爬虫爬取B站文章图片

kuank

废话不说，上代码

import requests
import os
from bs4 import BeautifulSoup

def download_images(url):
    # 发送HTTP请求获取网页源代码
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36'
    }
    response = requests.get(url, headers=headers)
    html = response.text

    # 使用BeautifulSoup解析HTML内容
    soup = BeautifulSoup(html, 'html.parser')

    # 创建一个目录用于保存图片
    os.makedirs('bilibili_images', exist_ok=True)

    # 找到所有图片的标签
    img_tags = soup.find_all('img')

    # 遍历所有图片标签，下载图片
    for img in img_tags:
        img_url = img.get('data-src') or img.get('src')
        if img_url.startswith('//'):
            img_url = 'https:' + img_url

        # 下载图片
        response = requests.get(img_url)
        # 提取图片文件名
        img_file = img_url.split('/')[-1]
        # 将图片保存到指定目录下
        with open('bilibili_images/' + img_file, 'wb') as f:
            f.write(response.content)
            print(f"Downloaded: {img_file}")

# 要爬取的文章URL
article_url = 'https://www.bilibili.com/read/cv18302467/'
download_images(article_url)

https://wwqu.lanzouq.com/i4OyO1l13yij
密码:52pj

kuank

注意:使用前要安装BeautifulSoup和requests库

williamipod

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/workspace/1/main.py", line 1, in <module>
    import requests
  File "/usr/local/lib/python3.10/site-packages/requests-2.31.0-py3.10.egg/requests/__init__.py", line 45, in <module>
    from .exceptions import RequestsDependencyWarning
  File "/usr/local/lib/python3.10/site-packages/requests-2.31.0-py3.10.egg/requests/exceptions.py", line 9, in <module>
    from .compat import JSONDecodeError as CompatJSONDecodeError
  File "/usr/local/lib/python3.10/site-packages/requests-2.31.0-py3.10.egg/requests/compat.py", line 13, in <module>
    import charset_normalizer as chardet
ModuleNotFoundError: No module named 'charset_normalizer'
出现这个这咋回事

三滑稽甲苯

这就是通用的图片下载器吧

52bojie

挺不错的，加油！

Wryyy6

好用，感谢分享

sai609

微信批量下载原创标签文章，python如何实现

红尘旧梦i

老婆是越来越多了，我感觉三妻四妾已经满足不了我了

yiliber

加油！加油！

backaxe

学习一下，感谢分享思路

w360

这个不会用a

AA082

非常有用，感谢