drew/fabula-ultima-html
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Add core rules

Browse Source
This commit is contained in:
Drew Malzahn
2026-06-06 13:03:00 +00:00
parent c75cd188c1
commit 75c6ab9975
583 changed files with 13580 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
scripts/pdftohtml.py
View File

@@ -30,7 +30,7 @@ def convert_text_to_html(raw_text, model_name="gemma4"):
Requirements:
1. Use appropriate HTML tags (<h1>, <p>, <ul>, <li>, <strong>, etc.) to recreate the structural hierarchy.
2. Add inline CSS or a <style> block in the <head> to make it look professional (modern sans-serif typography, clean margins, and clear layout).
2. Do not add CSS, styling will be added later.
3. Return ONLY valid HTML code. Do not include markdown code block backticks (```html) or extra conversational commentary.
Raw Document Text:
@@ -45,15 +45,16 @@ def convert_text_to_html(raw_text, model_name="gemma4"):
def main():
input_pdf = (
"Fabula_Ultima_-_Natural_Fantasy_Atlas_ENG_v1_1.pdf"
# "Fabula_Ultima_-_Natural_Fantasy_Atlas_ENG_v1_1.pdf"
"Fabula_Ultima_TTJRPG.pdf"
)
try:
from pathlib import Path
Path('./html').mkdir(exist_ok=True)
Path('./html2').mkdir(exist_ok=True)
for page_num, text in enumerate(extract_text_from_pdf(input_pdf)):
html_output = convert_text_to_html(text)
print(f'Writing html/{page_num}.html ({len(text)} bytes)')
with open(f'html/{page_num}.html', 'w') as fh:
print(f'Writing html2/{page_num}.html ({len(text)} bytes)')
with open(f'html2/{page_num}.html', 'w') as fh:
fh.write(html_output)
except FileNotFoundError:
print(f"Error: The file '{input_pdf}' was not found. Please check your path.")