diff options
Diffstat (limited to 'app/books/kindleparser.py')
| -rw-r--r-- | app/books/kindleparser.py | 57 |
1 files changed, 57 insertions, 0 deletions
diff --git a/app/books/kindleparser.py b/app/books/kindleparser.py new file mode 100644 index 0000000..b2f0191 --- /dev/null +++ b/app/books/kindleparser.py @@ -0,0 +1,57 @@ +""" +kindle My Clippings.txt parsed to json by: +klip: https://www.npmjs.org/package/klip +This script then parses that json and tries to load it into the django database +""" +import json +import datetime +from django.core.exceptions import ObjectDoesNotExist +from books.models import Book, BookHighlights + +def parse_kindle_clippings(path): + json_data = open(path) + data = json.load(json_data) + for item in data: + for clip in item['clippings']: + if clip["type"] != "Bookmark": + book = clip['title'] + clip_date = datetime.datetime.strptime(clip['date'], "%Y-%m-%dT%H:%M:%S.000Z") + try: + body_markdown = clip['content'] + except KeyError: + body_markdown = "" + try: + location = int(clip['locationRange']) + except: + location = 0 + try: + page = int(clip['pageRange']) + except: + page = 0 + try: + author_name = clip['author'] + except KeyError: + author_name = '' + try: + #see if we already have this book: + row = Book.objects.get(title=clip['title']) + except ObjectDoesNotExist: + b, created = Book.objects.get_or_create( + title = clip['title'], + author_name = author_name, + read_date = clip_date + ) + try: + #see if we already this highlight + row = BookHighlights.objects.get(book__title=clip['title'], date_added=clip_date ) + #if we don't create a new book highlight + except ObjectDoesNotExist: + book = Book.objects.get(title=clip['title']) + bh, created = BookHighlights.objects.get_or_create( + book = book, + page = page, + location = location, + date_added = clip_date, + body_markdown = body_markdown + ) + |