我与Python爬虫的初次邂逅

from bs4 import BeautifulSoup
import urllib.request
#用做解析
import urllib.parse
#文件读写
import os

#返回请求到的内容
def url_open(url):
    req = urllib.request.Request(url)

    response = urllib.request.urlopen(req)
    html = response.read()
    return html

def get_links(url):
    # 获取HTML源码
    html = url_open(url)
    #解析HTML
    soup = BeautifulSoup(html, 'html.parser')
    #定位父div
    divs = soup('div', {'class': 'pic'})
    #存储img的列表
    img_addrs = []

    #拿到每一个div中的img及其的src
    for div in divs:
        img_urls = div.find('img')['src']
        img_addrs.append(img_urls)
    return img_addrs
def save_imgs(folder,img_addrs):
    for each in img_addrs:
        filename = each.split('/')[-1]
        with open(filename, 'wb') as f:
            #读取网络图片
            img = url_open(each)
            f.write(img)

def download_pic(folder = 'pic'):
    url = 'http://jcss.shangxin.link/spiderTest.html'
    img_addrs = get_links(url)

    os.mkdir(folder)
    os.chdir(folder)

    save_imgs('pic', img_addrs)

if __name__ == '__main__':
    download_pic()