flightdeals.py

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys

import pandas as pd
import time
import datetime

browser = webdriver.Chrome(executable_path='chromedriver')

# Ticket type path
return_ticket = "//label[@id='flight-type-roundtrip-label-hp-flight']"
one_way_ticket = "//label[@id='flight-type-one-way-label-hp-flight']"
multi_ticket = "//label[@id='flight-type-multi-dest-label-hp-flight']"

# Choose ticket type
def ticket_chooser(ticket):
    try:
        ticket_type = browser.find_element_by_xpath(ticket)
        ticket_type.click()
    except Exception as e:
        pass

# Choose departure country
def departure_city_chooser(departure_country):
    fly_from = browser.find_element_by_xpath("//input[@id='flight-origin-hp-flight']")
    time.sleep(1)
    fly_from.clear()
    time.sleep(1.5)
    fly_from.send_keys('  ' + departure_country)
    time.sleep(1.5)
    first_item = browser.find_element_by_xpath("//a[@id='aria-option-0']")
    time.sleep(1.5)
    first_item.click()

# Choose arrival arrival country
def arrival_city_chooser(arrival_country):
    fly_to = browser.find_element_by_xpath("//input[@id='flight-destination-hp-flight']")
    time.sleep(1)
    fly_to.clear()
    time.sleep(1.5)
    fly_to.send_keys('  ' + arrival_country)
    time.sleep(1.5)
    first_item = browser.find_element_by_xpath("//a[@id='aria-option-0']")
    time.sleep(1.5)
    first_item.click()

# Choose departure date
def departure_date_chooser(month, day, year):
    dep_date_button = browser.find_element_by_xpath("//input[@id='flight-departing-hp-flight']")
    dep_date_button.clear()
    dep_date_button.send_keys(month + '/' + day + '/' + year)

# Choose return dates
def return_date_chooser(month, day, year):
    return_date_button = browser.find_element_by_xpath("//input[@id='flight-returning-hp-flight']")
    for i in range(11):
        return_date_button.send_keys(Keys.BACKSPACE)
    return_date_button.send_keys(month + '/' + day + '/' + year)

# Search!
def search():
    search = browser.find_element_by_xpath("//button[@class='btn-primary btn-action gcw-submit']")
    search.click()
    time.sleep(10)

# Create data frame
df = pd.DataFrame()
def compile_data():
    global df
    global dep_times_list
    global arr_times_list
    global airlines_list
    global price_list
    global durations_list
    global stops_list
    global layovers_list

    #departure times
    dep_times = browser.find_elements_by_xpath("//span[@data-test-id='departure-time']")
    dep_times_list = [value.text for value in dep_times]

    #arrival times
    arr_times = browser.find_elements_by_xpath("//span[@data-test-id='arrival-time']")
    arr_times_list = [value.text for value in arr_times]

    #airline name
    airlines = browser.find_elements_by_xpath("//span[@data-test-id='airline-name']")
    airlines_list = [value.text for value in airlines]

    #prices
    prices = browser.find_elements_by_xpath("//span[@data-test-id='listing-price-dollars']")
    price_list = [value.text.split('$')[1] for value in prices]

    #durations
    durations = browser.find_elements_by_xpath("//span[@data-test-id='duration']")
    durations_list = [value.text for value in durations]

    #stops
    stops = browser.find_elements_by_xpath("//span[@class='number-stops']")
    stops_list = [value.text for value in stops]

    #layovers
    layovers = browser.find_elements_by_xpath("//span[@data-test-id='layover-airport-stops']")
    layovers_list = [value.text for value in layovers]

    for i in range(len(dep_times_list)):
        try:
            df.loc[i, 'departure_time'] = dep_times_list[i]
        except Exception as e:
            pass
        try:
            df.loc[i, 'arrival_time'] = arr_times_list[i]
        except Exception as e:
            pass
        try:
            df.loc[i, 'airline'] = airlines_list[i]
        except Exception as e:
            pass
        try:
            df.loc[i, 'duration'] = durations_list[i]
        except Exception as e:
            pass
        try:
            df.loc[i, 'stops'] = stops_list[i]
        except Exception as e:
            pass
        try:
            df.loc[i, 'layovers'] = layovers_list[i]
        except Exception as e:
            pass
        try:
            df.loc[i, 'prices'] = price_list[i]
        except Exception as e:
            pass

# Run code
for i in range(24):
    link = 'https://www.expedia.com/'
    browser.get(link)
    time.sleep(5)

    #choose flights only
    flights_only = browser.find_element_by_xpath("//button[@id='tab-flight-tab-hp']")
    flights_only.click()
    ticket_chooser(return_ticket)
    departure_city_chooser('Bilbao')
    arrival_city_chooser('London')
    departure_date_chooser('10', '03', '2019')
    return_date_chooser('20', '03', '2019')
    search()
    compile_data()
    print(df)

    time.sleep(3600)