kayak.py

import os
import requests
from pprint import pprint
import time

from statistics import mean, median, median_grouped

def get_prices(verbose=False):
    cookies = {}

    headers = {
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:88.0) Gecko/20100101 Firefox/88.0',
        'Accept': '*/*',
        'Accept-Language': 'en-US,en;q=0.5',
        'Content-Type': 'application/x-www-form-urlencoded',
        'X-Requested-With': 'XMLHttpRequest',
        'Origin': 'https://www.kayak.com',
        'DNT': '1',
        'Connection': 'keep-alive',
        'Pragma': 'no-cache',
        'Cache-Control': 'no-cache',
        'TE': 'Trailers',
    }

    params = (
        ('p', '0'),
    )


    start_date = "2021-05-24"
    end_date = "2021-05-31"


    url = f"/cars/Honolulu,HI-c28070/{start_date}/{end_date}"

    searchId = ""

    data = {
      'searchId': searchId,
      'url': url,
      'contextualSearch': 'false',
      'requestReason': 'POLL',
      'pollNumber': '0',
      'applyFilters': 'flase',
      'driverAge': '-1',
      'sortMode': 'rank',
      'ascending': 'true',
      'priceType': 'totaltaxes',
      'showMap': 'flase',
      'pageNumber': '1',
      'textAdPageLocations': '',
      'displayAdPageLocations': 'bottom-left,bottom'
    }

    response = requests.post('https://www.kayak.com/s/horizon/cars/results/CarSearchPollAction', headers=headers, params=params, cookies=cookies, data=data)

    #NB. Original query string below. It seems impossible to parse and
    #reproduce query strings 100% accurately so the one below is given
    #in case the reproduced version is not "correct".
    # response = requests.post('https://www.kayak.com/s/horizon/cars/results/CarSearchPollAction?p=0', headers=headers, cookies=cookies, data=data)


    results = response.json()["CarResultsList"]["results"]

    prices = []
    
    if verbose:
        print(f'From {start_date} to {end_date}')
        print("")
    for k,v in results.items():
        try:
            providers = v["providers"]
            for provider in providers:
                code = provider["code"]
                price = provider["roundPrice"]
                prices.append(price)
                if verbose:
                    print(f'{code} ${price}')
        except:
            #print("failed")
            pass

    if verbose:
        print("")
        print(f"Avg price for time range {mean(prices)}")
        print(f"median price for time range {median(prices)}")
        
    return prices
    
if __name__ == '__main__':
    
    target_sample_count = 150
    delay = 15
    
    total_prices = []
    
    while len(total_prices) <= target_sample_count:
        total_prices.extend(get_prices(verbose=False))
        if delay:
            print(f"Sleeping for {delay}")
            time.sleep(delay)
        

    print(f"Total price data points {len(total_prices)}")
    
    print(f"Median {median(total_prices)}")
    print(f"Median group {median_grouped(total_prices)}")
    print(f"Lowest {min(total_prices)}")