使用爬虫代码获得深度学习目标检测或者语义分割中的图片。

问题描述：目标检测或者图像分割需要大量的数据，如果手动从网上找的话会比较慢，这时候，我们可以从网上爬虫下来，然后自己筛选即可。

代码如下（不要忘记安装代码依赖的库）：

# -*- coding: utf-8 -*-
import re
import requests
from urllib import error
from bs4 import BeautifulSoup
import os
num = 0
numPicture = 0
file = ''
List = []
 
def Find(url, A):
    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:
            # 这里搞了下
            Result = A.get(Url, timeout=7, allow_redirects=False)
        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, allow_redirects=False)
    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 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:
                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'\\' + keyword + '_' + str(num) + '.jpg'
            fp = open(string, 'wb')
            fp.write(pic.content)
            fp.close()
            num += 1
        if num >= numPicture:
            return
 
 
if __name__ == '__main__':  # 主函数入口
    ##############################
    # 这里加了点
    headers = {
        'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
        'Connection': 'keep-alive',
        'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101 Firefox/60.0',
        'Upgrade-Insecure-Requests': '1'
    }
 
    A = requests.Session()
    A.headers = headers
    ###############################
    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 = 'https://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=' + word + '&pn='
 
    # 这里搞了下
    tot = Find(url, A)
    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)
    t = 0
    tmp = url
    while t < numPicture:
        try:
            url = tmp + str(t)
            # 这里搞了下
            result = A.get(url, timeout=10, allow_redirects=False)
 
        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='  ')

这里以搜索明星的图片为例，运行代码，然后根据提示输入搜索图片的名字→搜索图片的张数→保存本地的文件夹即可。

注意：运行的时候只能使用国内网站，而不能使用外网。不然会出现这个错误→requests.exceptions.SSLError: HTTPSConnectionPool(host='image.baidu.com', port=443): Max retries exceeded with url: /search/flip?tn=baiduimage&ie=utf-8&word=%E6%A1%82%E6%9E%97&pn= (Caused by SSLError(SSLZeroReturnError(6, 'TLS/SSL connection has been closed (EOF) (_ssl.c:1131)')))