{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from weasyprint import HTML, CSS\n",
"from weasyprint.fonts import FontConfiguration\n",
"import nltk\n",
"\n",
"font_config = FontConfiguration()\n",
"\n",
"txt = open('txt/practicalvision.txt').read()\n",
"words = nltk.word_tokenize(txt) #tokenizing the text\n",
"tagged_words = nltk.pos_tag(words) #generating grammar tags for the tokens\n",
"\n",
"content = ''\n",
"content += 'Practical Vision, by Jalada
'\n",
"\n",
"\n",
"for word, tag in tagged_words:\n",
" content += f'{word} ' #for every word, generate an html tag wich includes the grammar tag as class\n",
" if '.' in word:\n",
" content += '
\\n'\n",
"\n",
"with open(\"txt/practical_viz.html\", \"w\") as f: #save as html\n",
" f.write(f\"\"\"\n",
"\n",
"\n",
" \n",
" \n",
" \n",
"\n",
"\n",
"{content}\n",
"\n",
"\"\"\")\n",
"\n",
"html = HTML(\"txt/practical_viz.html\") #define as HTML the genereted html file\n",
"\n",
"css = CSS(string=''' \n",
" body{\n",
" size: A4;\n",
" font-family: serif;\n",
" font-size: 12pt;\n",
" line-height: 1.4;\n",
" padding: 3vw;\n",
" color: rgba(0,0,0,0)\n",
" }\n",
" h1{\n",
" width: 100%;\n",
" text-align: center;\n",
" font-size: 250%;\n",
" line-height: 1.25;\n",
" color: black;\n",
" \n",
" }''', font_config=font_config) #define CSS for print final A4 pdf\n",
"\n",
"html.write_pdf('practical_viz.pdf', stylesheets=[css], font_config=font_config) #generate A4 pdf"
]
},
{
"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": "3.8.6"
}
},
"nbformat": 4,
"nbformat_minor": 4
}