程序员（媛）不懂汉服？岂能让别人小看，咱先靠肉眼大数据识别万张穿搭照

import requestsfrom lxml import etreeimport timeimport reimport random
USER_AGENTS = [    "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.85 Safari/537.36",    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",    "其它 USER_AGENT 自己搜集即可"]

def run(url):    try:        headers = {"User-Agent": random.choice(USER_AGENTS)}        res = requests.get(url=url, headers=headers)        # 直接通过 res.json 方法获取到 JSON 格式数据        json_text = res.json()        # 访问 JSON 中的特定对象，这里没有对接口数据进行验证，如有必要，请通过 Status 属性进行接口请求状态验证        data = json_text["Data"]        img_srcs = []        for item in data:            img_srcs.extend(item["ImageSrcs"])        long_str = "\n".join(img_srcs)        # 保存数据        save(long_str)
    except Exception as e:        print(e)

def save(long_str):    try:        with open(f"./imgs.csv", "a+") as f:            f.write("\n"+long_str)    except Exception as e:        print(e)

if __name__ == '__main__':    urls = []    for i in range(1, 10):        print(f"正在爬取第{i}批数据")        run(f"https://api5.hanfugou.com/Trend/GetTrendListForHot?maxid=3396754&objecttype=album&page={i}&count=500")
    print("全部爬取完毕")

def save_img(img_src):    try:        url = img_src        headers = {"User-Agent": random.choice(USER_AGENTS)}        # 注意 verify 参数设置为 False ，不验证网站证书        res = requests.get(url=url, headers=headers, verify=False)        data = res.content
        with open(f"./hanfu/{int(time.time())}.jpg", "wb+") as f:            f.write(data)    except Exception as e:        print(e)

if __name__ == '__main__':
    with open("./imgs.csv","r") as f:        while True:            img_url = f.readline().strip()            if img_url is None:                break            real_url = f"{img_url}_700x.jpg"            save_img(real_url)