爬蟲練習--爬妹子圖

import urllib.request
import urllib.parse
import re,os,time
'''
拼接url,發送請求，得到響應內容，分析響應內容，保存數據
'''
def get_request(new_url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36',
    }
    request = urllib.request.Request(url=new_url,headers=headers)
    return request

def get_content(request):
    response = urllib.request.urlopen(request)
    # print(response.read().decode('gbk'))
    return response.read().decode('gbk')

def parse_content(content):
    '''
    <div class="thumb">
        <a href="/article/122125840" target="_blank">
            <img src="//pic.qiushibaike.com/system/pictures/12212/122125840/medium/EAB3PVYM1XFGJF1A.jpg" alt="是胖到下巴都是肉的我">
        </a>
    </div>
    <div class="pic">
            <a target="_blank" href="https://www.meizitu.com/a/5521.html">
                <img src="http://pic.topmeizi.com/wp-content/uploads/2017a/04/08/limg.jpg" alt="<b>周末福利圖，我舅服最后一張帶感的</b>">
            </a>
   </div>
   <h3 class="tit">
       <a href="https://www.meizitu.com/a/5521.html" target="_blank">
       <b>周末福利圖，我舅服最后一張帶感的</b>
       </a>
   </h3>
    '''
    patten = re.compile(r'<div class="pic">.*?<img src="(.*?)" alt="(.*?)".*?</div>',re.S)
    ret = patten.findall(content)
    print(ret)
    # print(len(ret))
    down_load(ret)
#
def down_load(ret):
    dirname = 'mz'
    for tp in ret:
        #取出圖片地址
        image_url = tp[0]
        #取出圖片名稱
        image_name=tp[-1][3:-4]
        # image_name = tp[1]
        # patten1 = re.compile(r'<b>(.*)</b>')
        # ret1 = patten1.findall(image_name)
        #生成文件夾名字
        if not os.path.exists(dirname):
            os.mkdir(dirname)
        filename =image_name+'.'+ image_url.split('.')[-1]
        # print(filename)
        filepath = os.path.join(dirname,filename)
        # print(filepath)
        print('正在下載圖片%s。。。。'%filename)
        urllib.request.urlretrieve(image_url,filepath)
        print('結束下載圖片%s。。。。'%filename)
        time.sleep(2)

def main():
    #輸入起始頁碼
    start_page = int(input("請輸入起始頁碼"))
    end_page =int(input("請輸入結束頁碼"))
    url = 'https://www.meizitu.com/a/'
    for page in range(start_page,end_page+1):
        print("正在下載第%s頁....."%page)
        #拼接url
        new_url = url + 'list_1_'+str(page)+ '.html'
        # print(page)
        # print(new_url)
        request = get_request(new_url)
        content = get_content(request)
        # print(content.read().decode('gbk'))
        parse_content(content)
        print("結束下載第%s頁....." % page)
        time.sleep(2)
if __name__ == '__main__':
    main()