python模块：BeautifulSoup使用

import requests,wget,os,time
from bs4 import BeautifulSoup
from requests_html import HTMLSession
from requests_file import FileAdapter

headers = {'User-Agent': 'User-Agent:Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3)'
' AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36',
'Connection': 'close'}

pdf_dir = 'https://wikileaks.org/vault7/document/{0}/{1}.pdf'
base_dir = 'https://wikileaks.org/vault7/document/'
down_dir = "C:\\Users\\51257\\Desktop\\down\\{0}\\"

pdf_test_dir = 'https://wikileaks.org/vault7/document/Protego_Release_' \
'01_05-Design_Docs-20141009-System_HW_Description/' \
'Protego_Release_01_05-Design_Docs-20141009-System_HW_Description.pdf'

'''先进行测试 ，是否能下载pdf ---可以下载'''
#wget.download(pdf_test_dir, out = down_dir)


'''要从base_dir里获得要分类的文件夹，然后建立文件夹'''
session = HTMLSession()
session.mount('file://', FileAdapter()) # 挂载文件
file_url = f'file:///C:/Users/51257/Desktop/WikiLeaks - Documents.html'
r = session.get(file_url)
html = r.html
html_string = r.html.html # 返回网页的内容
session.close()
soup= BeautifulSoup(html_string,'html.parser')
release_section = soup.find('div',class_='release-section')

h3_list = release_section.find_all('h3')
for h3 in h3_list:
h3_list[h3_list.index(h3)] =str(h3).replace('<h3>','').replace('</h3>','').replace('/','')
print(h3_list)

ul_list = release_section.find_all('ul')
#print(ul_list)
for ul in ul_list:
h3_name = h3_list[ul_list.index(ul)]
h3_dir = down_dir.format(h3_name)
is_exist = os.path.exists(h3_dir)
if not is_exist:
os.mkdir(h3_dir)


a_list = ul.find_all('a')
for a in a_list:
base_href = a['href']
base_name = base_href.split('/')[-2]
tar_href = base_href+base_name+'.pdf'

if is_exist:
if not os.path.exists(h3_dir+base_name+'.pdf'):
try:
wget.download(tar_href,h3_dir)
time.sleep(3)
print('下载%s文件成功'%(h3_dir+base_name+'.pdf'))
except Exception as err:
print(err)
print(tar_href)
else:
print('存在%s文件'%base_name)