鉴于有些小伙伴在寻找博客园迁移到个人博客的方案，本人针对博客园实现了一个自动备份脚本，可以快速将博客园中自己的文章备份成Markdown格式的独立文件，备份后的md文件可以直接放入到hexo博客中，快速生成自己的站点，而不需要自己逐篇文章迁移，提高了备份文章的效率。
首先第一步将博客园主题替换为codinglife默认主题，第二步登录到自己的博客园后台，然后选择博客备份，备份所有的随笔文章，如下所示：
备份出来以后将其命名为backup.xml，然后新建一个main.py脚本，以及一个blog目录，代码实现的原理是，解析xml格式并依次提取出文档内容，然后分别保存为markdown文件。
转存文章到MD
写入备份脚本，代码如下所示，运行后即可自动转存文件到blog目录下，当运行结束后备份也就结束了。
# powerby: LyShark
# blog: www.cnblogs.com/lyshark
from bs4 import BeautifulSoup
import requests, os,re
header = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) By LyShark CnblogsBlog Backup Script"}
# 获取文章,并转成markdown
# blog: www.lyshark.com
def GetMarkDown(xml_file):
con = open(xml_file, 'r', encoding='utf8').read()
# 每篇文章都在 <item> 标签里
items = re.findall("<item>.*?</item>", con, re.I | re.M | re.S)
ele2 = ['<title>(. ?)</title>', '<link>(. ?)</link>', '<description>(. ?)</description>']
# md_name = xml_file.split('.xml')[0] '.md'
for item in items:
try:
title = re.findall(ele2[0], item, re.I | re.S | re.M)[0]
link = re.findall(ele2[1], item, re.I | re.S | re.M)[0]
des = re.findall(ele2[2], item, re.I | re.S | re.M)[0]
des = re.findall('<!\[CDATA\[(. ?)\]\]>', des, re.I | re.S | re.M)[0] # CDATA 里面放的是文章的内容
des = des.replace('~~~', "```")
lines = des.split('\n')
with open("./blog/" title.replace("/","") ".md", mode='w ', encoding='utf8') as f:
f.write("---\n")
f.write("title: '{}'\n".format(title.replace("##","").replace("###","").replace("-","").replace("*","").replace("<br>","").replace(":","").replace("：","").replace(" ","").replace(" ","").replace("`","")))
f.write("copyright: true\n")
setdate = "2018-12-27 00:00:00"
try:
# 读取时间
response = requests.get(url=link, headers=header)
print("读取状态: {}".format(response.status_code))
if response.status_code == 200:
bs = BeautifulSoup(response.text, "html.parser")
ret = bs.select('span[id="post-date"]')[0]
setdate = str(ret.text)
pass
else:
f.write("date: '2018-12-27 00:00:00'\n")
except Exception:
f.write("date: '2018-12-27 00:00:00'\n")
pass
f.write("date: '{}'\n".format(setdate))
# description检测
description_check = lines[0].replace("##","").replace("###","").replace("-","").replace("*","").replace("<br>","").replace(":","").replace("：","").replace(" ","").replace(" ","")
if description_check == "":
f.write("description: '{}'\n".format("该文章暂无概述"))
elif description_check == "```C":
f.write("description: '{}'\n".format("该文章暂无概述"))
elif description_check == "```Python":
f.write("description: '{}'\n".format("该文章暂无概述"))
else:
f.write("description: '{}'\n".format(description_check))
print("[*] 时间: {} --> 标题: {}".format(setdate, title))
f.write("tags: '{}'\n".format("tags10245"))
f.write("categories: '{}'\n".format("categories10245"))
f.write("---\n\n")
f.write('%s'