堆糖图片采集 Python 爬虫

代码如下

import requests
import os
def get_page_allurl(json):
    all_url = []
    num = int(json['data']['next_start'])
    path_count = len(json['data']['object_list'])
    for i in range(0, path_count):
        all_url.append(json['data']['object_list'][i]['photo']['path'])
    return all_url
def get_pic(key, page,filepath):
    start = 0
    for i in range(0, page):
        url = f"https://www.duitang.com/napi/blog/list/by_search/?kw={key}&start={start}"
        response = requests.get(url).json()
        print(response['data']['next_start'])
        start = int(response['data']['next_start'])
        print(response)
        urls = get_page_allurl(response)
        # 下载数组里的url保存
        for j in urls:
            file_name = j.split('/')[-1]
            # 保存图片
            save_path = filepath + "\\" + key + "\\"
            directory = os.path.dirname(save_path)
            if not os.path.exists(directory):
                os.makedirs(directory)
            with open(save_path + file_name, 'wb') as f:
                f.write(requests.get(j).content)

        print(f"第{i + 1}页下载完成")


get_pic("刘亦菲", 1,r"C:\Users\fmk\Desktop\堆糖")