import os import time import requests from selenium import webdriver from selenium.webdriver.common.by import By from bs4 import BeautifulSoup

设置运行模式

RUNNING_MODE = 1

设置保存路径

save_path = 'path/to/save/images'

设置文章链接

article_url = 'https://www.bilibili.com/read/cv3094491/?from=search&spm_id_from=333.337.0.0'

if RUNNING_MODE == 1: driver = webdriver.Chrome() print(f'开始抓取页面所有文章，请稍候..') driver.get(article_url) time.sleep(1) soup = BeautifulSoup(driver.page_source, 'html.parser') article_urls = [a['href'] for a in soup.select('a[target='_blank']') if 'https://www.bilibili.com/read/' in a['href']] print(f'本次共扫描到 {len(article_urls)} 篇文章！')

total_url_count = len(article_urls)
current_url_count = 0
for article_url in article_urls:
    current_url_count += 1
    print(f'正在加载第 {current_url_count}/{total_url_count} 篇文章内容...')
    driver.get(article_url)
    time.sleep(1)
    soup = BeautifulSoup(driver.page_source, 'html.parser')
    image_elements = soup.select('img[data-src]')
    total_img_count = len(image_elements)
    print(f'当前页面共检测到 {total_img_count} 张图片！')

    current_img_count = 0

    for image_element in image_elements:
        image_url = image_element['data-src']
        filename = image_url.split('/')[-1]
        save_file_path = os.path.join(save_path, f'{filename}')

        if os.path.exists(save_file_path):
            print(f'图片已存在，跳过下载。路径：{save_file_path}')
            time.sleep(0.2)
        else:
            try:
                with open(save_file_path, 'wb') as f:
                    response = requests.get(image_url)
                    f.write(response.content)
                    current_img_count += 1
                    print(f' [{current_img_count}/{total_img_count}] in [article:{current_url_count}] - 已下载图片：{filename}，保存路径：{save_file_path}')
                    time.sleep(0.1)
            except requests.RequestException as e:
                print(f'请求错误: {e}')
                print(f'等待十秒进行重试')
                time.sleep(10)
                continue

driver.quit()