根据关键字百度自动爬取n页图片

之前本来是做过这方面的代码，但是不知道弄哪儿去了，百度了一下这次重新记录下来

import requests
import os
#爬取第一页
url='https://image.baidu.com/search/acjson?' 
headers={#360安全浏览器,百度需要使用cookie
        'Cookie':'.......',
        'Referer': 'https://image.baidu.com/search/index?tn=baiduimage&fm=result&ie=utf-8&word=%E5%B0%8F%E7%8B%97', # 搜索小狗的链接
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'
        }

key='tn=resultjson_com&logid=10902883729278332902&ipn=rj&ct=201326592&is=&fp=result &queryWord={}&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=-1&z=&ic=&hd=&latest=&copyright=&word={}&s=&se=&tab=&width=&height=&face=0&istype=2&qc=&nc=1&fr=&expermode=&force=&pn={}&rn={}&gsm=1e&1615729530798='
word='小狗' # 这里的关键字进行更改
pn=eval('30')  # 这里输入要爬取的页数，30页，也就是30*30九百张图片
imurls=[]
for i in range(1,pn+1):
    url=(url+key).format(word,word,i*30,30)
    r=requests.get(url,headers=headers)
    #"thumbURL":"http://..."图片地址
    imurl=r.json().get('data')
    for im in imurl:
        if im:
            imurls.append(im.get('thumbURL'))
print(len(imurls))
i=1
for iurl in imurls:
    if iurl:
        print('正在下载第{}张图片...'.format(i))
        ir=requests.get(iurl,headers=headers)
        fpath=os.getcwd()+'/dog/'  #在当前路径下建立dog文件夹
        if not os.path.exists(fpath):
            os.mkdir(fpath)  #创建文件夹
        with open(fpath+str(i)+'.png',mode='wb') as f:
             f.write(ir.content)
        i+=1

下面这段代码虽然滚动了30页，但是还是只会获取第一个请求链接，所以只有30条数据。

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import time
import re
import requests
import os

# 设置ChromeDriver的路径
driver_path = "D:\software_office\chromedriver_win32\chromedriver.exe" # which chromedriver

# 创建一个Chrome浏览器实例
driver = webdriver.Chrome(driver_path)

# 访问百度图片搜索结果页面
url = 'https://image.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=result&fr=&sf=1&fmq=1683774515614_R&pv=&ic=&nc=1&z=&hd=&latest=&copyright=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&dyTabStr=MCw0LDEsNiw1LDMsNyw4LDIsOQ%3D%3D&ie=utf-8&sid=&word=%E5%8E%8C%E6%81%B6%E7%9A%84%E7%9C%9F%E4%BA%BA%E8%A1%A8%E6%83%85'
driver.get(url)

# 滚动页面
for _ in range(10):  # 滚动10次，你可以根据需要调整这个值
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
    time.sleep(1)  # 等待页面加载

# 获取页面源代码
html = driver.page_source

# 解析页面源代码，获取图片链接
res = re.findall('"objURL":"(.*?)"', html)
print('-------------',len(res))

# 保存图片
num = 0
pachong_picture_path = './disguestm'
if not os.path.exists(pachong_picture_path):
    os.mkdir(pachong_picture_path)

for i in res:
    num = num + 1
    try:
        picture = requests.get(i)
        file_name = os.path.join(pachong_picture_path, 'dis' + str(num) + ".png")
        with open(file_name, "wb") as f:
            f.write(picture.content)
    except:
        print('Failed to download image: {}'.format(i))

driver.quit()