File size: 4,817 Bytes
20d0048 c2df0d7 20d0048 c2df0d7 20d0048 c2df0d7 20d0048 598f79e 20d0048 c2df0d7 20d0048 |
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 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 |
import requests
import json
from PIL import Image
import os
from faker import Faker
fake = Faker()
fake_user_agent = fake.user_agent()
fake_headers = {
'scheme': 'https',
'Accept': '*/*',
'Accept-Encoding': 'gzip, deflate, br, zstd',
'Accept-Language': 'zh-CN,zh;q=0.9',
'Dnt': '1',
'Priority': 'u=1, i',
'Sec-Ch-Ua': '"Chromium";v="124", "Google Chrome";v="124", "Not-A.Brand";v="99"',
'Sec-Ch-Ua-Mobile': '?0',
'Sec-Ch-Ua-Platform': '"Windows"',
'Sec-Fetch-Dest': 'empty',
'Sec-Fetch-Mode': 'cors',
'Sec-Fetch-Site': 'same-origin',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36'
}
fake_headers['User-Agent'] = fake_user_agent
def getImgCoordinatesByMagi(image_path:"包含后缀的文件路径",fake_headers:dict=None) -> "全部对话坐标list,失败返回none":
# 创建一个Session对象
session = requests.Session()
if fake_headers is not None:
session.headers = fake_headers
with open(image_path, 'rb') as file:
image_bytes = file.read()
files = {
"image": image_bytes,
}
magi_fastapi_base = 'https://rogerxavier-fastapi-t5-magi.hf.space/getCoordinates'
try:
resp = session.post(magi_fastapi_base, files=files) ##用faker header试试
print(resp.json())
return resp.json()["panels"]
except Exception as e:
print(e)
return None #意外情况返回
def path_to_format(old_path)->"比如/path/to/your/image/1.jpg ->/path/to/your/image/100.jpg 经过03d":
# 获取文件名和文件扩展名
file_path, file_name = os.path.split(old_path)
file_name, file_extension = os.path.splitext(file_name)
# 提取文件名中的数字部分（假设数字部分在文件名的末尾）
number_str = ''.join(filter(str.isdigit, file_name))
number = int(number_str)
# 格式化数字部分为03d格式
formatted_number = "{:03d}".format(number)
# 生成新的文件名
new_file_name = f"{file_name.replace(number_str, formatted_number)}{file_extension}"
new_absolute_path = os.path.join(file_path, new_file_name)
return new_absolute_path
def save_img(new_save_path:"新文件的保存路径(包含后缀)",old_img_path:"旧文件路径(包含后缀)")->"void生成新的文件保存 ,传入旧文件路径是为了删除有问题的旧文件":
print(new_save_path)
# 原始照片文件名
original_image = old_img_path
##防止文件打开无法删除
text_bboxes_for_all_images = getImgCoordinatesByMagi(image_path =original_image,fake_headers = fake_headers)
if text_bboxes_for_all_images is not None:
with Image.open(original_image) as img:
for index, box in enumerate(text_bboxes_for_all_images):
cropped_img = img.crop(tuple(box))
# 保存裁剪后的图片，并按照数字大小依次排序命名(包括本身的也要3d,比如 0.jpg - >000.000_cropped.jpg)
cropped_img.save(f"{os.path.splitext(new_save_path)[0]}_{index:03d}_cropped.jpg")
else:
print("图片识别有问题,准备删除")
os.remove(original_image)
if __name__ == '__main__':
# 获取需要裁剪的无水印漫画位置
img_path = 'manga1'
subdir_path = os.path.join(os.getcwd(), img_path)
# 图片素材获取（包含子目录下所有图片）
image_files = []
for root, dirs, files in os.walk(subdir_path):
for file in files:
if file.endswith(".jpg") or file.endswith(".png"):
image_files.append(os.path.relpath(os.path.join(root, file)))
# 创建处理后的子目录在与image_files同级目录下
processed_subdir_path = os.path.join(os.path.dirname(subdir_path), f"{img_path}2")#加2表示经过2阶段处理
os.makedirs(processed_subdir_path, exist_ok=True)
# 对image_files进行某种处理，生成新图片，并保存在处理后的子目录中
for img_file in image_files:
# 处理图片的代码（这里仅作示例）
# 假设处理后的图片为new_img
img_dir = os.path.dirname(img_file)
new_img_dir = os.path.join(processed_subdir_path, img_dir)
os.makedirs(new_img_dir, exist_ok=True)
new_img_path = os.path.join(new_img_dir, os.path.basename(img_file))
new_img_path = path_to_format(new_img_path)
if not os.path.exists(f"{os.path.splitext(new_img_path)[0]}_{1:03d}_cropped.jpg"):
# 如果已经处理过那么跳过 ->只看第一个数字片段就行
# 处理图片并保存
save_img(new_save_path=new_img_path, old_img_path=img_file)
else:
print(f"Skipping {new_img_path} as it already exists.") |