python入门实战:爬取图片到本地

    简单记录一下爬取网站图片保存到本地指定目录过程,希望对刚入门的小伙伴有所帮助!
    目标网站就是下图所示页面:

实现步骤:
    1.爬取每页的图片地址集合
    2.下载图片到本地
    3. 获取指定页数的页面路径
以下是实现代码:

import bs4
import requests
import os
# 下载图片到本地 
def down_load_img(local_path,img_url):
    img_name = os.path.basename(img_url[img_url.rfind("/")+1:len(img_url)])
    with open(f"{local_path}\{img_name}","wb") as imgFile:
        res = requests.get(img_url)
        if res.status_code == 200:
            resp = imgFile.write(res.content)
            if resp is not None:
                print(f"{img_name}下载成功!")
            else:
                print(f"{img_name}下载失败!")
        else:
            print(f"{img_name}请求失败,下载失败!")

# 获取每页的图片地址
def get_img_url(website_url):
    return_img_url_list=[]
    res = requests.get(website_url)
    if res.status_code != 200:
        print("请求失败!")
    website_content = res.content
    soup = bs4.BeautifulSoup(website_content, "html.parser")
    img_url_list = soup.find_all("div", class_="pic")
    for imgUrl in img_url_list:
        style_info = imgUrl["style"]
        img = style_info[style_info.find("(") + 1:style_info.find(")")]
        return_img_url_list.append(img)
    return return_img_url_list
# 获取指定页数的页面路径
def get_website_url(page_num):
    website_format="https://pic.netbian.top/4kmeinv/index_{}.html"
    web_site_url_list=[]
    for i in range(1,page_num+1):
        web_site_url_list.append(f"https://pic.netbian.top/4kmeinv/index_{i}.html")
    return web_site_url_list

if __name__ == '__main__':
    local_path="D:\mvImg"
    page_num=2
    for website_url in get_website_url(page_num):
        for img_url in get_img_url(website_url):
            down_load_img(local_path,img_url)