python小白第三天，爬壁纸

本文来源吾爱破解论坛

首先，膜拜论坛里其他爬虫大佬，妹子图有人前面发过，一个是Beautiful爬的，一个是多线程，但是我保证，我没有看着他们的写，而是自己独立写的简单的单线程爬取，有的爱友可能没有python环境，我就顺便打包了一下，嘻嘻。大佬勿喷，小白一起交流。

exe下载地址：https://www.lanzous.com/i57m9wf

我不知道行不行，因为我电脑测试成功了，不知道没有环境的行不行，可以试试，激起大家学爬虫的热情。
[Python] 纯文本查看 复制代码

import requests
import os
from lxml import etree

class Spider(object):
    def headers(self):
        head={
                    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 SE 2.X MetaSr 1.0',
                    'Referer':'https://www.mzitu.com/tag/youhuo/'
                }
        self.first_request(head)
    def first_request(self,head):

        url = 'http://www.mzitu.com'
        response = requests.get(url,headers=head)
        # print(response.content.decode())
        html = etree.HTML(response.content.decode('utf-8'))
        Bigtit_list = html.xpath('//ul[@id="pins"]/li/a/img/@alt')
        Bigsrc_list = html.xpath('//ul[@id="pins"]/li/a/@href')
        # print(Bigtit_list,Bigsrc_list)
        for Bigtit,Bigsrc in zip(Bigtit_list,Bigsrc_list):
            if os.path.exists(Bigtit) == False:
                os.mkdir(Bigtit)
            print(Bigsrc)


            self.second_request(Bigtit,Bigsrc,head)

    def second_request(self,Bigtit,Bigsrc,head):
        for i in range(1,15):
            response = requests.get(Bigsrc+'/'+str(i),headers=head)
            html = etree.HTML(response.content.decode())
            img_name = html.xpath('//div[@class="main-image"]/p/a/img/@alt')
            img_link =html.xpath('//div[@class="main-image"]/p/a/img/@src')
            for name,link in zip(img_name,img_link):

                try:
                    rst = requests.get(link,headers=head)

                    img = rst.content
                    print(link)
                    file_name = Bigtit +'\\'+link.split('/')[-1]
                    print('正在下载的图片为:',name)
                    with open(file_name,'wb') as f:
                        f.write(img)
                except Exception as err:
                    print(err)


spyder=Spider()
spyder.headers()

import requests
import re
from lxml import etree


class Spyder(object):
    def first_url(self,page):
        for i in range(1,page):
            url = 'http://www.bizhi88.com/s/122/'+str(i)+'.html'
            response = requests.get(url)
            html = response.content.decode()
            mid_tit_list = re.compile('<a class="title" href=".*?" target="_blank" title=".*?">(.*?)</a>').findall(html)
            mid_url_list = re.compile('<a class="title" href="(.*?)" target="_blank" title=".*?">.*?</a>').findall(html)

            for mid_tit,mid_url in zip(mid_tit_list,mid_url_list):
                self.get_url(mid_tit,mid_url)

    def get_url(self,mid_tit,mid_url):
        url = 'http://www.bizhi88.com'+mid_url
        response = requests.get(url)
        html = etree.HTML(response.content.decode())
        new_url = html.xpath('//div[@class="layout wp-con"]/div/img/@src')
        # print(new_url)
        self.data_save(new_url,mid_tit)

    def data_save(self,new_url,mid_tit):
        response = requests.get(new_url[0])
        data = response.content
        print('正在下载的图片名字是：',mid_tit)
        with open(mid_tit+'.jpg','wb') as f:
            f.write(data)

spyder = Spyder()
page = int(input('请输入要下载而页数：'))
spyder.first_url(page)

QQ截图20190729113039.png (65.11 KB, 下载次数: 1)

下载附件  保存到相册

2019-7-29 11:30 上传

妹纸图

QQ截图20190729113500.png (108.75 KB, 下载次数: 2)

下载附件  保存到相册

2019-7-29 11:35 上传

壁纸88