停止更新我的语雀博客

博客地址https://jameshoi.github.io/

要跟语雀说再见了，最爱这个能每篇文章显示封面的功能，但是在语雀写文章再转pdf格式实在是太烂了，导出成markdown图片还保留cdn的图片格式，而且还不能批量导出文章。

最后我自己写了个脚本解决这个问题，贴到这里给后人作为参考吧

import requests
import json
import os
import time
from urllib.parse import urlparse,urlsplit,parse_qs,parse_qsl
TOKEN = "" #这里填你的token
NAMESPACE = "jameshoi"
SAVE_PATH = "./source/"
DOWNLOAD_FILE_PATH = "https://jameshoi.github.io/files/"
TIMEOUT = 5
def download_file(url,filename):
    while True:
        try:
            response=requests.get(url,timeout=TIMEOUT)
            break
        except Exception as e: 
            time.sleep(2)
    with open(filename,'wb') as f: f.write(response.content)
def get_all_md_info(doc_path):
    url = "https://www.yuque.com/api/v2/repos/jameshoi/{}/docs".format(doc_path)
    headers = {
    'Content-Type': 'application/json',
    'X-Auth-Token': TOKEN
    }
    response = requests.get(url, headers=headers,timeout=TIMEOUT)
    return json.loads(response.content)
def download_md(doc_path,doc_name):
    optional = "attachment=true&latexcode=false&anchor=false&linebreak=false"
    url = "https://www.yuque.com/jameshoi/{}/{}/markdown?{}".format(doc_path,doc_name,optional)
    download_file(url,SAVE_PATH+doc_name+".md")
def save_img(doc_name,url):
    filename = urlparse(url).path.split("/")[-1]
    if not os.path.exists(SAVE_PATH+doc_name): os.mkdir(SAVE_PATH+doc_name)
    download_file(url, SAVE_PATH+doc_name+"/"+filename)
    return filename
def replace_img_url(doc_name):
    with open(SAVE_PATH+doc_name+".md","rb+") as f:
        content = f.read().decode()
    start = 0; url_list = []
    while True:
        head = content.find("![",start)
        mid = content.find("(",head)+1
        end = content.find(")",mid)
        if head == -1 or mid == 0 or end == -1: break
        url = content[mid:end]; start = end
        filename = save_img(doc_name, url)
        url_list.append([url, doc_name+"/"+filename])
    for [url,path] in url_list: content = content.replace(url,path)
    with open(SAVE_PATH+doc_name+".md","wb+") as f: f.write(content.encode())
def add_md_info(doc_name,title,date):
    data = "---\ntitle: {}\ndate: {}\n---\n".format(title,date)
    with open(SAVE_PATH+doc_name+".md","rb+") as f:
        old = f.read(); f.seek(0)
        f.write(data.encode()); f.write(old)
def replace_file_url(doc_name):
    with open(SAVE_PATH+doc_name+".md","rb+") as f:
        content = f.read().decode()
    start = 0; url_list = []
    while True:
        head = content.find("[",start)
        mid = content.find("(",head)+1
        end = content.find(")",mid)
        if head == -1 or mid == 0 or end == -1: break
        url = content[mid:end]; start = end
        if content[mid:mid+33] != "https://www.yuque.com/attachments": continue
        filename = content[head+1:mid-2]
        url_list.append([url, DOWNLOAD_FILE_PATH+doc_name+"/"+filename])
    for [url,path] in url_list: content = content.replace(url,path)
    with open(SAVE_PATH+doc_name+".md","wb+") as f: f.write(content.encode())
def yuque_main():
    DOC_PATH = ["writeup","default"]
    for doc_path in DOC_PATH:
        all_info = get_all_md_info(doc_path)
        total = len(all_info["data"]); i = 0
        for info in all_info["data"]:
            doc_name = info["slug"]; i += 1
            date = info["created_at"]
            title = info["title"]
            print("[{}][{}/{}]正在下载 {}.md".format(doc_path,i,total,doc_name))
            download_md(doc_path, doc_name)
            replace_img_url(doc_name)
            add_md_info(doc_name, title, date)
            replace_file_url(doc_name)
if __name__ == '__main__':
    yuque_main()