keywords_questions_extraction

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Tue Aug 21 13:07:31 2018

@author: cristianodalfarra
"""

#!/usr/bin/env python
# coding:utf-8

# =============================================================================
# # https://www.quora.com/How-can-I-scrape-Googles-autocomplete-suggestions-with-python
# 
# import requests, json
# URL="http://suggestqueries.google.com/complete/search?client=firefox&q=dove * obbligazioni&hl=it"
# headers = {'User-agent':'Mozilla/5.0'}
# response = requests.get(URL, headers=headers)
# result = json.loads(response.content.decode('utf-8'))
# print(result)
# 
# 
# 
# =============================================================================

# https://www.bronco.co.uk/our-ideas/content-topics/

import requests
import json
 
# here you include your main terms, this can be as many as you like
terms = ['obbligazioni']
 
# these are just 'variations' which are appended to the start of your 'terms'
variations = [
              'quali * '    , 
              'sono * '     , 
              'possono * '  , 
              'può *' 
              'come  * '    ,   
              'quanto * '   , 
              'perchè * '   , 
              'dove * '     , 
              'quando * '   , 
              'chi * '       ,
              'cosa * '      ,
              'a cosa * '    ,
              'che * '
              'chi è * '       ,
              'chi sono * '       ,
              'ha * '              ,
              'hanno * '     ,
              'deve * '      ,
              'dovrebbe * '
              ]
 
for term in terms:
	for variant in variations:
        # request api
		r=requests.get('http://suggestqueries.google.com/complete/search?client=firefox&q={}{}'.format(variant, term))
        # grab returned text loading as json
		parsed_json = json.loads(r.text)
        # print each parsed item
		print (parsed_json[0])
		for i in parsed_json[1]:
			print ('- ', i)