一个图片小爬虫

表示放假看了看python ，一直想写个爬虫玩一下，但是好多网站都有反爬虫的机制orz..,导致爬下来的图片根本没法看（哭 。最近发现一个很良心的站，于是写了个小爬虫嘿嘿嘿。主要用到了BeautifulSoup库和requests库，比较简单，效率比较差，有待改进就当自娱自乐了hhh

import os
import requests
from bs4 import BeautifulSoup
import re

class Mmonly(object):

    def all_page(self,url):
        for page in range(1,388):
            print('当前第',page,'页')
            page_html = url[:-6] + str(page) + '.html'
            self.all_url(page_html)

    def all_url(self,url):
        html = self.request(url)
        all_a = BeautifulSoup(html.text,'html5lib').find_all('div',class_ = 'ABox')
        for a in all_a:
            href = a.contents[0]
            name = href.contents[0]
            url = href['href']
            title = name['alt']
            path = str(title)
            if self.mkdir(path):
                self.html(url)
            else:
                pass

    def mkdir(slef,path):
        path = path.strip()
        isExists = os.path.exists(os.path.join('G:\python\mmonly.cc',path))
        if not isExists:
            print('创建一个叫',path,'的文件夹')
            os.mkdir(os.path.join('G:\python\mmonly.cc',path))
            os.chdir(os.path.join('G:\python\mmonly.cc',path))
            return True
        else:
            print(path,'文件夹已经存在')
            return False

    def html(self,url):
        pic_html = self.request(url)
        pic_num = BeautifulSoup(pic_html.text,'html5lib').find('span',class_ = 'totalpage').get_text()
        cnt = 0
        for page in range(1,int(pic_num)+1):
            page_url = url[:-5] + '_' + str(page) + '.html'
            #print(page_url)
            cnt += 1
            self.img(page_url,cnt)

        #print(pic_num)

    def img(self,url,cnt):
        img_html = self.request(url)
        img_url = BeautifulSoup(img_html.text,'html5lib').find('div', class_ ='big-pic').find('img')['src']
        #print(img_url)
        self.save(img_url,cnt)

    def save(self,url,cnt):
        name = str(cnt)
        #print(name)
        img = self.request(url)
        f = open(name+'.jpg','ab')
        f.write(img.content)
        f.close();

    def request(self,url):
        headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.101 Safari/537.36'}
        content = requests.get(url,headers = headers)
        return content


mmonly = Mmonly()
url = 'http://www.mmonly.cc/ktmh/list_28_1.html'
mmonly.all_page(url)