Skip to content

Instantly share code, notes, and snippets.

@SebDeclercq

SebDeclercq/Parsing O'Reilly Highlights.ipynb

Created July 9, 2020 14:44
Show Gist options
  • Save SebDeclercq/d141a8e43ec744b091c75409b04fa43a to your computer and use it in GitHub Desktop.
Save SebDeclercq/d141a8e43ec744b091c75409b04fa43a to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
Parsing O'Reilly Highlights.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"import csv\n",
"from collections import defaultdict\n",
"from typing import DefaultDict, List, Tuple"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"HEADER: str = '''<!DOCTYPE html>\n",
" <html>\n",
" <head>\n",
" <meta http-equiv=\"Content-type\" content=\"text/html;charset=UTF-8\">\n",
" <title>Preface</title>\n",
" <link rel=\"stylesheet\" href=\"https://cdn.jsdelivr.net/npm/[email protected]/dist/katex.min.css\" integrity=\"sha384-yFRtMMDnQtDRO8rLpMIKrtPCD5jdktao2TV19YiZYWMDkUR5GQZR/NOVTdquEx1j\" crossorigin=\"anonymous\">\n",
" <link rel=\"stylesheet\" href=\"https://cdn.jsdelivr.net/gh/Microsoft/vscode/extensions/markdown-language-features/media/markdown.css\">\n",
" <link rel=\"stylesheet\" href=\"https://cdn.jsdelivr.net/gh/Microsoft/vscode/extensions/markdown-language-features/media/highlight.css\">\n",
" <link href=\"https://cdn.jsdelivr.net/npm/katex-copytex@latest/dist/katex-copytex.min.css\" rel=\"stylesheet\" type=\"text/css\">\n",
" <style>\n",
".task-list-item { list-style-type: none; } .task-list-item-checkbox { margin-left: -20px; vertical-align: middle; }\n",
"</style>\n",
" <style>\n",
" body {\n",
" font-family: -apple-system, BlinkMacSystemFont, 'Segoe WPC', 'Segoe UI', 'Ubuntu', 'Droid Sans', sans-serif;\n",
" font-size: 14px;\n",
" line-height: 1.6;\n",
" }\n",
" </style>\n",
" \n",
" <script src=\"https://cdn.jsdelivr.net/npm/katex-copytex@latest/dist/katex-copytex.min.js\"></script>\n",
" </head>\n",
" <body>'''\n",
"\n",
"FOOTER: str = '''\n",
" </body>\n",
" </html>'''\n",
"\n",
"TITLE: str = 'Extreme Programming Explained: Embrace Change, Second Edition'"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [],
"source": [
"highlights: Dict[str, Tuple[str, List[str]]] = {}\n",
"with open('safari-annotations-export.csv', encoding='utf8') as file:\n",
" reader: csv.DictReader = csv.DictReader(file)\n",
" for record in reader:\n",
" title: str = record['Book Title']\n",
" chapter: str = record['Chapter Title']\n",
" highlight: str = record['Highlight']\n",
" if title == TITLE:\n",
" if title not in highlights:\n",
" highlights[title] = [(chapter, [])]\n",
" if highlights[title][-1][0] != chapter:\n",
" highlights[title].append((chapter, [],))\n",
" highlights[title][-1][1].append(highlight)\n",
"\n",
"fname: str = f'{\"Extreme Programming Explained\".replace(\" \", \"-\")}.html'\n",
"with open(fname, 'w', encoding='utf8') as file:\n",
" file.write(HEADER)\n",
" for title, chapter_highlights in highlights.items():\n",
" file.write(f'<h1>{title}</h1>\\n')\n",
" for chapter, highlights_ in chapter_highlights[::-1]:\n",
" file.write(f'<h2>{chapter}</h2>\\n')\n",
" file.write('<ul>\\n')\n",
" for highlight in highlights_:\n",
" file.write('<li>\\n<blockquote>\\n')\n",
" fmt_highlight = ''.join([f'<p>{line}</p>\\n' for line in highlight.split('\\n')])\n",
" file.write(fmt_highlight)\n",
" file.write('</blockquote>\\n</li>\\n')\n",
" file.write('</ul>\\n')\n",
" file.write(FOOTER)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.2"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment