1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
|
from multiprocessing import Pool
import os
import requests
import time
from PIL import Image
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36',
}
def fetch_file(url, fn, **kwargs):
try:
resp = requests.get(url, params=kwargs, headers=headers, verify=False)
if resp.status_code != 200:
return None
except:
return None
size = 0
if os.path.exists(fn):
return
with open(fn, 'wb') as f:
for chunk in resp.iter_content(chunk_size=1024):
if chunk:
size += len(chunk)
f.write(chunk)
print("{} kb. {}".format(round(size / 1024), fn))
return None
def fetch_raw(url, **kwargs):
try:
resp = requests.get(url, params=kwargs, headers=headers, verify=False)
if resp.status_code != 200:
return None
except:
return None
return resp.text
def fetch_json(url, **kwargs):
try:
resp = requests.get(url, params=kwargs, headers=headers, verify=False)
if resp.status_code != 200:
return None
except:
return None
return resp.json()
# Run this with a pool of 5 agents having a chunksize of 3 until finished
def parallel_fetch(dataset):
print("Fetching {} tiles".format(len(dataset)))
agents = 5
chunksize = 3
with Pool(processes=agents) as pool:
pool.starmap(fetch_file, dataset, chunksize)
def load_image(fn):
try:
image = Image.open(fn)
width, height = image.size
return image, width, height
except:
return None, 0, 0
|
