【经验分享】如何利用Python批量迁移csdn博客到Hexo个人博客

1、博客批量导出为md

import requests
import parsel
import tomd
import os
import re

#对一篇文章的爬取
def spider_one_csdn(title_url):    # 目标文章的链接
    head={
    
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36 Edg/84.0.522.52"
    }
    html=requests.get(url=title_url,headers=head).text
    page=parsel.Selector(html)
    #创建解释器
    title=page.css(".title-article::text").get()
    content=page.css("article").get()
    content=re.sub("<a.*?a>","",content)
    content = re.sub("<br>", "", content)
    #过滤a标签和br标签
    text=tomd.Tomd(content).markdown
    #转换为markdown 文件
    path = os.getcwd()  # 获取当前的目录路径
    file_name = "./download"
    final_road = path + file_name
    try:
        os.mkdir(final_road)
        print('创建成功！')
    except:
        # print('目录已经存在或异常')
        pass
    try:
        with open(final_road+r"./"+title+".md",mode="w",encoding="utf-8") as f:
            f.write('---\n' + "title: " + title + '\n---\n')
            f.write(text)
    except:
        print(title)

def get_article_link(user):
    page=1
    head = {
    
    
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36 Edg/84.0.522.52",
        "Referer": "https://blog.csdn.net/tansty_zh"
        }
    while True:
        link = "https://blog.csdn.net/{}/article/list/{}".format(user, page)
        print("现在爬取第", page, "页")
        html = requests.get(url=link, headers=head).text
        cel = parsel.Selector(html)
        name_link = cel.css(".article-list h4 a::attr(href) ").getall()
        if not name_link:
            break
            #没有文章就退出
        for name in name_link:
            spider_one_csdn(name)
        page+=1

def main():
    name="weixin_44704985" #修改成你的csdn名称
    get_article_link(name)


if __name__ == '__main__':
    main()

2、文件夹整理

分类整理Markdown文件，如图为我的文件夹结构，文件夹上层为download

3、批量生成符合hexo分类和命名格式的文件

生成格式如下

import os

def rename_all(dir):
    for home, dirs, files in os.walk(dir):
        for d in dirs:
            for filename in os.listdir(os.path.join(home, d)):
                fullname = os.path.join(home, d, filename)
                rename_one(filename,fullname)

def rename_one(filename,fullname):
    with open(fullname,mode="r",encoding="utf-8") as f:
        file_name = filename.split(".md")[0]
        hexo_categories = fullname.split("/")[2].split("\\")[0]
        hexo_title = 'title: ' + file_name + '\n'
        hexo_categories = 'categories:\n' + '- ' + hexo_categories + '\n'
        hexo_str = '---\n' + hexo_title + hexo_categories + '\n---'
        markdown = f.read()
        text = markdown.split("---\n")[-1]
        with open(fullname,mode="w",encoding="utf-8") as f:
            f.write(hexo_str)
            f.write(text)
            f.close()

if __name__ == "__main__":
    path = "./download/"
    rename_all(path)

4、文件转移到hexo根目录下的文件夹“source_posts\”中

效果如下

5、欢迎访问我的个人博客

Hexo博客