import time

def get_timestamp():
    t = str(time.time())
    return  t.replace(".","")[:-3]   # 因为最后的时间是13位


if __name__ == '__main__':
    for page in range(1,2):
        for i in range(page,page+5):
            start = (i-page)*40+1+200*(page-1)  
            end = 200*(page-1)+(i-page+1)*40   
            ts = get_timestamp()
            url = f'https://tieba.baidu.com/photo/g/bw/picture/list?kw=%E5%88%98%E8%AF%97%E8%AF%97&alt=jview&rn=200&tid=3263751314&pn={page}&ps={start}&pe={end}&info=1&_={ts}'
            print(url)

head = {
    'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36",
    'Referer': 'https://tieba.baidu.com/p/1457326101'}  # 必不可少的Referer 认证

# 通过requests获取访问的页面
def get_json(url):
    r = requests.get(url, headers=head)
    if r.status_code != 200:  # 如果没有正常获得网页，产生异常
        raise Exception()
    return r.json()

def parse_json(json, name):
    pic_list = json.get('data').get('pic_list')
    for pic in pic_list:
        purl = pic.get('purl')
        # time.sleep(3)  # 此处可以考虑使用休眠

head1 = {
    'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36",
    'Host': 'imgsrc.baidu.com'
}

def get_pic(pic_url, name):
    r = requests.get(pic_url, headers=head1)
    if r.status_code != 200:  # 如果没有正常获得网页，产生异常
        raise Exception()
    filename = pic_url.rsplit('/')[-1]
    print(filename)
    with open('girl1/' + name + filename, mode='wb') as sw:
        sw.write(r.content)
    print('下载图片：' + filename + '成功！')

def maindown(url, name):
    num = 1
    # 下载html页面
    json = get_json(url)
    # 从页面中提取链接
    parse_json(json, name)


if __name__ == '__main__':
    for page in range(1, 5):
        for i in range(page, page + 5):
            start = (i - page) * 40 + 1 + 200 * (page - 1)  # 201. 241.  281. 321  361
            end = 200 * (page - 1) + (i - page + 1) * 40  # 240 280 320  360  400   440. 3*40
            ts = get_timestamp()
            url = f'https://tieba.baidu.com/photo/g/bw/picture/list?kw=%E5%88%98%E8%AF%97%E8%AF%97&alt=jview&rn=200&tid=3263751314&pn={page}&ps={start}&pe={end}&info=1&_={ts}'
            # 下载html页面
            json = get_json(url)
            # 从页面中提取图片链接并下载到本地
            parse_json(json, name)
            time.sleep(5)  # 此处加了休眠的目的是防止被阻止爬取

  class BaiduPicDetect:
       def __init__(self):
           self.AK = "你的API Key"
           self.SK = "Secret Key"
           self.headers = {
               "Content-Type": "application/json; charset=UTF-8"
           }
   
       # 通过AK和SK得到access_token值
       def get_access_token(self):
           host = 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=' + self.AK + '&client_secret=' + self.SK
           response = requests.get(host, headers=self.headers)
           json_result = json.loads(response.text)
           return json_result['access_token']

    # 注意下面两个方法也是BaiduPicDetect类中的方法
   
    # 要将识别的图片转成base64格式
    def img_to_base64(slef, path):
        with open(path, 'rb') as f:
            base64_data = base64.b64encode(f.read())
            return base64_data

    # 开始检测每一张图片
    def detect_face(self, img_src):
        .....  # 代码太多回复给源码
        return age, beauty, gender

def beauty_check(path):
  ......  # 遍历path文件夹并将测评数据保存到DataFrame中，其中df即DataFrame对象

    return df


if __name__ == '__main__':
  # 当前py文件与girl文件夹在同级，而图片都在girl文件夹中（仅是美女的图片哦！也可以创建boy的文件夹放帅哥）
    path = 'girl'
    result = beauty_check(path)
    result.to_csv('./girl/颜值测评.csv', index=False)
    print('finish！')

import pandas as pd  
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline

plt.rcParams['font.sans-serif'] = ['Arial Unicode MS']  # 处理中文问题 我是Mac系统

data= pd.read_csv('./girl.csv',error_bad_lines=False)

beauty = data.groupby('name')['beauty'].mean().sort_values(ascending=False)

sns.barplot(x=beauty.index,y=beauty.values,palette=sns.color_palette('husl'))