前言

描述

有时写Markdown会把图片放在图床，而且图床上传图片后会改变图片的名称，想要下载下来备份并不是很方便，不如写个程序自动保存一下，以后不想用图床了还可以把图片直接放在自己的服务器，这时只需要批量对图片地址进行替换。

举例

像这样，我使用了hello图床

hello图床（https://www.helloimg.com/）

但是当我像把图片放到服务器上，不再用图床了，就得这样改

即将https://www.helloimg.com/images/2021/02/10替换成/static/post

前提是图片名称和在图床上一样

那么如何保持一样？直接从图床上下载图片就好

这个程序就是替你完成这个工作

开始

程序

Python3程序

'''
Author: lx56
Blog: https://blog.lxscloud.top
'''
import time
import requests
import os

mddir = './md/' #设置根路径
dldir = './dl/'
markdown_setup = ["![", "](", ")"]
download_list = ["https://", "http://"]
ext_name = ["md"]
headers = {
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36"
}

def checkdir_andcreate(dir_path_set):
  if dir_path_set[-1:] == "":
    dir_path_set = dir_path_set[0:-1]
  if os.path.isdir(dir_path_set) == False:
    os.mkdir(dir_path_set)
    

def file_size_trans(filesize_input_B):
  precent_unit = ''
  # KB
  if 1024 <= filesize_input_B < (1024 ** 2):
     precent_unit = 'KB'
     filesize_input_B = filesize_input_B / 1024
  # MB
  elif (1024 ** 2) <= filesize_input_B < (1024 ** 3):
     precent_unit = 'MB'
     filesize_input_B = filesize_input_B / (1024 ** 2)
  # GB
  elif (1024 ** 3) <= filesize_input_B < (1024 ** 4):
     precent_unit = 'GB'
     filesize_input_B = filesize_input_B / (1024 ** 3)
  # TB
  elif (1024 ** 4) <= filesize_input_B < (1024 ** 5):
     precent_unit = 'TB'
     filesize_input_B = filesize_input_B / (1024 ** 4)
  # B
  else:
     precent_unit = 'Byte'
  r_info = "{:.1f}".format(filesize_input_B) + ' ' + precent_unit
  return r_info

def download_file_with_speed(download_url, dirset = "."):
  dirset += "/"
  
  filepath = dirset + download_url[download_url.rindex("/")+1:]
  if os.path.isfile(filepath): 
    print("File exists, skip....")
    return
  # 流式请求下载地址并以下载名保存文件
  with requests.get(download_url, stream=True, headers=headers) as r, open(filepath, 'wb') as file:
    # 获得文件的大小，单位字节B
    total_size = int(r.headers['content-length'])
    # 已下载的字节大小
    content_size = 0
    # 进度下载完成的百分比
    process_p = 0
    # 记录开始时间
    start_time = time.time()
    # 到上一秒的下载的文件大小
    temp_size = 0
    # 开始下载每次请求1024字节
    for content in r.iter_content(chunk_size=1024):
        file.write(content)
        # 更新下载大小
        content_size += len(content)
        # 计算下载进度
        process_p = (content_size / total_size) * 100
        # 每一秒统计一次下载量
        if time.time() - start_time > 1:
            # 重置开始时间
            start_time = time.time()
            # 每秒的下载量
            speed = content_size - temp_size
            print('Process: {:.1f}% Speed: {}/S'.format(process_p, file_size_trans(speed)))
            # 重置以下载大小
            temp_size = content_size
            
    print('100% Size: {}'.format(file_size_trans(total_size)))


def check_mark(str_line, list_check, mode_check):
  resault_check = False
  for i in list_check:
    if mode_check == True:
      resault_check = True
      try:
        str_line.index(i)
      except:
        resault_check = False
        break
    elif mode_check == False:
      resault_check = False
      state = 0
      try:
        str_line.index(i)
        state = 1
      except:
        state = 0
      if state == 1:
        resault_check = True
        break
    else:
      resault_check = False
  return resault_check

def read_and_find(file_name):
  f1_n = file_name
  dir_set = dldir + f1_n[f1_n.rindex("/")+1:f1_n.rindex(".")]
  try:
    if os.path.isdir(dir_set) == False:
        os.mkdir(dir_set)
    dir_set_ok = True
  except:
    print("Dir create fail")
    dir_set_ok = False
  if dir_set_ok:
    try:
      file_processing = open(file_name, 'r', encoding = 'utf-8') 
      for line in file_processing.readlines():
        lines = str(line)
        if check_mark(lines, markdown_setup, True) == True:
          http_l = lines.index("](") + 2
          http_r = lines.index(")", http_l)
          pic_http_addr = lines[http_l:http_r]
        
          if check_mark(pic_http_addr,download_list , False):
            print("Try to download:", pic_http_addr)
            #下载文件
            try:
              download_file_with_speed(pic_http_addr, dir_set)
              print()
            except Exception as e:
              print("Err download:", pic_http_addr, f"err={e}")
              print()
      file_processing.close()
      return True
    except:  
      print("Err at read file :", file_name)
      return False

checkdir_andcreate(dldir)
checkdir_andcreate(mddir)

dict_pic_path = []
list = os.listdir(mddir) #列出文件夹下所有的目录与文件
for i in range(0,len(list)):
       path = os.path.join(mddir,list[i])
       if os.path.isfile(path):
         str_path = str(path)
         str_path = str_path[str_path.rfind(".")+1:]
         for i in ext_name: #忽略不在白名单的扩展名
          if str_path == i:
           #print(path)
           dict_pic_path.append(path)
           break

for i in dict_pic_path:
  print("File:", i)
  print("-----------------------------------")
  read_and_find(i)
  print("-----------------------------------\n")