Skip to content

Instantly share code, notes, and snippets.

@SebDeclercq

SebDeclercq/oreilly-export-csv2html.py

Created July 10, 2020 13:42
Show Gist options
  • Save SebDeclercq/6f2653719e4ee3852a635f84f1a22ed1 to your computer and use it in GitHub Desktop.
Save SebDeclercq/6f2653719e4ee3852a635f84f1a22ed1 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
oreilly-export-csv2html.py
from collections import defaultdict
from pathlib import Path
from typing import ClassVar, DefaultDict, List, Tuple
import csv
import re
class Book:
'''Class representing a book w/ some of the metadata available
in the safari-annotations-export.csv file
Attrs:
title: The title (duh)
slug: The slug to use for the filename (for instance)
html_filename: The filename to use for the HTML export
chapters: The **ordered** list of the book's chapters
highlights: A list of the highlights, chapter by chapter
'''
def __init__(self, *, title: str, slug: str = '') -> None:
self.title: str = title
self.slug: str = slug
self.chapters: List[str] = []
self.highlights: DefaultDict[str, List[str]] = defaultdict(list)
if not self.slug:
self.slug = re.sub(r'[^\W]', '-', self.title)
self.html_filename: Path = Path(f'{self.slug}.html')
@property
def to_html(self) -> None:
'''Export the highlights to HTML'''
OReillyCSV2HTML.export_to_html(self)
class OReillyCSV2HTML:
'''safari-annotations-export.csv file parser'''
OREILLY_EXPORT_FILENAME: Path = Path('safari-annotations-export.csv')
HEADER: str = '''<!DOCTYPE html>
<html>
<head>
<meta http-equiv="Content-type" content="text/html;charset=UTF-8">
<title>HTML_TITLE</title>
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/[email protected]/dist/katex.min.css" integrity="sha384-yFRtMMDnQtDRO8rLpMIKrtPCD5jdktao2TV19YiZYWMDkUR5GQZR/NOVTdquEx1j" crossorigin="anonymous">
<link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/Microsoft/vscode/extensions/markdown-language-features/media/markdown.css">
<link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/Microsoft/vscode/extensions/markdown-language-features/media/highlight.css">
<link href="https://cdn.jsdelivr.net/npm/katex-copytex@latest/dist/katex-copytex.min.css" rel="stylesheet" type="text/css">
<style>
.task-list-item { list-style-type: none; } .task-list-item-checkbox { margin-left: -20px; vertical-align: middle; }
</style>
<style>
body {
font-family: -apple-system, BlinkMacSystemFont, 'Segoe WPC', 'Segoe UI', 'Ubuntu', 'Droid Sans', sans-serif;
font-size: 14px;
line-height: 1.6;
}
</style>
<script src="https://cdn.jsdelivr.net/npm/katex-copytex@latest/dist/katex-copytex.min.js"></script>
</head>
<body>'''
FOOTER: str = '''
</body>
</html>'''
@classmethod
def get_highlights(cls, book: Book) -> Book:
'''Parse the csv file in order to collect all the highlights
for a specific book.
Params:
book: The book to search for.
Returns:
The book fed w/ its chapters & highlights.
'''
with cls.OREILLY_EXPORT_FILENAME.open(encoding='utf8') as file:
reader: csv.DictReader = csv.DictReader(file)
for record in reader:
if record['Book Title'] == book.title:
chapter: str = record['Chapter Title']
highlight: str = record['Highlight']
if chapter not in book.chapters:
book.chapters.insert(0, chapter)
book.highlights[chapter].append(highlight)
return book
@classmethod
def export_to_html(cls, book: Book) -> None:
'''Export a book to HTML.
Params:
book: The book to export
'''
with book.html_filename.open('w', encoding='utf8') as file:
file.write(cls.HEADER.replace('HTML_TITLE', book.title))
file.write(f'<h1>{book.title}</h1>\n')
for chapter in book.chapters:
file.write(f'<h2>{chapter}</h2>\n')
file.write('<ul>\n')
for highlight in book.highlights[chapter]:
file.write('<li>\n<blockquote>\n')
fmt_highlight = ''.join([f'<p>{line}</p>\n' for line in highlight.split('\n')])
file.write(fmt_highlight)
file.write('</blockquote>\n</li>\n')
file.write('</ul>\n')
file.write(cls.FOOTER)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment