爬虫爬取图片

之前在考研，没有回复csdn，sorry啦，如何还有需要数据集的话，私聊就行，之前大家需要的昆虫数据集可以用类似的方爬取就行。

代码

可以爬取多页

#https://pic.netbian.com/4kmeinv/
#爬取图片
import requests
from bs4 import  BeautifulSoup
def craw_html(url):
    try:

        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
        }
        response = requests.get(url=url, headers=headers)
        print(response.status_code)
        response.encoding = response.apparent_encoding
        response = response.text
        soup = BeautifulSoup(response, 'html.parser')
        # tables = soup.find_all('ul', {'class': "clearfix"})
        tables=soup.find_all('img')
        print(tables)
        count=0
        for table in tables:
            name=table['alt']
            # print(table['alt']+','+table['src'])
            pic_src='https://pic.netbian.com'+table['src']
            dirs='E:/爬虫data/practice/pics/'+name + '.jpg'
            with open(dirs, 'wb') as f:
                     f.write(requests.get(pic_src).content)
                     print(name+'+'+'保存成功')
                     count=count+1

        print("成功爬取{}张图片".format(count))
    except:
        print("爬取失败")
def all_index():
    #https://pic.netbian.com/4kmeinv/index_2.html
    #https://pic.netbian.com/4kmeinv/index_3.html
    index=int(input("共63页，请问要爬取多少页"))
    url = 'https://pic.netbian.com/4kmeinv/'
    craw_html(url)
    for i in range(2,3+index):
        url='https://pic.netbian.com/4kmeinv/'+'index_{}.html'.format(index)
        craw_html(url)

    print("总共成功爬取{}张图片".format(20*index))

if __name__ == '__main__':
    all_index()

结果展示：