python优雅地实现输入关键词下载图片

python优雅地实现输入关键词下载图片

思路

• 创建文件夹
• 拿到url（网上很多）
• 循环下载到文件夹中

注意

• 这是借鉴网上的代码，但是有各种BUG
• 文件夹若存在会报错，所以给个用户选择过程
• 若图片加载不出来，无法下载，代码修改了这个bug
• 环境：Python 3.7.7

代码

import urllib.request
import urllib.parse
import ssl
import re
#import pymysql
#import cv2
import time
import os
import shutil
from urllib.error import HTTPError    #导入urllib.error模块，用HTTPError捕获异常信息
i = 0

ssl._create_default_https_context = ssl._create_unverified_context

def open_url(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.104 Safari/537.36 Core/1.53.4843.400 QQBrowser/9.7.13021.400'}
    req = urllib.request.Request(url=url, headers=headers)

    '''req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0')'''
    page = urllib.request.urlopen(req)
    html = page.read().decode('utf-8')
    # print(html)
    return html

def get_img(html, file_name, num):
    global i
    photo_link = r'"objURL":"(http://[^"]*.jpg)"'
    imgs = re.findall(photo_link, html)
    last_link = r'<a href="(/search/flip[^"]*)" class="n">下一页</a>'
    last = re.findall(last_link, html)
    # print(last, i)

    try:
        for each in imgs:
            #print(each)
            if i >= num:
                print('下载结束！')
                return '---', -1
            #print(each)
            filename = file_name + '/' + str(i) + '.jpg'
            try:
                response = urllib.request.urlopen(each) # 打开网址时即可知道是否有异常，所以将本语句放入try语句
                with open(filename, "wb") as f:
                        f.write(response.read())  # 将内容写入图片
                        #成功才+1
                        i +=1
            except HTTPError as e:  # 捕获返回HTTPError类的实例e
                print(e)
                response.close()
                if e.code == 403:  # 捕获异常状态码如果等于403
                    print('权限不足')  # 输出'权限不足'
                elif e.code == 404:  # 捕获异常状态码如果等于404
                    print('没有那个地址')  # 输出'没有那个地址'
                return last, i  # return后面代码均不执行
            response.close()
            return last, i
    except:
        print(last, i)
        return last, i

if __name__ == "__main__":
    key_word = input('请输入要下载的图片：')
    num = int(input('请输入要下载图片的数量：'))
    print('准备下载... ...')
    key_words = urllib.parse.quote(key_word)
    baidu = 'http://image.baidu.com/search/flip?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=result&fr=&sf=1&fmq=1548421364447_R&pv=&ic=0&nc=1&z=&hd=&latest=&copyright=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&ctd=1548421364449%5E00_1351X629&word='
    url = baidu + key_words
    j = 0
    if_del=0
    if os.path.exists(key_word):
        j = int(input('原文件夹存在，是否替换，是：1，否：0：'))
        if j == 1:
            print('路径是：' + os.getcwd() + '\\' + key_word)
            if_del = int(input('是否删除，1是，0否'))
            if if_del ==1:
                shutil.rmtree(os.getcwd() + '\\' + key_word)
                os.makedirs(key_word)
                while url:
                    try:
                        last, a = get_img(open_url(url), key_word, num)
                        url = 'http://image.baidu.com' + last[0]
                        if a == -1:
                            break
                    except:
                        time.sleep(0.01)
                        pass
            else:
                print('有相同文件夹名字，请删除或另起一个名字')
        else:
            print('有相同文件夹名字，请删除或另起一个名字')
    else:
        os.makedirs(key_word)
        while url:
            try:
                last, a = get_img(open_url(url), key_word, num)
                url = 'http://image.baidu.com' + last[0]
                if a == -1:
                    break
            except:
                time.sleep(0.01)
                pass