import os

import requests

import http.client

import json

import re

import math

import pickle

import urllib

import shutil

def make_dir(path):

    if not os.path.isdir(path):

        os.mkdir(path)

def make_img_path(save_dir_path, i, N, num_imgs_per_transaction):

    #パスと拡張子に分割(例;http://~~/img1.txt=>http://~~/img+.txt)

    file_extenxion = os.path.splitext(url)[-1]

    #lower小文字に変換

    if file_extenxion.lower() in ('.jpg', '.jpeg', '.gif', '.png', '.bmp'):

        full_path = os.path.join(save_dir_path, str(i+N*num_imgs_per_transaction) + file_extenxion.lower())

        return full_path

    else:

        raise ValueError('Not applicable file extension')

def download_image(url, timeout=10):

    response = requests.get(url, allow_redirects=True, timeout=timeout)

    #200は接続成功のHTTPステータスコード

    if response.status_code != 200:

        error = Exception("HTTP status:"+responce.status_code)

        raise error

    content_type = response.headers["content-type"]

    if 'image' not in content_type:

        error = Exception("Content-Type"+content_type)

        raise error

    return response.content

def save_img(filename, image):

    with open(filename, "wb") as fout:

        fout.write(image)

if __name__=="__main__":

    """

    要変更！！！！！！！！！！！！！！

    """

    name_list = ['白石麻衣', '高山一実', '松村沙友理']

    save_dir_path_list = ['shiraishi_mai', 'takayama_kazumi', 'matsumura_sayuri']

    for (name, save_dir_path) in zip(name_list, save_dir_path_list):

        make_dir("Member/" + save_dir_path)

        num_imgs_required = 50

        num_imgs_per_transaction = 50

        offset_count = math.floor(num_imgs_required/num_imgs_per_transaction)

        url_list = []

        headers = {

            'Content-Type': 'multipart/form-date',

            'Ocp-Apim-Subscription-Key': 'My_API_Key',

        }

        for offset in range(offset_count):

            params = urllib.parse.urlencode({

                'q': name,

                'mkt': 'ja-JP',

                'count': num_imgs_per_transaction,

                'offset': offset * num_imgs_per_transaction #検索トップから何件後からの画像をDLするか

            })

            try:

                conn = http.client.HTTPSConnection('api.cognitive.microsoft.com')

                conn.request("POST", "/bing/v5.0/images/search?%s" % params, "{body}", headers)

                response = conn.getresponse()

                data = response.read()

                save_res_path = os.path.join("Member", save_dir_path, 'pickle_files')

                make_dir(save_res_path)

                with open(os.path.join(save_res_path, '{}.pickle'.format(offset)), mode='wb') as f:

                    pickle.dump(data, f)

                conn.close()

            except Exception as err:

                print("[Errno {0}] {1}".format(err.errno, err.strerror))

            else:

                decode_res = data.decode('utf-8')

                data = json.loads(decode_res)

                pattern = r"&r=(http.+)&p="

                for values in data['value']:

                    unquoted_url = urllib.parse.unquote(values['contentUrl'])

                    img_url = re.search(pattern, unquoted_url)

                    if img_url:

                        url_list.append(img_url.group(1))

            for i, url in enumerate(url_list):

                try:

                    img_path = make_img_path("Member/"+save_dir_path, i, offset, num_imgs_per_transaction)

                    image = download_image(url)

                    save_img(img_path, image)

                    print('save image ... {}'.format(url))

                except KeyboardInterrupt:

                    break

                except Exception as err:

                    print("%s" % (err))

        shutil.rmtree(save_res_path)

├── Img_Crawler.py

├── Member

    └── shiraishi_mai

        ├── 0.jpg

        ├── 1.jpg

        ・

        ・

    └── takayama_kazumi

    ・

・

import os

import cv2

import numpy as np

cascade_path = "/usr/local/Cellar/opencv/3.3.0_3/share/OpenCV/haarcascades/haarcascade_frontalface_default.xml"

faceCascade = cv2.CascadeClassifier(cascade_path)

mem_list = ['shiraishi_mai', 'takayama_kazumi', 'matsumura_sayuri']

for n in mem_list:

    member = os.path.join("Member", n)

    img_files = os.listdir(member)

    save_path = os.path.join(member, "cutted")

    os.mkdir(save_path)

    face_recognize_num = 0

    for f in img_files:

        root, ext = os.path.splitext(f)

        if ext == '.jpg' or ext == '.jpeg':

            path = os.path.join(member, f)

            img = cv2.imread(path, cv2.IMREAD_COLOR)

            gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

            face = faceCascade.detectMultiScale(gray, 1.11, 3)

            if len(face) > 0:

                for (x,y,w,h) in face:

                    dst = img[y:y+h, x:x+w]

                    resize_img = cv2.resize(dst, (64,64))

                    save_res_path = os.path.join(save_path) + '/' + str(face_recognize_num) + '.jpg'

                    cv2.imwrite(save_res_path, resize_img)

                    print(save_res_path)

                    face_recognize_num += 1

├── Img_Crawler.py

├── face_recognize.py

├── Member

    └── shiraishi_mai

        ├── 0.jpg

        ├── 1.jpg

        ・

        ・

        ├── cutted

            ├── 0.jpg

            ├── 1.jpg

       　　    ・

　　　　　　　　　　　　　　　　    ・

    └── takayama_kazumi

    ・

・