captcha_scraper/scrape_member.py


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

import os
from pathlib import Path
from urllib.parse import urlparse
import requests


IMAGE_EXTENSIONS = {".jpg", ".jpeg", ".png", ".webp", ".gif", ".bmp", ".tiff", ".tif", ".avif"}

def fetch_photos(url: str) -> list:
    response = requests.get(url, timeout=30)
    response.raise_for_status()
    data = response.json()
    return data.get("photos", [])


def download_photos_from_url(url: str, folder_name: str) -> int:
    target_dir = Path(__file__).resolve().parents[1] / "captcha-original" / folder_name
    target_dir.mkdir(parents=True, exist_ok=True)
    downloaded = 0
    for photo in fetch_photos(url):
        src = photo.get("src")
        if not src:
            continue

        filename = Path(urlparse(src).path).name
        if not filename:
            continue

        destination = target_dir / filename
        if destination.exists():
            continue

        try:
            image_response = requests.get(src, timeout=30)
            image_response.raise_for_status()
            destination.write_bytes(image_response.content)
            print(f"Saved {destination}")
            downloaded += 1
        except Exception as e:
            print(f"Failed to download {src}: {e}")

    print(f"Downloaded {downloaded} files into {target_dir}")
    return downloaded


def renumber_images_recursive(root_folder: str | Path) -> None:
    root = Path(root_folder)
    for current_dir, _, _ in os.walk(root):
        directory = Path(current_dir)
        images = sorted(
            [p for p in directory.iterdir() if p.is_file() and p.suffix.lower() in IMAGE_EXTENSIONS],
            key=lambda p: p.name.lower(),
        )
        if not images:
            continue

        temp_files = []
        for i, image in enumerate(images):
            temp = directory / f"__tmp_{i}{image.suffix.lower()}"
            image.rename(temp)
            temp_files.append(temp)

        for i, temp in enumerate(temp_files):
            temp.rename(directory / f"{i}{temp.suffix.lower()}")

        print(f"Renumbered {len(images)} images in {directory}")


def main():
    pass
    # download_photos_from_url("https://kpopping.com/api/idol-sections?idolId=a1664634-5caf-45d3-a57f-49d99d929aa9&section=photos", "NMIXX")
    # download_photos_from_url("https://kpopping.com/api/idol-sections?idolId=4b6d6573-576e-45d6-8c50-73e885d36a3e&section=photos", "NMIXX")
    # download_photos_from_url("https://kpopping.com/api/idol-sections?idolId=ed6dc832-9b12-4be2-88f2-df7167b241d6&section=photos", "NMIXX")
    # download_photos_from_url("https://kpopping.com/api/idol-sections?idolId=cef6a133-21e5-4034-952f-1edc284a8620&section=photos", "NMIXX")
    # download_photos_from_url("https://kpopping.com/api/idol-sections?idolId=425a818e-b8c3-4f80-9f6c-9151dd490bab&section=photos", "NMIXX")
    # download_photos_from_url("https://kpopping.com/api/idol-sections?idolId=a9d03774-55a1-4ae3-ba4d-3852f674c2e0&section=photos", "NMIXX")
    # renumber_images_recursive("../captcha-original/NMIXX")
    # aespa
    # download_photos_from_url("https://kpopping.com/api/idol-sections?idolId=689e39d5-49f1-4454-9f22-82c2911c855d&section=photos", "aespa")
    # download_photos_from_url("https://kpopping.com/api/idol-sections?idolId=324e43db-9254-4e7e-adf5-48f5318850e2&section=photos", "aespa")
    # download_photos_from_url("https://kpopping.com/api/idol-sections?idolId=5307515b-2488-4043-bf00-06887c5b62aa&section=photos", "aespa")
    # download_photos_from_url("https://kpopping.com/api/idol-sections?idolId=077c4f02-7ca6-49a6-9daf-df1dabc55d0f&section=photos", "aespa")
    # renumber_images_recursive("../captcha-original/aespa")

if __name__ == "__main__":
    main()