csdn 文章批量转换markdown格式下载至本地_csdn文章下载为markdown

---

1. 背景

最近准备搭建新博客,所以想把所有csdn的文章下载下来，但实在太多，不可能一篇一篇去导出，所以写了一个批量导出脚本，尽管csdn的在线编辑、发布、专栏、自定义模块、模板等比较成熟,但实在没有一点美感,这一点令人比较失望，一开始我比较在意在线编辑速度快，笔记更新方便，检索也还算可以,前几天阿里云开发者社区、infoQ中国社区运营人员相继邀请我去他们平台发布文章，但我更想尝试本地利用Obsidian工具编写笔记试试，并同步github或gitee仓库存储,博客也许会以github page依托利用hexo、Jekyll等工具发布，如果还可以同步notion或云雀就更完美。

2. 功能

1. 通过传入id确立个人用户主页；
2. 创建个人博客目录，专栏目录；
3. 获取专栏URL、名称、篇数量；
4. 依靠专栏URL获取对应的多页文章URL、标题；
5. 遍历文章URL通过cookie获取文章内容并转换markdown格式。

3. 下载

$ git clone https://github.com/Ghostwritten/csdn_to_md.git 
1

4. 配置

chrome浏览器登陆csdn平台，按"F12"找到自己网页cookie,选择部分cookie内容复制至csdn_to_md.py脚本109行。

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-CPYqwJNL-1651508805129)(https://github.com/Ghostwritten/csdn_to_md/blob/main/cookie.png)]

5. 代码

github仓库：csdn_to_md

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import json
import os
import uuid
import time
import requests
import datetime
import argparse
import re
from bs4 import BeautifulSoup


def request_blog_column(id):

    headers = {
      'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.75 Safari/537.36'
    }
    
    urls = 'https://blog.csdn.net/' + id
    reply = requests.get(url=urls,headers=headers)
    parse = BeautifulSoup(reply.content, "html.parser")
    spans = parse.find_all('a', attrs={'class':'special-column-name'})

    blog_columns = []
    
    for span in spans:
          href = re.findall(r'href=\"(.*?)\".*?',str(span),re.S)
          href = ''.join(href)
         # print(href)

          headers = {
          'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.75 Safari/537.36'
          }
          blog_column_reply = requests.get(url=href,headers=headers)
         # print(blog_column_reply)
          blogs_num = re.findall(r'<a class="clearfix special-column-name"  href=\"'+ href +'\".*?<span class="special-column-num">(.+?)篇</span>',blog_column_reply.text,re.S)
         # print(str(blogs_num[0]))
          blogs_column_num = str(blogs_num[0])


          blog_column = span.text.strip()

          blog_column_dir = './' + str(id) + '/' + str(blog_column)          
          if not os.path.exists(blog_column_dir):
            os.mkdir(blog_column_dir)

          blog_id = href.split("_")[-1]
          blog_id = blog_id.split(".")[0]
          blog_columns.append([href,blog_column,blog_id,blogs_column_num])
        #  print(blog_columns)
          
 

    return blog_columns

def request_blog_list(id):
    blog_columns = request_blog_column(id)
    blogs = []
    for blog_column in blog_columns:
        blog_column_url = blog_column[0]
        blog_column_name = blog_column[1]
        blog_column_id = blog_column[2]
        blog_column_num = int(blog_column[3])
        #print(blog_column_url) 

        if blog_column_num > 40: 
           page_num = round(blog_column_num/40)
           for i in range(page_num,0,-1):
               blog_column_url = blog_column[0]
               url_str = blog_column_url.split('.html')[0]
               blog_column_url = url_str + '_' + str(i) + '.html'
               append_blog_info(blog_column_url,blog_column_name,blogs)
           blog_column_url = blog_column[0]
           blogs = append_blog_info(blog_column_url,blog_column_name,blogs)
        #   print(blogs)
               
        else:
           blogs = append_blog_info(blog_column_url,blog_column_name,blogs)
        #   print(blogs)
   
    #print(blogs)
    return blogs


def append_blog_info(blog_column_url,blog_column_name,blogs):
    headers = {
      'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.75 Safari/537.36'
    }
    reply = requests.get(url=blog_column_url,headers=headers)
    blog_span = BeautifulSoup(reply.content, "html.parser")
    blogs_list = blog_span.find_all('ul', attrs={'class':'column_article_list'})
    for arch_blog_info in blogs_list:
        blogs_list = arch_blog_info.find_all('li')
        for blog_info in blogs_list:
	    
            blog_url = blog_info.find('a', attrs={'target':'_blank'})['href']
            blog_title = blog_info.find('h2', attrs={'class':"title"}).get_text().strip().replace(" ", "_").replace('/','_')
            blog_dict = {'column': blog_column_name,'url': blog_url, 'title': blog_title}
            blogs.append(blog_dict)
    return blogs 

def request_md(id):

    blogs = request_blog_list(id)
    
    for blog_dict in blogs:
        blog_url = blog_dict['url']
        blog_title = blog_dict['title']
        blog_column = blog_dict['column']
        blog_id = blog_url.split("/")[-1] 
        url = f"https://blog-console-api.csdn.net/v1/editor/getArticle?id={blog_id}"
        headers = {
        
         #"Cookie": "uuid_tt_dd=20_18815108270-1651420958061-407001;dc_session_id=10_1651420958062.474827;acw_tc=276077c116514209580398703eb6ccd1972794b4689cf3b5039f85506a6146;UserName=hahalelehehe; UserInfo=30ee073e05d84844b34a829ef0d80541; UserToken=30ee073e05d84844b34a829ef0d80541; UserNick=ghostwritten; AU=5F9; BT=1651420447587; Hm_up_6bcd52f51e9b3dce32bec4a3997715ac=%7B%22islogin%22%3A%7B%22value%22%3A%221%22%2C%22scope%22%3A1%7D%2C%22isonline%22%3A%7B%22value%22%3A%221%22%2C%22scope%22%3A1%7D%2C%22isvip%22%3A%7B%22value%22%3A%221%22%2C%22scope%22%3A1%7D%2C%22uid_%22%3A%7B%22value%22%3A%22xixihahalelehehe%22%2C%22scope%22%3A1%7D%7D; log_Id_click=1111; c_pref=https%3A//i.csdn.net/; c_ref=https%3A//blog.csdn.net/xixihahalelehehe%3Fspm%3D1010.2135.3001.5343; c_page_id=default; dc_tos=rb7pev; log_Id_pv=1346; Hm_lpvt_6bcd52f51e9b3dce32bec4a3997715ac=1651422057; log_Id_view=2182;",
         "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.87 Safari/537.36"
           
        }
        data = {"id": blog_id}
        reply = requests.get(url, headers=headers,data=data)
        reply_data = reply.json()
    #    print(reply_data)

        try:
           key = "key" + str(uuid.uuid4())
           content = reply_data["data"]["markdowncontent"].replace("@[toc]", "")
           blog_title_dir = './' + str(id) + '/' + str(blog_column) + '/' + str(blog_title) + '.md'
           with open(blog_title_dir, "w", encoding="utf-8") as f:
               f.write(content)
             
           print("download blog markdown blog:" + '【' + blog_column + '】' + str(blog_title))
        except Exception as e:
           print("***********************************")
           print(e)
           print(url)




def read_from_json(filename):
    jsonfile = open(filename, "r",encoding='utf-8')
    jsondata = jsonfile.read()
    return json.loads(jsondata)

def write_to_json(filename, data):
    jsonfile = open(filename, "w")
    jsonfile.write(data)



def main():
    parser = argparse.ArgumentParser()

    parser.add_argument('-i', '--id', dest='id',type=str,  required=True, help='csdn name')

    args = parser.parse_args()
    
    csdn_id = args.id

    name_dir = './' + str(csdn_id)
    if not os.path.exists(name_dir):
       os.mkdir(name_dir)

    request_md(csdn_id)

if __name__ == '__main__':
    main()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169

5. 演示

• 观看视频

$ python3 csdn_to_md.py -i  xixihahalelehehe
download blog markdown blog:【helm】helm_快速学习手册
download blog markdown blog:【helm】如何开发一个完整的Helm_charts应用实例
download blog markdown blog:【helm】helm_将yaml文件转换json的插件helm-schema-gen
download blog markdown blog:【helm】helm_NOTES.txt
download blog markdown blog:【helm】helm_test_测试详解
download blog markdown blog:【helm】helm_charts_入门指南
download blog markdown blog:【helm】openshift_Certified_Helm_Charts_实践
download blog markdown blog:【helm】Helm_Values.yaml
......


$ cd xixihahalelehehe 

$ /xixihahalelehehe# tree 
.
├── ansible
│   ├── anible_【模块】_notify.md
│   ├── ansbile【模块】replace_替换.md
│   ├── ansbile_模块开发-自定义模块.md
│   ├── ansible_assert_模块.md
│   ├── ansible_become配置.md
│   ├── ansible_cron_模块.md
│   ├── ansible_debug模块.md
│   ├── ansible_delegate_to_模块.md
│   ├── ansible_file模块详解.md
│   ├── ansible_gather_facts配置.md
│   ├── ansible_hosts_and_groups配置.md
│   ├── ansible_jinja2详解.md
│   ├── ansible-playbook_role角色.md
│   ├── ansible-playbook实战.md
│   ├── ansible_script模块.md
│   ├── ansible_set_fact模块.md
│   ├── ansible_URI模块.md
│   ├── ansible【任务】安装httpd.md
│   ├── ansible变量.md
│   ├── ansible_安装.md
│   ├── ansible_快速学习手册.md
│   ├── ansible【模块】add_host.md
│   ├── ansible【模块】blockinfile.md
│   ├── ansible_【模块】find.md
│   ├── ansible【模块】include_tasks.md
│   ├── ansible【模块】linefile_文件行处理.md
│   ├── ansible【模块】modprobe.md
│   ├── ansible【模块】pause.md
│   ├── ansible_【模块】sysctl.md
│   ├── ansible【模块】systemd.md
│   ├── ansible【模块】template.md
│   ├── ansible【模块】yum.md
│   ├── ansible_系统选择性执行脚本.md
│   ├── ansible远程容器机种方法.md
│   └── ansible_配置.md
├── blog
│   ├── github如何搭建一个博客.md
│   ├── jekyll的一个主题TeXt-theme拆解.md
│   ├── jekyll配置管理github博客.md
│   ├��─ 如何使用jekyll插件.md
│   ├── 如何安装jekyll并搭建一个博客.md
│   └── 如何购买域名.md
├── c++
│   └── makefile入门.md
├── camera
│   ├── A7R2_图标列表.md
│   ├── sony_A7R2介绍.md
│   └── SONY_A7R2_基础操作.md
├── Cisco
│   ├── 运维之思科篇_-----1.VLAN_、_Trunk_、_以太通道及DHCP.md
│   ├── 运维之思科篇_-----2.vlan间通讯_、_动态路由.md
│   ├── 运维之思科篇_-----3.HSRP（热备份路由协议），STP（生成树协议），PVST（增强版PST）.md
│   ├── 运维之思科篇_-----4._标准与扩展ACL_、_命名ACL.md
│   ├── 运维之思科篇_-----5._NAT及静态转换_、_动态转换及PAT.md
│   ├── 运维之思科篇_-----6..md
│   └── 运维之思科篇_-----6.思科项目练习.md

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74

6. 技术

• python json

• python os

• python time

• python request

• python argparse

• python re

• python bs4

• python split()

• python list 列表

• python 计算之除法

• python range()

7. 参考

• https://blog.csdn.net/pang787559613/article/details/105444286