python学习之BeautifulSoup模块爬图

BeautifulSoup模块爬图学习HTML文本解析标签定位
网上教程多是爬mzitu，此网站反爬限制多了。随意找了个网址，解析速度有些慢。
脚本流程：首页获取总页数-->拼接每页URL-->获取每页中所有主题URL-->遍历图片源URL下载，保存

 #python3
 #coding:utf-8_
 #_author: Jack
 #_date: 2020/3/28

 from bs4 import BeautifulSoup
 import requests,os,sys,time

 DIR_PATH = os.path.dirname(os.path.abspath(__file__))
 sys.path.append(DIR_PATH)

 HEADER = {
         'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:74.0) Gecko/20100101 Firefox/74.0',
        }

 def create_dir(file_path):
     '''
     :param file_path: images_directory
     :return:
     '''
     if not os.path.exists(file_path):
         os.makedirs(file_path)
         print('Creatr directory：',file_path)
     os.chdir(file_path) # cd ..

 def save_data(src,dir_name,file_name):
     '''
     :param src: images url
     :param sum: directory name
     :param file_name: image name
     :return:
     '''
     file_path = os.path.join(DIR_PATH,'images',str(dir_name))  #directory path
     image_path = os.path.join(file_path,file_name)  #images path
     create_dir(file_path)

     if not os.path.isfile(image_path):
         req = requests.get(src,headers=HEADER)
         with open(image_path, 'wb') as f_save:
             f_save.write(req.content)
             print('Download successful:',file_name)
             f_save.flush()
     else:
         print('File already exists! Pass')

 def request_to_url(url,header):
     '''
     :param url: page_url
     :param head: request.header
     :return: respond.text
     '''
     res = requests.get(url,headers=header)
     return res.text

 def soup(url,header):
     '''
     :param url:
     :param header:
     :return: HTML_Tag
     '''
     return BeautifulSoup(request_to_url(url,header),'html.parser')

 def action(url):
     '''
     Download a count of 100 images and create a new folder
     :param url: URL
     :return:
     '''
     download_count = 0
     dir_name =100
     try:
         page_tag = soup(url,HEADER).find('div',class_='pg').find_all('a')
         max_page = int(page_tag[-2].text.split(' ')[-1])

         for i in range(1,max_page+1):   #find page
             page_url = os.path.join(url,'forum.php?order=&fid=0&page=%d'%i)
             #time.sleep(1)
             page_all_theme_list = soup(page_url,HEADER).find('div',class_='kind_show')
             theme_list = page_all_theme_list.find_all('div', class_='photo_thumb kind_left')

             for i in theme_list:    #find theme
                 theme = i.find('div', class_='title').find('a')
                 #title = theme.string
                 img_url = theme.get('href')
                 print("Ready download: %s" % theme.string,img_url)
                 # time.sleep(1)
                 img_page_tag = soup(img_url,HEADER).find('td',class_='t_f').find_all('img')

                 for i in img_page_tag:  #find image
                     try:
                         img_src = i.get('src')
                         if download_count %100 == 0:
                             dir_name +=100
                         save_data(img_src,dir_name,img_src.split('/')[-1])
                         download_count += 1
                         print('Download successful: %d' %download_count)

                     except Exception as e:
                         print('Img_tag & Save_data Error:',e)
                         continue

     except Exception as e:
         print('The trunk Error:',e)

 if __name__ == '__main__':
     print('Run.....')
     URL = 'http://www.lesb.cc/'
     action(URL)
     print('Perform !')