Created
October 17, 2019 06:23
-
-
Save minikomi/3255a27babeb12c60b61837d4b9ccef7 to your computer and use it in GitHub Desktop.
parsing clippings from kindle into json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| quotes = [q.split("\n") for q in txt.split("==========\n")] | |
| import re | |
| from datetime import datetime | |
| import json | |
| re_page = re.compile("- Your Highlight on page ([\d\-]+)") | |
| re_loc = re.compile(".*Location ([\d\-]+)") | |
| re_date = re.compile("Added on (.*[AM|PM])") | |
| def parse_date(d_str): | |
| return datetime.strptime(d_str, "%A, %B %d, %Y %I:%M:%S %p") | |
| ret = {} | |
| for q in quotes: | |
| a_m = re.findall(r"\(([^\(\)]+)\)", q[0]) | |
| author = a_m[-1] if a_m else None | |
| if author: | |
| book = q[0].replace(" ({})".format(author), "") | |
| else: | |
| book = q[0] | |
| page_m = re.search(re_page, q[1]) | |
| page = page_m[1] if page_m else None | |
| loc_m = re.search(re_loc, q[1]) | |
| loc = loc_m[1] if loc_m else None | |
| date_m = re.search(re_date, q[1]) | |
| date = parse_date(date_m[1]).isoformat() if date_m else None | |
| data = {"date": date, | |
| "page": page, | |
| "loc": loc, | |
| "quote": "\n".join(q[2:]).strip()} | |
| if book not in ret: | |
| ret[book] = {"author": author, | |
| "quotes": [data]} | |
| else: | |
| ret[book]["quotes"].append(data) | |
| print(json.dumps(ret, indent=4, sort_keys = True)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment