告别简书

最近在把简书的内容导出, 以后简书只会用来转帖(也不发布). 他的好处是网上随便粘贴内容, 十分方便. 缺点至今没有处理, 就是他的内容管理.

1. 没有分级目录: 目录多了会乱, 没有分级目录就很傻..
2. 不便于内容搜索: 简书只适于发布, 然后你要搜索自己的内容? Google吧..
3. 没有桌面客户端. 不知道为啥一直不弄个桌面客户端, 手机端倒是有了.

我还是继续用VSCode作笔记管理吧~

附带脚本:　download_jianshu_Image.py, 指定输入目录（简书下载文件）以及输出目录(图片文件存放) 直接下载.
该脚本不能替换md文件中的链接. 不能更改图片后缀.

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

# * Download images file from given website
# * Setup INPUT/OUTPUT firstly.
# * Modify from : https://cloud.tencent.com/developer/article/1599063

import re, requests, os

# 输入文件夹，即 简书导出的 .md 文件位置
INPUT_DIR = '/home/hom/Nutstore/VNote/Jianshu'
# 输出文件夹，即 文章里的图片的下载后的存放位置
OUTPUT_DIR = '/home/hom/Nutstore/VNote/Zimgs/Jianshu'

def ensure_dir_exist(dir_name):
    if not os.path.exists(dir_name):
        os.mkdir(dir_name)


def start_a_file(a_markdown_file, output_dir):
    f = open(a_markdown_file)
    line = f.readline()
    i = 0
    while 1:
        line = f.readline()
        if not line:
            break
        i = i + 1
        ln = line[:-1]
        process_line(ln, output_dir)
    f.close()
    return


def process_line(line, output_dir):
    if line == '':
        return
    img_list = re.findall(r"\!\[[^\]]*\]\((.+?)\)", line, re.S)
    for iu in img_list:
        img_url = iu.split('?')[0]
        print('[Process:]' + img_url)
        if img_url.startswith(('http://', 'https://')) and 'jianshu' in img_url:
            ensure_dir_exist(output_dir)
            download_image_file(img_url, output_dir)
        else:
            print("[ 不合法的 image url]:" + img_url)
    return


def download_image_file(url, output_dir):
    print("# 准备下载...", end=' ')
    r = requests.get(url)
    img = r.content
    print("准备写入...", end=' ')
    new_name = output_dir + "/" + os.path.basename(url)
    with open(new_name, 'wb') as f:
        f.write(img)
        print("写入完成!")
    return


def walk_dir(dir_name):
    for root, dirs, files in os.walk(dir_name):
        relative_name = root.replace(INPUT_DIR, '')
        print('  root={}'.format(relative_name))
        ensure_dir_exist(OUTPUT_DIR + "/" + relative_name)
        for f in files:
            print('   file = {}'.format(f))
            if f.split('.')[-1] != 'md':
                continue
            a_markdown_file = os.path.join(root, f)
            # 生成图片存放的文件夹。
            dir_name = (a_markdown_file.split('/')[-1]).split('.')[0]
            this_file_output_dir = OUTPUT_DIR + '/' + relative_name + '/' + dir_name
            print('   this_file_output_dir = {}'.format(this_file_output_dir))
            # 处理文件
            start_a_file(a_markdown_file, this_file_output_dir)


ensure_dir_exist(OUTPUT_DIR)
walk_dir(INPUT_DIR)

附带一个脚本, 可以将简书导出的笔记转为本地(包括下载图片, 转换本地地址). 支持单文件使用. 批处理请自行修改.

#! /usr/bin/env python
# -*- coding: UTF-8 -*-
#
# * 根据简书的md 文件, 下载图片文件, 用imghdr推断类型

import re, requests, os, sys, imghdr

OUTDIR = '/imgs/Jianshu'  # 替换md 中对应链接为本地目录位置.
DIRECTOUTDIR = False  # 设置False, 下载图片到md文件所在目录, True将下载到OUTDIR

def process_line(line, output_dir):
    if line == '':
        return
    img_list = re.findall(r"\!\[[^\]]*\]\((.+?)\)", line, re.S)
    outfnames = []
    for iu in img_list:
        img_url = iu.split('?')[0]
        print('[Process:]' + img_url)
        if img_url.startswith(('http://', 'https://')) and 'upload-images.jianshu' in img_url:
            dfile = download_image_file(img_url, output_dir)
            if dfile and not os.path.splitext(dfile)[1]:
                ofile = dfile+'.'+imghdr.what(dfile)
                os.rename(dfile, ofile)
                outfnames.append((iu,ofile))
            elif dfile:
                outfnames.append((iu,dfile))
        else:
            print("[ 非简书 image url]:" + img_url)
    return outfnames

def download_image_file(url, output_dir):
    print("# 准备下载...", end=' ')
    r = requests.get(url)
    img = r.content
    print("准备写入...", end=' ')
    new_name = output_dir + "/" + os.path.basename(url)
    with open(new_name, 'wb') as f:
        f.write(img)
        print("写入完成!")
        return new_name

def main():
    f = open(sys.argv[1])
    lines = f.readlines()
    f.close()

    with open(sys.argv[1]+'.tmp', 'w') as f:
        for line in lines:
            if DIRECTOUTDIR:
                out = process_line(line, DIRECTOUTDIR)
            else:
                if os.path.dirname(sys.argv[1]):
                    out = process_line(line, os.path.dirname(sys.argv[1]))
                else:
                    out = process_line(line, '.')

            # Replace markdown contents
            if out:
                for pair_img in out:
                    line = line.replace(pair_img[0], OUTDIR+os.sep+os.path.basename(pair_img[1]))
                f.write(line)
            else:
                f.write(line)
    os.rename(sys.argv[1]+'.tmp', sys.argv[1])

if __name__ == '__main__':
    main()