# coding=utf-8 
import os 
import re 
import time 
import pdfkit 
import requests 
from bs4 import BeautifulSoup 
from PyPDF2 import PdfFileMerger
import sys
reload(sys)
sys.setdefaultencoding('utf8')

html_template = """ 
 
 
 
   
 
 
{content} 
 
 

""" 

#----------------------------------------------------------------------
def parse_url_to_html(url, name): 
  """ 
  解析URL，返回HTML内容 
  :param url:解析的url 
  :param name: 保存的html文件名 
  :return: html 
  """ 
  try: 
    response = requests.get(url) 
    soup = BeautifulSoup(response.content, 'html.parser') 
    # 正文 
    body = soup.find_all(class_="x-wiki-content")[0] 
    # 标题 
    title = soup.find('h4').get_text() 

    # 标题加入到正文的最前面，居中显示 
    center_tag = soup.new_tag("center") 
    title_tag = soup.new_tag('h1') 
    title_tag.string = title 
    center_tag.insert(1, title_tag) 
    body.insert(1, center_tag) 
    html = str(body) 
    # body中的img标签的src相对路径的改成绝对路径 
    pattern = "(