爬虫实战--基于requests和beautifulsoup的妹子网图片爬取（福利哦！）

时间：2021-12-03 09:55:32
#coding=utf-8

import requests

from bs4 import BeautifulSoup

import os

all_url = 'http://www.mzitu.com'

#http请求头

Hostreferer = {

    'User-Agent':'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)',

    'Referer':'http://www.mzitu.com'

               }

Picreferer = {

    'User-Agent':'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)',

    'Referer':'http://i.meizitu.net'

}

#此请求头破解盗链

start_html = requests.get(all_url,headers = Hostreferer)

#保存地址

path = '/home/lyt/mzitu/'

#找寻最大页数

soup = BeautifulSoup(start_html.text,"html.parser")

page = soup.find_all('a',class_='page-numbers')

max_page = page[-2].text

same_url = 'http://www.mzitu.com/page/'

for n in range(1,int(max_page)+1):

    ul = same_url+str(n)

    start_html = requests.get(ul, headers = Hostreferer)

    soup = BeautifulSoup(start_html.text,"html.parser")

    all_a = soup.find('div',class_='postlist').find_all('a',target='_blank')

    for a in all_a:

        title = a.get_text() #提取文本

        if(title != ''):

            print("准备扒取："+title)

            #win不能创建带？的目录

            if(os.path.exists(path+title.strip().replace('?',''))):

                    #print('目录已存在')

                    flag=1

            else:

                os.makedirs(path+title.strip().replace('?',''))

                flag=0

            os.chdir(path + title.strip().replace('?',''))

            href = a['href']

            html = requests.get(href,headers = Hostreferer)

            mess = BeautifulSoup(html.text,"html.parser")

            pic_max = mess.find_all('span')

            pic_max = pic_max[10].text #最大页数

            if(flag == 1 and len(os.listdir(path+title.strip().replace('?',''))) >= int(pic_max)):

                print('已经保存完毕，跳过')

                continue

            for num in range(1,int(pic_max)+1):

                pic = href+'/'+str(num)

                html = requests.get(pic,headers = Hostreferer)

                mess = BeautifulSoup(html.text,"html.parser")

                pic_url = mess.find('img',alt = title)

                print(pic_url['src'])

                # exit(0)

                html = requests.get(pic_url['src'],headers = Picreferer)

                file_name = pic_url['src'].split(r'/')[-1]

                f = open(file_name,'wb')

                f.write(html.content)

                f.close()

            print('完成')

    print('第',n,'页完成')
准备扒取：性感美女奶瓶土肥圆硕大美乳雪白细腻惹人冲动

已经保存完毕，跳过

准备扒取：甜美小蜜唐思琪巨乳颤颤姿势妩媚，看完心潮澎湃

已经保存完毕，跳过

准备扒取：美腿御姐萌琪琪曼妙身姿如狼似虎

已经保存完毕，跳过

准备扒取：欲女王雨纯情趣调教 她火热紧致让你性趣满满

准备扒取：尤蜜荟美女模特妲己Toxic天然美乳娇媚入骨

已经保存完毕，跳过

准备扒取：风骚欲女周于希奶大屁股翘 脱衣玩自摸豪放大胆

http://i.meizitu.net/2018/09/12a01.jpg

http://i.meizitu.net/2018/09/12a02.jpg

http://i.meizitu.net/2018/09/12a03.jpg

http://i.meizitu.net/2018/09/12a04.jpg

http://i.meizitu.net/2018/09/12a05.jpg

http://i.meizitu.net/2018/09/12a06.jpg

http://i.meizitu.net/2018/09/12a07.jpg

打印后的结果为：

相关文章