[PYTHON] Get images by keyword search from Twitter

As the title suggests, it is a script for downloading images with specific keywords using Twitter's search API.

https://github.com/Code-Hex/twippai Here is the reference.

Execution environment OS：OX X EI Capitan(10.11.5) Python:2.7.10

In addition to the standard library, you need to install these. requests requests_oauthlib

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

import os
import json
import time
import requests
from hashlib import md5
from requests_oauthlib import OAuth1

def md5hex(str):
	a = md5()
	a.update(str)
	return a.hexdigest()
	
folder = './data'

#Returns True if the path exists
path = os.path.exists(folder)

if not path:
	os.mkdir(folder)

consumer_key = ''#your key
consumer_secret = ''#your key
access_token = ''#your key
access_token_secret = ''#your key

#See below for Twitter API
#https://syncer.jp/twitter-api-matome/get/search/tweets
url = 'https://api.twitter.com/1.1/search/tweets.json'
oauth = OAuth1(consumer_key,consumer_secret,
				access_token,access_token_secret)
				#Specifying the signature method. It worked without
				#signaturemethod = 'HMAC-SHA1')
				
idnum = ''
count = 1
while count <= 10:
	#You can also use Twitter search operators
		query_form = {'q' : u'Ditto filter:images min_retweets:1',
										'lang' : 'ja',
										'count' : 100,
										'result_type' : 'recent',
										'max_id' : idnum}
		uri = requests.get(url, auth = oauth, params = query_form)
		json_loads = json.loads(uri.content)
		
		
		for data in json_loads['statuses']:
			if 'media' not in data['entities']:
				continue
			else:
				urls = data['entities']['media']
				media_urls = urls[0]['media_url']#Get the URL of the image
				downloads = requests.get(media_urls).content #Image DL
				print media_urls + " " + str([count])
			#% S is replaced as a string
			
			#The URL is returned as a character string in hexadecimal format and used as the file name.?
			filename = '%s.jpg' % md5hex(urls[0]['media_url'])
			filepath = '%s/%s' % (folder, filename)
			
			images = open(filepath, 'wb')
			images.write(downloads)
			images.close()
			count += 1
		idum = data['id']
		time.sleep(1)