crawler_meizitu_02_class

'''
author:smilehsu
blog:smilehsu.cc
requirements:Windows7、python3.52
'''

import os, re, requests, shutil
from bs4 import BeautifulSoup

#base_url='http://meizitu.com/a/'

all_link=[]
error_page=[]
dir_path='d:\meizitu'

class meizitu():

    def all_url(self,url,maxpage):
        for i in range(1,maxpage+1):
            page_url=url+str(i)+'.html'
            all_link.append(page_url)

        for p in all_link:
            html=self.request(p)
            soup=BeautifulSoup(html.text,'lxml')

            try:
                #取得頁面的title跟該頁面的圖片連結
                title=soup.find('div',{'class':'metaRight'}).find('a')
                #取得圖片連結
                img_url=soup.find('div',{'class':'postContent'}).find_all('img')
                #測試用 印出頁面的title
                print(title.text)
                #測試用
                #print(len(img_url),img_url)
                #要存圖片的資料夾檔名就用頁面的title
                dirname=title.text
                #建立資料夾
                self.mkdir(dirname)
                #儲存圖檔
                self.save(img_url)

            except:
                print('error: {}'.format(p))
                error_page.append(p)
                pass

    def request(self,url):
        headers = {'User-Agent': "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1"}
        res = requests.get(url, headers=headers,stream=True)
        res.encoding='gb2312'
        return res

    def mkdir(self, dirname):
        dirname=dirname.strip()
        isExists = os.path.exists(os.path.join(dir_path, dirname))
        mydir_path=os.path.join(dir_path, dirname)


        if not isExists:
            print('建立資料夾:'+mydir_path)
            os.makedirs(mydir_path)
            os.chdir(mydir_path)
            return True

        else:
            print('資料夾已存在'+mydir_path)
            os.chdir(mydir_path)
            return False

    def save(self, img_url):
        for pic in img_url:
            #路徑check
            #print('目前工作目錄:'+os.getcwd())
            #頁面裡的圖片連結
            pic_src=pic['src']
            print('要下載的圖檔連結'+pic_src)
            #下載圖片後要存檔的檔名
            #pic_name=dir_name+'_'+pic_src.split('/')[-1]
            pic_name=pic_src.split('/')[-1]
            #下載圖片
            get_pic=self.request(pic_src)
            f=open(pic_name,'wb')
            shutil.copyfileobj(get_pic.raw,f)
            f.close()
            del get_pic

Meizitu=meizitu()
Meizitu.all_url(url='http://meizitu.com/a/',maxpage=5)