stash

_content/monographs/debt_graeber-david.md

@@ -3,6 +3,8 @@ title: "Debt: The First 5000 Years"
 authors:
   - graeber-david
 course: economics
+external_url: "https://archive.org/details/DebtTheFirst5000Years/page/n2/mode/1up"
+alternative_link: "https://warwick.ac.uk/fac/arts/english/currentstudents/undergraduate/modules/fulllist/special/statesofdamage/syllabus201516/graeber-debt_the_first_5000_years.pdf"
 status: featured
 olid: OL27883779M
 tags:

_content/monographs/phoenix-complex_marder-michael.md

@@ -8,6 +8,7 @@ drive_links:
   - "https://drive.google.com/file/d/1ytSlb0gASNrU3vyoktnkEH7BbYbeerp8/view?usp=drivesdk"
 tags:
   - mythology
+  - natural
   - time
 year: 2023
 olid: OL42751992M

_tags/books.md

@@ -1,7 +1,7 @@
 ---
 title: "The Book"
 status: unpublished
-parents: [things, media]
+parents: [media]
 ---
 
 The history of bound pages.

_tags/media.md

@@ -2,7 +2,7 @@
 title: "Media Studies"
 hashtag: "mediaStudies"
 status: unpublished
-parents: [communication]
+parents: [communication, things]
 ---
 
 The study of how different forms of communication afford different communication styles and thus alter how people think.

scripts/android_import_sutta.py

@@ -13,8 +13,7 @@
 from gdrive import upload_to_google_drive, get_gfolders_for_course, get_known_courses, create_drive_shortcut, DRIVE_LINK
 from archivedotorg import save_url_to_archiveorg
 from pdfutils import readpdf, get_page_count
-# Bypassing for now due to SciPy crash
-# from tag_predictor import TagPredictor
+from tag_predictor import TagPredictor
 
 yaml_list_prefix = '\n  - '
 NONSC_TRANSLATORS = [{
@@ -229,7 +228,7 @@ def process_pdf(pdf_file):
   print(f"Processing {pdf_file}...")
   pdf_file = Path(pdf_file)
   pages = get_page_count(pdf_file)
-  # pdf_text = readpdf(pdf_file)
+  pdf_text = readpdf(pdf_file)
   guess = guess_id_from_filename(pdf_file.stem)
   while True:
     sutta = input_with_prefill("Sutta ID? ", guess)
@@ -244,8 +243,7 @@ def process_pdf(pdf_file):
     if not prompt("File already exists! Continue anyway?"):
       return
   blurb = get_blurb_for_suttaid(slug) or ''
-  # course = TagPredictor.load().predict([blurb + ' ' + pdf_text])[0]
-  course = ''
+  course = TagPredictor.load().predict([blurb + ' ' + pdf_text])[0]
   parsed = sutta_id_re.match(slug)
   book = parsed.group(1)
   nums = [parsed.group(2), parsed.group(3)]

scripts/gdrive.py

@@ -571,11 +571,9 @@ def _yt_thumbnail(snippet):
   return snippet['thumbnails']['default']['url']
 
 def make_ytvideo_summary_html(vid):
-  # temporarily bypass caching during SciPy bug
-  # from tag_predictor import YOUTUBE_DATA_FOLDER
-  # cachef = YOUTUBE_DATA_FOLDER.joinpath(f"{vid}.json")
-  # if cachef.exists():
-  if False:
+  from tag_predictor import YOUTUBE_DATA_FOLDER
+  cachef = YOUTUBE_DATA_FOLDER.joinpath(f"{vid}.json")
+  if cachef.exists():
     snippet = json.loads(cachef.read_text())
     transcript = snippet.get('transcript',[])
   else:
@@ -586,7 +584,7 @@ def make_ytvideo_summary_html(vid):
       snippet['transcript'] = transcript
     except:
       pass
-    # cachef.write_text(json.dumps(snippet))
+    cachef.write_text(json.dumps(snippet))
   return _make_ytvideo_summary_html(vid, snippet, transcript)
 
 def _make_ytvideo_summary_html(vid, snippet, transcript):