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
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
|
#!/usr/bin/env python3
import os
import requests
import tempfile
import re
from argparse import ArgumentParser
from PIL import Image
def extract_uuid(url):
uuid_pattern = re.compile(r'[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{12}')
match = uuid_pattern.search(url)
return match.group(0) if match else None
def fetch_manifest(uuid):
url = f'https://iiif.bodleian.ox.ac.uk/iiif/manifest/{uuid}.json'
try:
response = requests.get(url)
response.raise_for_status()
return response.json()
except requests.exceptions.RequestException as e:
print(f"Error fetching JSON data: {e}")
return None
def calculate_chunks(image_width, image_height, chunk_size=4000):
chunks = []
for y in range(0, image_height, chunk_size):
for x in range(0, image_width, chunk_size):
width = min(chunk_size, image_width - x)
height = min(chunk_size, image_height - y)
chunks.append((x, y, width, height))
return chunks
def generate_url(uuid, x, y, width, height):
return f'https://iiif.bodleian.ox.ac.uk/iiif/image/{uuid}/{x},{y},{width},{height}/{width},{height}/0/default.jpg'
def download_chunk(url, save_path):
response = requests.get(url, stream=True)
if response.status_code == 200:
with open(save_path, 'wb') as f:
for chunk in response.iter_content(1024):
f.write(chunk)
else:
raise Exception(f"Failed to download chunk: {url}")
def merge_chunks(image_width, image_height, chunk_paths):
full_image = Image.new('RGB', (image_width, image_height))
for (x, y, width, height), path in chunk_paths:
chunk = Image.open(path)
full_image.paste(chunk, (x, y))
return full_image
def download_and_merge_image(image_width, image_height, image_uuid, output_file):
chunks = calculate_chunks(image_width, image_height)
chunk_paths = []
with tempfile.TemporaryDirectory() as temp_dir:
for i, (x, y, width, height) in enumerate(chunks):
url = generate_url(image_uuid, x, y, width, height)
chunk_path = os.path.join(temp_dir, f"chunk_{i}.jpg")
download_chunk(url, chunk_path)
chunk_paths.append(((x, y, width, height), chunk_path))
full_image = merge_chunks(image_width, image_height, chunk_paths)
full_image.save(output_file)
if __name__ == '__main__':
parser = ArgumentParser()
parser.add_argument('--uuid', type=str, required=True)
parser.add_argument('--output-dir', type=str, required=True)
parser.add_argument('--skip-pages', type=int, default=0,
help='number of pages to skip')
args = parser.parse_args()
m = fetch_manifest(args.uuid)
page = 0
for c in m['sequences'][0]['canvases']:
if args.skip_pages != 0 and page < args.skip_pages:
page += 1
continue
download_and_merge_image(c['width'], c['height'], extract_uuid(c['@id']), os.path.join(args.output_dir, f'{page}.jpg'))
print(f'{page} done')
page += 1
|
