Python 备份 CSDN 博客

代码来源

根据csdn 中的 一位博主 备份代码修改

新增加

增加了保存图片 到本地，和修改markdown中图片的路径

问题

如果博客的内容太多，需要分多个truck 传输,保存时出现’'字符时,无法保存

注意

得获取登陆后的cookie，要不没法从服务器请求回博客详细内容

勉强可以用 , 95% 得到备份

import json
import uuid
import time
import requests
import datetime
from bs4 import BeautifulSoup
import re
import rich
import threading
from time import sleep
from rich.panel import Panel
from rich.progress import Progress

progress = Progress(auto_refresh=False)
master_task = progress.add_task("overall", total=21)
jobs_task = progress.add_task("jobs")

from rich.console import Console
console = Console()
def replace_image_path(markdown,new_path) -> str:
    pattern = r'!\[.*?\]\((.+)\)'
    
    lines = markdown.split('\n')
    for i in range(len(lines)):
        match = re.search(pattern, lines[i])
        
        if match is not None:
            original_path = match.group(1)
            lines[i] = lines[i].replace(original_path, new_path+"/"+original_path.rsplit('/')[-1])
    return '\n'.join(lines)

def request_blog_list(remote_url:str,page)->[]:
    blogs = []
    url = f'{remote_url}/{page}'
    reply = requests.get(url,headers='')
    parse = BeautifulSoup(reply.content, "lxml")
    spans = parse.find_all('div', attrs={'class':'article-item-box csdn-tracking-statistics'})
    for span in spans[:40]:
        try:
            href = span.find('a', attrs={'target':'_blank'})['href']
            date = span.find('span', attrs={'class':'date'}).get_text()
            blog_id = href.split("/")[-1]
            read_num = span.find('span', attrs={'class':'read-num'}).get_text()
            blogs.append([blog_id, date, read_num])
        except:
            print('Wrong, ' + href)
    return blogs

def request_md(blog_id, date):
    url = f"https://blog-console-api.csdn.net/v1/editor/getArticle?id={blog_id}"
    # 检查 cookies 从 csdn 博客中
    headers = {
        "cookie":"",
        "User-Agent": ""
    }
    data = {"id": blog_id}
    reply = requests.get(url, headers=headers, data=data)
    json_cache = reply.json()
    markdowncontent=json_cache['data']['markdowncontent']
    if markdowncontent  is not None:
        with open(f"blogs/{json_cache['data']['title']}.md","w+") as f:
            f.write(replace_image_path(markdowncontent,"img"))
        png = BeautifulSoup(reply.content,"lxml").find("img")
        if png is not None:
            res =  png.get('src')
            res = res.replace('"','').replace('\\','')
            if res is not None:
                with open(f"blogs/img/{res.rsplit('/', 1)[-1]}","wb") as f :
                    f.write(requests.get(res).content)





def main(start:int= 1,total_pages:int=1):
    with console.status("[bold green]Working on tasks...") as status:
         blogs = []
         for page in range(start, total_pages + 1):
             blogs.extend(request_blog_list("https://blog.csdn.net/weixin_45647912/article/list",page))
         for blog in blogs:
             blog_id = blog[0]
             date = blog[1].split()[0].split("-")
             request_md(blog_id, date)

if __name__ == '__main__':
    progress.console.print(
        Panel(
            "[bold blue]A demonstration of progress with a current task and overall progress.",
            padding=1,
        )
    )
    start = 0
    stop = 0
    job_no = 0
    for it in range(1,21,3):
        start = it
        stop = it +3
        if stop > 21 :
            stop = 21
        progress.log(f"Starting job #{job_no}") 
        th = threading.Thread(target=main,args=(start,stop))
        th.start()
        th.join()
        job_no+=1
    progress.console.print(
        Panel(
            "[bold blue]A demonstration of progress with a current task and overall progress. [ done]",
            padding=1,
        )
    )