# 安裝依賴
pip install requests python-magic-bin==0.4.24  # Windows
pip install requests python-magic           # Linux/macOS

[
  {
    "postimage": "{...}",
    "preimage": "{...}",
    "original_image_id": "6cd6187a-a20e-f011-998a-000d3ac8927d"
  },
  // 更多數(shù)據(jù)條目...
]

import json
import requests
import base64
import os
import mimetypes
# 配置參數(shù)
INPUT_JSON = "input.json"  # 輸入的JSON文件路徑
OUTPUT_DIR = "raw_images"   # 圖片輸出目錄（修改目錄以示區(qū)別）
API_URL = "https://prod-53.southeastasia.logic.azure.com:443/workflows/8de920a489c7490a9e2207bd538ce964/triggers/manual/paths/invoke?api-version=2016-06-01&sp=%2Ftriggers%2Fmanual%2Frun&sv=1.0&sig=qO01WQl5tzDZeGpeVid43SpndovXbq4G7QO0NWcz7B8"
def determine_image_type(base64_str):
    """通過(guò)數(shù)據(jù)URI或魔術(shù)數(shù)字檢測(cè)圖片類型"""
    try:
        # 處理數(shù)據(jù)URI格式
        if base64_str.startswith("data:image/"):
            mime_type = base64_str.split(";")[0].split(":")[1]
            return mimetypes.guess_extension(mime_type) or ".png"
        # 通過(guò)魔術(shù)數(shù)字檢測(cè)原始二進(jìn)制格式
        decoded = base64.b64decode(base64_str)
        if decoded.startswith(b'\xff\xd8\xff'):
            return ".jpg"
        elif decoded.startswith(b'\x89PNG\r\n\x1a\n'):
            return ".png"
        elif decoded.startswith(b'GIF87a') or decoded.startswith(b'GIF89a'):
            return ".gif"
        elif decoded.startswith(b'RIFF') and decoded[8:12] == b'WEBP':
            return ".webp"
    except Exception:
        pass
    return ".bin"  # 未知類型
def process_images():
    # 創(chuàng)建輸出目錄
    os.makedirs(OUTPUT_DIR, exist_ok=True)
    # 讀取JSON文件
    try:
        with open(INPUT_JSON, 'r', encoding='utf-8') as f:
            data = json.load(f)
    except Exception as e:
        print(f"讀取JSON文件失敗: {e}")
        return
    # 遍歷處理每個(gè)條目
    for idx, item in enumerate(data, 1):
        image_id = item.get("original_image_id")
        if not image_id:
            print(f"條目 {idx} 缺少original_image_id，已跳過(guò)")
            continue
        print(f"正在處理 ({idx}/{len(data)}): {image_id}")
        # 調(diào)用API
        try:
            response = requests.post(
                API_URL,
                json={"EntityGuid": image_id},
                headers={"Content-Type": "application/json"},
                timeout=60  # 延長(zhǎng)超時(shí)時(shí)間
            )
            print(f"響應(yīng)狀態(tài)碼: {response.status_code}")
            response.raise_for_status()
        except requests.exceptions.RequestException as e:
            print(f"API調(diào)用失敗: {str(e)[:200]}")  # 顯示部分錯(cuò)誤信息
            continue
        # 處理base64數(shù)據(jù)
        try:
            base64_str = response.text
            # 檢測(cè)并分割數(shù)據(jù)URI
            if "," in base64_str:
                header, payload = base64_str.split(",", 1)
                file_ext = determine_image_type(header)
                base64_str = payload
            else:
                decoded = base64.b64decode(base64_str)
                file_ext = determine_image_type(base64_str)
            # 解碼base64
            image_data = base64.b64decode(base64_str)
            # 生成文件名（保留原始格式）
            output_path = os.path.join(OUTPUT_DIR, f"{image_id}{file_ext}")
            # 保存原始二進(jìn)制數(shù)據(jù)
            with open(output_path, "wb") as f:
                f.write(image_data)
            print(f"原始圖片已保存至: {output_path} ({len(image_data):,} bytes)")
        except Exception as e:
            print(f"處理失敗: {str(e)[:200]}")
if __name__ == "__main__":
    process_images()

import requests
from bs4 import BeautifulSoup
from PIL import Image
import os 
from io import BytesIO
import time
url = "http://www.yestone.com/gallery/1501754333627"
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36"}
r = requests.get(url, headers=headers)
soup = BeautifulSoup(r.content, 'html.parser')
items = soup.find('div',class_='images-list')
folder_path = './photo'
# html = requests.get('http://st2.cdn.yestone.com/thumbs/2704315/vector/11688/116887226/api_thumb_450.jpg')
# html = requests.get('/_nuxt/img/4c1a746.jpg')
# print(html.content)
# image = Image.open(BytesIO(html.content))
# image.save(folder_path+"/aaa.jpg")
# print(items.find_all('img'))
# exit()
if os.path.exists(folder_path) == False:
   os.makedirs(folder_path)
for index, item in enumerate(items.find_all('img')):
    if item:
        html = requests.get(item.get('src'))
        img_name = str(index + 1) + '.jpg'
        image = Image.open(BytesIO(html.content))
        image.save(folder_path+"/"+img_name)
        print('第%d張圖片下載完成' % (index + 1))
        time.sleep(1)  # 自定義延時(shí)
print('抓取完成')