Py学习  »  Python

Python爬取图片+百度人脸检测过滤高颜值美女

python • 3 年前 • 166 次点击  

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:


过滤后的图片:


看看最高颜值的美女:


较低颜值的女性:

*声明:本文于网络整理,版权归原作者所有,如来源信息有误或侵犯权益,请联系我们删除或授权事宜。

觉得不错,点个“在看”然后转发出去


Python社区是高质量的Python/Django开发社区
本文地址:http://www.python88.com/topic/63341
 
166 次点击