526互联

爬虫爬取网页图片《滕王阁序》文徵明 行草

发布时间 2023-09-14 17:55:54作者: 嘿十三

python爬取网页图片

import urllib.request  # python自带的爬操作url的库
import re  # 正则表达式

def getImage(url):
    headers = {
        'User-Agent': 'Mozilla/5.0(linux; android 6.0; Nexus 5 Build/MRA58N) \
     AppleWebKit/537.36(KHTML, like Gecko) Chrome/56.0.2924.87 Mobile Safari/537.36'
    }
    url = urllib.request.Request(url, headers=headers)
    page = urllib.request.urlopen(url).read()
    page = page.decode('UTF-8')

    imageList = re.findall(r'(https://img[^\s]*?)"', page)
    x = 0
    for imageUrl in imageList[:20]:
        try:
            print('正在下载: %s' % imageUrl)
            image_save_path = 'D:/Users/Desktop/tmp/imagebugliang/%d.jpg' % x
            # 下载图片并且保存到指定文件夹中
            urllib.request.urlretrieve(imageUrl, image_save_path)
            x = x + 1
        except:
            continue


if __name__ == '__main__':
    url = "https://www.zmkm8.com/article-7194-1.html"
    getImage(url)