【Python】网页所有图片检索下载 3次改进！

第一版：

import requests
import os
from bs4 import BeautifulSoup

# 设置网页地址
url = "https://www.Baidu.com"

# 发送请求并获取页面内容
response = requests.get(url)
content = response.content

# 使用 BeautifulSoup 解析页面
soup = BeautifulSoup(content, 'html.parser')

# 设置下载文件夹路径
download_folder = "./图片检索下载文件夹"

# 创建下载文件夹
if not os.path.exists(download_folder):
    os.makedirs(download_folder)

# 查找页面中的图片元素
images = soup.find_all("img")

# 下载图片
for image in images:
    src = image["src"]
    response = requests.get(src)
    if response.status_code == 200:
        with open(os.path.join(download_folder, os.path.basename(src)), "wb") as f:
            f.write(response.content)

第二版：

import requests
import os
from bs4 import BeautifulSoup

def download_images(url, download_folder):
    response = requests.get(url)
    soup = BeautifulSoup(response.content, 'html.parser')
    images = soup.find_all('img')

    if not os.path.exists(download_folder):
        os.makedirs(download_folder)

    for i, image in enumerate(images):
        img_url = image.get('src')
        response = requests.get(img_url, stream=True)

        if response.status_code == 200:
            with open(os.path.join(download_folder, str(i)+'.jpg'), 'wb') as f:
                for chunk in response:
                    f.write(chunk)
        else:
            print(f"Skipping {img_url} due to status code {response.status_code}")

url = 'https://w.wallhaven.cc/full/9d/wallhaven-9ddx9x.jpg'
download_folder = '图片检索下载文件夹'
download_images(url, download_folder)

第三版：

import requests
import os
from bs4 import BeautifulSoup

# 设置网站地址
url = input("请在这里输入你要检索的地址: ")

# 设置下载位置
folder_location = r'.\图片检索下载文件夹'

if not os.path.exists(folder_location):
    os.makedirs(folder_location)

# 请求网页
response = requests.get(url)
content = response.content

# 解析网页
soup = BeautifulSoup(content, "html.parser")
for img in soup.findAll("img"):
    img_url = img.attrs.get("src")
    if not img_url:
        continue
    if "http" not in img_url:
        # 如果图片的 URL 不是完整的，则拼接完整的 URL
        img_url = url + img_url
    response = requests.get(img_url)
    try:
        if response.status_code == 200:
            # 根据图片 URL 设置文件名
            file_name = os.path.join(folder_location, img_url.split("/")[-1])
            with open(file_name, "wb") as f:
                f.write(response.content)
    except Exception as e:
        print("下载错误！")
print("所有图片已下载！")