handling some more block types

custom_syadmin/build_from_notion.py

@@ -5,6 +5,7 @@ import shutil
 import subprocess
 import re
 import stat
+from urllib.parse import urlparse, parse_qs
 
 from notion.client import NotionClient
 from notion.markdown import notion_to_markdown
@@ -13,7 +14,7 @@ from notion.markdown import notion_to_markdown
 # Set the variables we'll be allowing for (as CL arg or environment variable)
 vars = {
     "syllabus_db": "https://www.notion.so/memoryspace/594e40c85f2844b5911f14e7db21850f?v=2a2e8a86e8a74d29844f5eef41d18b3f",
-    "syllabus_title": "Pirate Care",
+    "syllabus_title": "Machine Listening",
     "token_v2": "Find the value of 'token_v2' in your browser cookies when logged into Notion",
     "hugo_path": "hugo",
     "hugo_site_path": "/mnt/d/dev/websites/arche-syllabus-test", # The Hugo site
@@ -94,6 +95,25 @@ def hugo(hugo_site_path, dest, hugo_environment='gitea', base_url=None):
     hugo_output = cmd([HUGO_PATH, '-e', hugo_environment, '-d', dest, '--noTimes'], cwd=hugo_site_path, env=env)
 
 
+def hugo_video_shortcode(url):
+    """ Returns the Hugo shortcode for a YouTube or Vimeo url """ 
+    if "youtube.com" in url:
+        try:
+            url_data = urlparse(url)
+            query = parse_qs(url_data.query)
+            video = query["v"][0]
+            return "{{< youtube " + video + " >}}"
+        except:
+            pass
+    elif "vimeo.com" in url:
+        try:
+            video = urlparse(url).path.lstrip("/")
+            return "{{< vimeo " + video + " >}}"
+        except:
+            pass
+    return f"[{url}]({url})"
+
+
 def get_record_text(post, level=0):
     """ Generates the markdown text of a Notion page 
     see: # https://github.com/brentbaum/brentbaum-notion-publishing/blob/master/notion/get_posts.py """
@@ -109,6 +129,12 @@ def get_record_text(post, level=0):
                 text += f"![{caption}]({child.display_source})\n"
             else:
                 text += f"![{caption}]({child.source})\n"
+        elif child.type == "video":
+            caption = f"\n_{child.caption}_" if child.caption else ""
+            text += f"{hugo_video_shortcode(child.source)}{caption}\n\n"
+        elif child.type == "bookmark":
+            caption = f"\n_{child.caption}_" if child.caption else ""
+            text += f"[{child.title}]({child.link}){caption}\n\n"
         elif child.type == "divider":
             text += "---"
         elif child.type == "bulleted_list":
@@ -119,7 +145,7 @@ def get_record_text(post, level=0):
         else:
             prefix = prefixes.get(child.type, "")
             text += prefix + child.title.encode('utf-8').decode('utf-8') + "\n\n"
-    
+    print(text)
     text = re.sub('`(bib|session|topic):([a-zA-Z0-9-]+)`', r'![](\1:\2)', text)
     return text
 
@@ -190,7 +216,7 @@ def notion_to_md(id, filepath=None, yaml_func=None):
     # print(page_data)
     if filepath:
         os.umask(0)
-        with open(os.open(filepath, os.O_CREAT | os.O_WRONLY, 0o777), 'w', encoding="utf-8") as f:
+        with open(os.open(filepath, os.O_CREAT | os.O_WRONLY, 0o777), 'w') as f:
             f.write(page_content)
     return page_data