爬取pexels女性图片+百度人脸检测过滤高颜值美女

最新推荐文章于 2020-05-25 14:50:55 发布

cskywit

最新推荐文章于 2020-05-25 14:50:55 发布

阅读量3.9k

点赞数 2

分类专栏： Python

本文链接：https://blog.csdn.net/cskywit/article/details/81545465

版权

Python 专栏收录该内容

42 篇文章 8 订阅

订阅专栏

pexels网站提供了大量贴图，从中搜索美女图片，编写爬虫进行下载，下载后图片中除了女人外，还包含男人，风景、静物和动物，调用百度人脸检测模块识别检测，将其中颜值大于60分的美女保存到另外一个文件夹。爬取图片共计1251张，最后过滤出的美女共计287张。上代码：

爬虫程序：

from bs4 import BeautifulSoup
import requests
import os
import time
save_path = 'F://photos/'
url_path = 'https://www.pexels.com/search/'
headers ={
    'accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
    'user-agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.112 Safari/537.36'
}
searchWord = 'beauty'
urls = [url_path+searchWord+'/?page={}'.format(str(i)) for i in range(1,100)]

if not os.path.exists(save_path):
    os.mkdir(save_path)
page =1
for url in urls:
    img_list = []
    wb_data = requests.get(url,headers=headers)
    print("当前爬取页面链接",url)
    soup = BeautifulSoup(wb_data.text,'lxml')
    imgs = soup.select('article > a > img')
    for img in imgs:
        photo_src = img.get('src')
        img_list.append(photo_src)
    print("第{}页，共计{}张图片".format(page,len(img_list)))
    for item in img_list:
        data = requests.get(item, headers=headers)
        fp = open(save_path+item.split('?')[0][-10:],'wb')
        fp.write(data.content)
        fp.close()
    page = page+1
    time.sleep(2)

颜值检测程序：

from aip import AipFace
import base64
import os
import time
import shutil
#接入百度AI人脸识别的参数
APP_ID="换成你自己的"
API_KEY = "换成你自己的"
SECRET_KEY = "换成你自己的"
imageType = "BASE64"
options = {}
options["face_field"] = "gender,beauty"
options["face_type"] = "LIVE"

#下载图片和筛选图片的文件夹
file_path = 'F://photos/'
copy_file_path = 'F://highScore/'
file_lists=os.listdir(file_path)

aipFace =AipFace(APP_ID,API_KEY,SECRET_KEY)
#将图片转换为BASE64格式，这是百度平台的要求
def get_file_content(filePath):
    with open(filePath,'rb') as fp:
        content = base64.b64encode(fp.read())
        return content.decode('utf-8')

for file_list in file_lists:
    result = aipFace.detect(get_file_content(os.path.join(file_path,file_list)),imageType,options)
    error_code = result['error_code']
    if error_code == 222202:
        #没有人脸
        continue
    if error_code==223110:
        #人脸太多
        continue
    try:
        sex_type = result['result']['face_list'][-1]['gender']['type']
        #只要美女图片
        if sex_type == 'male':
            continue
        beauty = result['result']['face_list'][-1]['beauty']
        new_beauty = round(beauty/10,1)
        print(file_list,new_beauty)
        if new_beauty>=6:
            copy_src = os.path.join(file_path,str(new_beauty)+'_'+file_list)
            copy_dst = os.path.join(copy_file_path,str(new_beauty)+'_'+file_list)
            #重命名高分照片
            os.rename(os.path.join(file_path,file_list),copy_src)
            #复制高分照片到另外的照片
            shutil.copyfile(copy_src,copy_dst)
        time.sleep(1)
    except KeyError:
        pass
    except TypeError:
        pass

爬取的图片：