bs4爬取

import requests
import os
from bs4 import BeautifulSoup
# 使用任意爬虫技术爬取：https://www.umei.cc/bizhitupian/diannaobizhi/ 中的前10页图片，并且打印最终个数，保存到images文件夹
# 创建保存图片的文件夹
if not os.path.exists('images'):
    os.mkdir('images')
count = 0
for i in range(1, 11):
    if i == 1:
        url = 'https://www.umei.cc/bizhitupian/diannaobizhi/'
    else:
        url = 'https://www.umei.cc/bizhitupian/diannaobizhi/index_{}.htm'.format(i)
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 Edg/120.0.0.0"
    }
    response = requests.get(url=url, headers=headers)
    response.encoding = "utf-8"
    text = response.text
    soup = BeautifulSoup(text, 'lxml')
    # 获取图片列表数
    image_elements = soup.select('#infinite_scroll > div')
    print('第{}页有{}张图片'.format(i, len(image_elements)))
    # 遍历详情网页获取图片
    for image_element in image_elements:
        # 图片详情网页地址
        url_01 = 'https://www.umei.cc/' + image_element.select('div:nth-child(1) > div:nth-child(1) > div > a')[0]['href']
        title = image_element.select('span > a')[0].text
        image_urls = requests.get(url=url_01, headers=headers)

        print(image_urls)
        if image_urls.status_code != 200:
            print('图片详情网页请求失败，跳过')
            continue
        # 获取图片网页里的图片地址
        image_text = image_urls.text
        image_soup = BeautifulSoup(image_text, 'lxml')
        url_02 = image_soup.select('body > div:nth-child(3) > div:nth-child(2) > div:nth-child(6) > a > img')[0]['src']
        image_data = requests.get(url=url_02, headers=headers).content
        count += 1

        # 下载图片并保存到本地文件夹images中
        with open('images/{}.jpg'.format(title), 'wb') as f:
            f.write(image_data)
            print(title, "下载成功")

    print('第{}页爬取完成'.format(i))

print('总共爬取了{}张图片'.format(count))