python爬虫项目爬取图片

最新推荐文章于 2024-08-09 00:05:38 发布

_fox

最新推荐文章于 2024-08-09 00:05:38 发布

阅读量652

点赞数

文章标签： python 爬虫开发语言

本文链接：https://blog.csdn.net/qq_19599237/article/details/133935740

版权

import requests
from bs4 import BeautifulSoup
import os
#爬取的url
url = "https://pic.netbian.com/"
#页面解析
r = requests.get(url)
r.encoding = 'gbk'
soup = BeautifulSoup(r.text, "html.parser")
images = soup.find_all("img")

for image in images:
    #排除某些不是所需图片的img标签
    try:
        src = (image['src'])
    except:
        continue

    #获得图片的链接
    if "/uploads/" not in src:
        continue
    url_image = f"https://pic.netbian.com{src}"
    print(url_image)

    #获得文件名 使用反斜线/作为分隔符
    path_name = os.path.basename(url_image)

    #对于图片的写入(文件名不能过长)
    with open(f"picture/{path_name}", "wb") as f:
        resp = requests.get(url_image)
        f.write(resp.content)