【Python】爬取百度图片进行人脸识别

import os,cv2,requests,json,re,time
import tensorflow as tf
from bs4 import BeautifulSoup

def check_path(path):
    try:
        a = []
        for i in path.split(‘/‘):
            if i != ‘‘:
                a.append(i)
        path = ‘/‘.join(a)
    except:
        pass
    return path

def decrypt_objURL(str):
    """

    :param str: 加密的图片地址
    :return:解密后的图片地址 type=str
    """
    table = {‘w‘: "a", ‘k‘: "b", ‘v‘: "c", ‘1‘: "d", ‘j‘: "e", ‘u‘: "f", ‘2‘: "g", ‘i‘: "h",
             ‘t‘: "i", ‘3‘: "j", ‘h‘: "k", ‘s‘: "l", ‘4‘: "m", ‘g‘: "n", ‘5‘: "o", ‘r‘: "p",
             ‘q‘: "q", ‘6‘: "r", ‘f‘: "s", ‘p‘: "t", ‘7‘: "u", ‘e‘: "v", ‘o‘: "w", ‘8‘: "1",
             ‘d‘: "2", ‘n‘: "3", ‘9‘: "4", ‘c‘: "5", ‘m‘: "6", ‘0‘: "7",
             ‘b‘: "8", ‘l‘: "9", ‘a‘: "0", ‘_z2C$q‘: ":", "_z&e3B": ".", ‘AzdH3F‘: "/"}

    url = re.sub(r‘(?P<value>_z2C\$q|_z\&e3B|AzdH3F+)‘, lambda matched: table.get(matched.group(‘value‘)),str)
    new_url = re.sub(r‘(?P<value>[0-9a-w])‘, lambda matched: table.get(matched.group(‘value‘)), url)

    return new_url

def Request_Img(word=‘佟丽娅‘,imgNum=300):
    objURL_list = []
    for i,page in enumerate(range(0,imgNum,30)):
        Url = ‘http://image.baidu.com/search/acjson?tn=resultjson_com&ipn=rj&word={}&pn={}‘.format(word,str(page))
        response = requests.get(url=Url).json()[‘data‘]
        # print(response)
        try:
            for img in response:
                url = decrypt_objURL(img[‘objURL‘])
                # print(url)
                objURL_list.append(url)
        except Exception as e:
            print(‘出现异常！！！‘,e)

    return objURL_list

def Face_Detection(urllist,savepath=‘./TLY‘):
    if len(urllist) != 0:
        for url in urllist:
            print(url)
            try:
                re = requests.get(url=url).content
                with open(‘./.img‘,‘wb‘) as f:
                    f.write(re)
                face_cascade = cv2.CascadeClassifier(‘./haarcascade_frontalface_default.xml‘)
                img = cv2.imread(‘./.img‘)
                # cv2.imshow(‘etst‘,img)
                # cv2.waitKey(10)
                # cv2.destroyAllWindows()
                gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
                faces = face_cascade.detectMultiScale(gray,
                                                      scaleFactor=1.15,
                                                      minNeighbors=10,
                                                      minSize=(1,1))
                if len(faces) != 0:
                    print(faces)
                    for x,y,w,h in faces:
                        if not os.path.exists(savepath):
                            os.mkdir(savepath)
                        if not os.path.exists(check_path(savepath+‘/face‘)):
                            os.mkdir(check_path(savepath+‘/face‘))
                        name = ‘‘.join(str(time.time()).split(‘.‘))
                        cv2.imwrite(savepath+‘/face/‘+name+‘_face‘+‘.jpg‘,img[y-10:y+h+10,x-10:x+w+10])
                        cv2.imwrite(savepath+‘/‘+name+‘.jpg‘,cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,0),2))

            except:
                pass

if __name__ == ‘__main__‘:
    Face_Detection(Request_Img())

原文地址：https://www.cnblogs.com/zxingwork/p/11421634.html