', 'From', 'To', 'Departure Date', 'Return Date']

# Writing the extracted flight details to a CSV file
with open(csv_file, mode='w', newline='', encoding='utf-8') as file:
    writer = csv.DictWriter(file, fieldnames=fieldnames)
    writer.writeheader()  # Write the header row
    for flight in flights:
        writer.writerow(flight)  # Write each flight's details

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