Script to import a JSONFeed file and referenced images to micro.blog.

import-jsonfeed-microblog.py

#!/usr/bin/python3
# -*- coding: utf-8 -*-

import json
import pypandoc
import re
import requests
import os.path
import sys
import time


headers = {
    'Authorization': 'Bearer XXXXXX',
}

count = 0

with open('feed2.json') as f:
  data = json.load(f)


for i in data['items']:
  count = count + 1

  print ("%s" % count)
  print (i['title'])
  print (i['date_published'])

  md = pypandoc.convert_text(i['content_html'], 'md', format='html')

  # print ("Before uploading images...")
  # print (md)

  urls = re.findall(r'(?:https://www.thingelstad.com)?(/assets/[\.\w\d\/\_\-]+)', md)

  for u in urls:
    # Make sure the file exists to upload
    filepath = '.../thingles.github.io%s' % u
    if not os.path.isfile(filepath):
      print ("Cannot find %s" % filepath)
      sys.exit(1)
    else:
      fsize = os.path.getsize(filepath)
      print ("Found %s (%s)..." % (filepath, fsize))

    # Upload the image to micro.blog
    files = {
        'file': (filepath, open(filepath, 'rb')),
    }
    response = requests.post('https://micro.blog/micropub/media', headers=headers, files=files)
    print (response)

    # get location header 
    new_image = response.headers['location']
    print ("%s -> %s" % (u, new_image))

    # input("Press Enter to continue...")

    # Update the markdown to use the new URL
    md = re.sub(rf'(?:https://www.thingelstad.com)?{u}', new_image, md)

    time.sleep(2)

  # print ("After uploading images...")
  # print (md)

  print ("Sending to micro.blog...")
  data = {
    'name': i['title'],
    'content': md,
    'published': i['date_published']
  }
  print (data)
  response = requests.post('https://micro.blog/micropub', headers=headers, data=data)
  print (response.text)

  time.sleep(2)
  # input("Press Enter to continue...")