【Python】爬取网站的图片

 1.自学python后的简单demo,记录一下

from urllib.request import urlopen,Request,urlretrieve
from urllib.error import HTTPError
import re
import os

from bs4 import BeautifulSoup as bf

'''
爬取图片
使用正则表达式匹配标签

'''

def down(imgUrl,path):
    img = urlopen(imgUrl)
    img = img.read()
    f = open(path, "wb")
    f.write(img)
    f.close()

def downLoadImg(imgUrl,name):
    path = "D:/img/"
    if not os.path.isdir(path):
        os.makedirs(path)
    path = '{}{}.jpg'.format(path, name)
    # print("保存图片到本地:",path)
    urlretrieve(imgUrl, path)

def saveImg(url):
    print(url)
    header = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36'
    }  # 头部信息
    try:
        request = Request(url, headers=header)
        myURL = urlopen(request)
        print("该网页是否存在：", myURL.getcode())  # 200
        if myURL.getcode() == 200:
            html = myURL.read().decode('gbk')
            # print(html)
            reg = '<img src=".*?" alt=".*?"'
            imgre = re.compile(reg)  # 编译一下，提升运行速度
            urls = imgre.findall(html)  # 匹配
            # print(urls)
            urlMap = iter(urls)
            for i in urlMap:
                str = list(i.split('"'))
                downLoadImg("https://pic.xxxnetbian.com" + str[1], str[3])

        else:
            if myURL.getcode() == 404:
                print(404)  # 404
    except HTTPError as e:
        print(e)

for i in range(10):
    if i==0:
        url = 'https://pic.xxxnetbian.com'
        saveImg(url)
    elif i == 1:
        continue
    else:
        url = 'https://pic.xxxnetbian.com/index_'+str(i)+'.html'
        saveImg(url)

2.效果：