#!/usr/bin/env python
# -*- coding: utf-8 -*-
import httplib, urllib, base64, json, re, os, sys, codecs, locale, time

pull_count = 50                            ## Var used to control # of hits per pull
offset = 0                                 ## Var used to push pagination counter to http get
num_paginations = 10                       ## Var used to control max # of paginations
local_counter = 1                          ## Helps Write commas to json file for all but last run
timer_counter = 1                          ## Variable used to make system wait after 5 pulls
dump_file = 'BingDump.json'                ## Name of local file where results are written to
api_domain = 'api.cognitive.microsoft.com'
query = 'Bill Gates'
user_agent = 'Mozilla/5.0 (MAC OSX, Educational Usage Only)'
x_search = '199.99.99.99'

#Request Headers, open connection, open file write to output file
headers = {
    'Ocp-Apim-Subscription-Key': 'MYSUBSCRIPTIONKEY',
    'User-Agent' : user_agent,
    'X-Search-ClientIP': x_search,
}
conn = httplib.HTTPSConnection(api_domain)
fhand = open(dump_file,'w')

#Function to build URL for API PULL
def scraper() :
    pull_count_str = str(pull_count)
    offset_str = str(offset)
    params = urllib.urlencode({
        'q': query,
        'count': pull_count_str,
        'offset': offset_str,
        'mkt': 'en-us',
        'safesearch': 'Moderate',
        'responseFilter': 'webpages', #controls whether pull scrapes from web/image/news etc
    })
    return(params)

#Function set to wait 4 seconds after 5 pulls
def holdup(entry) :
    if entry != 5 :
        entry += 1
    else:
        entry = 1
        time.sleep(4)
    return(entry)

#Function that establishes http get, and writes data to json file
def getwrite(entry1, entry2) :
    conn.request("GET", "/bing/v5.0/search?%s" % entry1, "{body}", entry2)
    response = conn.getresponse()
    data = response.read()
    json_data = json.loads(data)
    fhand.write(json.dumps(json_data, indent=4))

#Main Code - Pulls data iteratively and writes it to json file
fhand.write('{')

for i in range(num_paginations) :

    dict_load = '"' + str(local_counter) + '"' +  ' : '
    fhand.write(dict_load)
    try:
        link_params = scraper()
        print('Retrieving: ' + api_domain + '/bing/v5.0/search?' + link_params)
        getwrite(link_params, headers)
    except Exception as e:
        print("[Errno {0}] {1}".format(e.errno, e.strerror))
        fhand.write('"Error. Could not pull data"')
    offset += pull_count
    if local_counter != num_paginations : fhand.write(', ')
    local_counter += 1
    timer_counter = holdup(timer_counter)

fhand.write('}')
fhand.close()
conn.close()