Python爬虫图片收起附件源代码2

# -*- coding:utf-8 -*- """ @Author: LZL @File: Spider_sjzg.py @Purpose: for Purpose(Need to fill in) @CreateTime: 2021/9/8 18:15 @Software: PyCharm @Thought: 对象思维 """ import requests import time import os from pathlib import Path from selenium import webdriver from selenium.webdriver.support.ui import WebDriverWait from selenium.webdriver.common.by import By from selenium.webdriver.support import expected_conditions as EC import random #https://image.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=result&fr=&sf=1&fmq=1631096170270_R&pv=&ic=&nc=1&z=&hd=&latest=&copyright=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&sid=&word=cat from pyinstrument import Profiler profiler=Profiler() profiler.start() class Get_Baidu: def __init__(self): self.search=input("请输入想要爬取的图片类型:") self.url = "https://image.baidu.com/search/index?tn=baiduimage" self.browser = webdriver.Chrome() # 设置显示等待时间 self.wait = WebDriverWait(self.browser, 20) # 设置最大化 self.browser.maximize_window() self.count =0 self.img_name = "" self.expression=["ヾ(^▽^*)))","（´v｀）","(≧∇≦)ﾉ","o(^▽^)o","(o>ε(o>ｕ(≧∩≦)","(￣︶￣)↗","o(*￣▽￣*)o","(p≧w≦q)","！*★,°*:.☆(￣▽￣)/$:*.°★* 。","ㄟ(≧◇≦)ㄏ","(/≧▽≦)/","(　ﾟ∀ﾟ) ﾉ♡","o(*￣︶￣*)o","(๑¯∀¯๑)","(≧∀≦)ゞ","φ(≧ω≦*)♪","╰(*°▽°*)╯","^O^","(*^▽^*)","ヽ(✿ﾟ▽ﾟ)ノ","(´▽`ʃ♡ƪ)","φ(゜▽゜*)♪","o(*￣▽￣*)o","(u‿ฺu✿ฺ)",] def main(self): self.mkdir() self.browser.get(self.url) time.sleep(1) self.wait.until(EC.presence_of_element_located((By.ID, "kw"))) self.browser.find_element_by_id("kw").send_keys(self.search) time.sleep(1) self.browser.find_element_by_class_name("s_newBtn").click() self.get_img() def mkdir(self): if os.path.exists(self.search) !=True: os.mkdir(self.search) else: print("目录文件已存在,请删除或重命名... 3秒后结束程序") time.sleep(3) exit(0) def get_img(self): divs = self.browser.find_elements_by_class_name("imgbox-border") for div in divs: if divs.index(div) >= self.count: try: div.click() except: print("****** 广告?（｡ò ∀ ó｡）反正吧他就是点击不了 ┭┮﹏┭┮ ****** ") continue windows=self.browser.window_handles self.browser.switch_to_window(windows[1]) try: img_url = self.browser.find_element_by_id('currentImg').get_attribute('src') except: self.browser.close() windows = self.browser.window_handles self.browser.switch_to_window(windows[0]) continue if "http" not in img_url: self.get_img() r = requests.get(img_url) img_name = self.search+str(self.count) + ".jpg" if self.count%6 == 0: print("累计爬取图片:%d 张 %s" % (self.count,self.expression[random.randint(0,len(self.expression)-1)])) with open("%s/%s"%(self.search,img_name), 'wb', buffering=0) as f: f.write(r.content) self.count += 1 self.img_name = img_name if self.count != 0: while self.getfile(self.img_name): time.sleep(2) print("文件不存在！读取中.....") self.browser.close() windows = self.browser.window_handles self.browser.switch_to_window(windows[0]) js = "var q=document.documentElement.scrollTop=100000" self.browser.execute_script(js) time.sleep(5) # self.get_img() def getfile(self, path): my_file = Path("%s/%s"%(self.search,path)) print(os.path.join(self.search,path)) if my_file.is_file(): return False else: return True print("****************************************") print("*** 百度图片Spider 跟据输入内容进行爬取***") print("*** 如需修改请联系 QQ:389131999 ***") print("****************************************") Get_Baidu().main() profiler.stop() profiler.print()