A crawler that goes through the Google Photos filedump and finds files from a certain year-only!

crawl.py

import os
import ntpath
from shutil import copyfile
from PIL import Image

banned = ["html", "json"]

q = []
toMove = []
q.append(input("First dir: ")) 

f = open("log.txt", mode="w", encoding='utf-8')

while len(q) != 0:
	cur = q[0]
	del q[0]
	if os.path.isdir(cur):
		for i in os.listdir(cur):
			q.append(cur+"/"+i)
	elif os.path.isfile(cur):
		sp = cur.split(".")
		if len(sp) != 0:
			if sp[-1] not in banned and "2017-" in cur:
				#print(cur)
				f.write(cur + "\n")
				toMove.append(cur)

if os.path.isdir("output"):
	for i in os.listdir("output"):
		os.remove("output"+"/"+i)
else:
	os.mkdir("output")
	
for i in toMove:
	copyfile(i, "output/"+ ntpath.basename(i))