爬虫：妹子图

import requests
import re,os
from urllib import request


for i in range(0,4):
    url = 'http://www.mzitu.com/page/%s/'%(i)

    headers = {
               'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
               'Accept-Encoding': 'gzip, deflate',
               'Accept-Language': 'zh-CN,zh;q=0.9',
               'Cache-Control': 'max-age=0',
               'Connection': 'keep-alive',
               'Cookie': 'Hm_lvt_dbc355aef238b6c32b43eacbbf161c3c=1534477754,1534515220,1534596942; Hm_lpvt_dbc355aef238b6c32b43eacbbf161c3c=1534597512',
               'Host': 'www.mzitu.com',
               'If-Modified-Since': 'Fri, 17 Aug 2018 13:59:46 GMT',
               'Referer': 'http://www.mzitu.com/146823',
               'Upgrade-Insecure-Requests': '1',
               'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.84 Safari/537.36',
            }

    response = requests.get(url,headers=headers)

    # with open('test.html', 'wb') as f:
    #     f.write(response.content)

    html = response.text

    meizi_url_list = re.findall('<span><a href="(.*?)" target="_blank">',html)

    # print(meizi_url_list)

    if not os.path.exists('download'):
        os.mkdir('download')

    for meizili in meizi_url_list:
        # print(meizili,type(meizili))
        for i in range(1,10):
            urlli = meizili + '/%s'%(i)

            headers = {
                'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
                'Accept-Encoding': 'gzip, deflate',
                'Accept-Language': 'zh-CN,zh;q=0.9',
                'Cache-Control': 'max-age=0',
                'Connection': 'keep-alive',
                'Cookie': 'Hm_lvt_dbc355aef238b6c32b43eacbbf161c3c=1534477754,1534515220,1534596942; Hm_lpvt_dbc355aef238b6c32b43eacbbf161c3c=1534597512',
                'Host': 'www.mzitu.com',
                'If-Modified-Since': 'Fri, 17 Aug 2018 13:59:46 GMT',
                'Referer': 'http://www.mzitu.com/',
                'Upgrade-Insecure-Requests': '1',
                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.84 Safari/537.36',
            }

            responseli = requests.get(urlli,headers=headers)

            htmlli = responseli.text

            # meizili_url_list = re.findall('<img src="(.*?)" alt=',htmlli)
            pattern = r'img\ssrc="(.+?)"\sa'
            # 妹子jpg的url
            try:
                meizili_url = re.findall(pattern, htmlli)[0]
                print(meizili_url,type(meizili_url))
                # print(meizili_url.split('/')[-1])
                headers = {
                    'Referer': meizili,
                    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.84 Safari/537.36',
                }
                aaa = requests.get(meizili_url, headers=headers).content

                print(aaa)
                filename = 'download/'+meizili_url.split('/')[-1]
                with open(filename, 'wb') as pic:
                    pic.write(aaa)
            except:
                pass

            # # 下载图片
            # request.urlretrieve(image_url, filename)