这个代码主要用来搜索指定类别的图片,用于opencv训练集,图片下载后会进行预处理,将图片转换为灰度图并将大小变换为20*20,便于进行训练
# -*- coding: utf-8 -*-
"""
Created on Wed Nov 27 11:55:25 2019
@author: admin
"""
import re
import requests
from urllib import error
from bs4 import BeautifulSoup
import os
import cv2
import numpy as np
num = 0
numPicture = 0
file = ''
List = []
gray_file = ''
def Find(url):
global List
print('正在检测图片总数,请稍等.....')
t = 0
i = 1
s = 0
while t < 1000:
Url = url + str(t)
try:
Result = requests.get(Url, timeout=7)
except BaseException:
t = t + 60
continue
else:
result = Result.text
pic_url = re.findall('"objURL":"(.*?)",', result, re.S) # 先利用正则表达式找到图片url
s += len(pic_url)
if len(pic_url) == 0:
break
else:
List.append(pic_url)
t = t + 60
return s
def recommend(url):
Re = []
try:
html = requests.get(url)
except error.HTTPError as e:
return
else:
html.encoding = 'utf-8'
bsObj = BeautifulSoup(html.text, 'html.parser')
div = bsObj.find('div', id='topRS')
if div is not None:
listA = div.findAll('a')
for i in listA:
if i is not None:
Re.append(i.get_text())
return Re
def converttogray(path, num):
i = 0
while True:
if i < num:
pic_path = path+str(i)+'.jpg'
#直接读取灰度图,因为训练使用的是灰度图
img = cv2.imread(pic_path, cv2.IMREAD_GRAYSCALE)
#训练最佳size
dim = (20, 20)
#判断图片是否存在
if img is not None:
resized_pic = cv2.resize(img, dim) # resize 20 * 20
cv2.imwrite(gray_file + r'\\' + 'obj' + '_' + str(i) + '.jpg', resized_pic)
else:
print('img is None')
i = i + 1
else:
break
def dowmloadPicture(html, keyword):
global num
# t =0
pic_url = re.findall('"objURL":"(.*?)",', html, re.S) # 先利用正则表达式找到图片url
print('找到关键词:' + keyword + '的图片,即将开始下载图片...')
for each in pic_url:
print('正在下载第' + str(num + 1) + '张图片,图片地址:' + str(each))
try:
if each is not None:
#这里一定要转换为utf-8不然会报错
pic = requests.get(each, timeout=7)
else:
continue
except BaseException:
print('错误,当前图片无法下载')
continue
else:
string = file + r'\\' + 'obj' + '_' + str(num) + '.jpg'
fp = open(string, 'wb')
fp.write(pic.content)
fp.flush()
fp.close()
num += 1
if num >= numPicture:
converttogray(file + r'\\' + 'obj' + '_', num)
return
if __name__ == '__main__': # 主函数入口
word = input("请输入搜索关键词(可以是人名,地名等): ")
#add = 'http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=%E5%BC%A0%E5%A4%A9%E7%88%B1&pn=120'
url = 'http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=' + word + '&pn='
tot = Find(url)
Recommend = recommend(url) # 记录相关推荐
print('经过检测%s类图片共有%d张' % (word, tot))
numPicture = int(input('请输入想要下载的图片数量 '))
file = input('请建立一个存储图片的文件夹,输入文件夹名称即可')
y = os.path.exists(file)
if y == 1:
print('该文件已存在,请重新输入')
file = input('请建立一个存储图片的文件夹,)输入文件夹名称即可')
os.mkdir(file)
else:
os.mkdir(file)
gray_file = input('请建立一个存储gray图片的文件夹,输入文件夹名称即可,不可以是中文名:')
y = os.path.exists(gray_file)
if y == 1:
print('该文件已存在,请重新输入')
file = input('请建立一个存储图片的文件夹,)输入文件夹名称即可')
os.mkdir(gray_file)
else:
os.mkdir(gray_file)
t = 0
tmp = url
while t < numPicture:
try:
url = tmp + str(t)
result = requests.get(url, timeout=10)
print(url)
except error.HTTPError as e:
print('网络错误,请调整网络后重试')
t = t+60
else:
dowmloadPicture(result.text, word)
t = t + 60
print('当前搜索结束,感谢使用')
print('猜你喜欢')
for re in Recommend:
print(re, end=' ')