前言

由于工作需要，需要从网上获取大量图片。（使用谷歌图片需自备梯子）

涉及到的库

pip 安装

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
import time
import urllib.request
from bs4 import BeautifulSoup as bs
import os

需要使用的插件

谷歌浏览器插件：chromedriver
下载地址：http://chromedriver.storage.googleapis.com/index.html
下载与自己浏览器版本对应的插件，版本查看在浏览器的设置中查找

实现过程

- 代码分析

# -*- coding: UTF-8 -*-"""
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
import time
import urllib.request
from bs4 import BeautifulSoup as bs
import re
import os# ****************************************************
base_url_part1 = 'https://www.google.com/search?q='
base_url_part2 = '&source=lnms&tbm=isch'                  # base_url_part1以及base_url_part2都是固定不变的，无需更改
search_query = '******'                                   # 检索的关键词，可自己输入你想检索的关键字
location_driver = r'***\***\chromedriver'                 # Chrome驱动程序在电脑中的位置class Crawler:def __init__(self):self.url = base_url_part1 + search_query + base_url_part2# 启动Chrome浏览器驱动def start_brower(self):chrome_options = Options()chrome_options.add_argument("--disable-infobars")# 启动Chrome浏览器driver = webdriver.Chrome(executable_path=location_driver, chrome_options=chrome_options)# 最大化窗口，因为每一次爬取只能看到视窗内的图片driver.maximize_window()# 浏览器打开爬取页面driver.get(self.url)return driverdef downloadImg(self, driver):t = time.localtime(time.time())picpath = r'E:\data'  # 下载到的本地目录# 路径不存在时创建一个if not os.path.exists(picpath): os.makedirs(picpath)# 下载图片的本地路径 /home/LQ/ImageDownload/xxx# 记录下载过的图片地址，避免重复下载img_url_dic = {}x = 0# 当鼠标的位置小于最后的鼠标位置时,循环执行for i in range(50):  # 此处可自己设置爬取范围pos = i * 500  # 每次下滚500js = "document.documentElement.scrollTop=%d" % posdriver.execute_script(js)time.sleep(1)# 获取页面源码html_page = driver.page_source# 利用Beautifulsoup4创建soup对象并进行页面解析soup = bs(html_page, "html.parser")# 通过soup对象中的findAll函数图像信息提取imglist = soup.findAll('img', {'class': 'rg_i Q4LuWd'})for imgurl in imglist:try:print(x)if imgurl['src'] not in img_url_dic:target = '{}/{}.jpg'.format(picpath, str(x))# print ('Downloading image to location: ' + target + '\nurl=' + imgurl['src'])img_url_dic[imgurl['src']] = ''urllib.request.urlretrieve(imgurl['src'], target)time.sleep(1)x += 1except KeyError:print("ERROR!")continuedef run(self):print('\t\t\t**************************************\n\t\t\t**\t\tWelcome to Use Spider\t\t**\n\t\t\t**************************************')driver = self.start_brower()self.downloadImg(driver)driver.close()print("Download has finished.")if __name__ == '__main__':craw = Crawler()craw.run()