🚧 convert to markdown+mediawiki

2_to_markdown.py

@@ -0,0 +1,104 @@
+import json
+import sys
+from pathlib import Path
+from datetime import timedelta
+import re
+from pathvalidate import validate_filename
+import os
+
+def parse_duration(duration):
+    if not duration:
+        return ""
+    match = re.match(r"PT(?:(\d+)H)?(?:(\d+)M)?", duration)
+    if not match:
+        return duration
+    hours, minutes = match.groups()
+    hours = f"{int(hours)}h " if hours else ""
+    minutes = f"{int(minutes)}m" if minutes else ""
+    return f"{hours}{minutes}".strip()
+
+def format_recipe_to_markdown(recipe):
+    md = []
+
+    # Title
+    md.append(f"# {recipe.get('name', 'Untitled Recipe')}")
+
+    # Description
+    if 'description' in recipe:
+        md.append(f"\n_{recipe['description']}_\n")
+
+    # Metadata
+    time_parts = []
+    if 'prepTime' in recipe:
+        time_parts.append(f"Prep time: {parse_duration(recipe['prepTime'])}")
+    if 'cookTime' in recipe:
+        time_parts.append(f"Cook time: {parse_duration(recipe['cookTime'])}")
+    if 'totalTime' in recipe:
+        time_parts.append(f"Total time: {parse_duration(recipe['totalTime'])}")
+    if 'recipeYield' in recipe:
+        time_parts.append(f"Yield: {recipe['recipeYield']}")
+    if time_parts:
+        md.append('\n**Details:** ' + ' | '.join(time_parts) + '\n')
+
+    # Ingredients
+    if 'recipeIngredient' in recipe:
+        md.append("\n## Ingredients")
+        for ingredient in recipe['recipeIngredient']:
+            md.append(f"- {ingredient}")
+
+    # Instructions
+    if 'recipeInstructions' in recipe:
+        md.append("\n## Instructions")
+        instructions = recipe['recipeInstructions']
+        if isinstance(instructions, list):
+            for i, step in enumerate(instructions, 1):
+                if isinstance(step, dict):
+                    text = step.get('text', '').strip()
+                else:
+                    text = str(step).strip()
+                md.append(f"{i}. {text.replace(chr(10), ' ')}")
+        else:
+            for i, line in enumerate(instructions.strip().split('\n'), 1):
+                if line.strip():
+                    md.append(f"{i}. {line.strip()}")
+
+    # Nutrition
+    if 'nutrition' in recipe:
+        md.append("\n## Nutrition")
+        for key, value in recipe['nutrition'].items():
+            if key != "@type":
+                md.append(f"- **{key.replace('_', ' ').capitalize()}**: {value}")
+
+    return '\n'.join(md)
+
+def main(json_file):
+    with open(json_file, 'r', encoding='utf-8') as f:
+        data = json.load(f)
+
+    # If the JSON-LD is embedded in @graph or a list
+    # if isinstance(data, list):
+    #     recipe = next((item for item in data if item.get('@type') == 'Recipe'), data[0])
+    # elif '@graph' in data:
+    #     recipe = next((item for item in data['@graph'] if item.get('@type') == 'Recipe'), data['@graph'][0])
+    if isinstance(data, list) and data[0].get('@type') == 'Recipe':
+        recipes = data
+    elif data.get('@type') == 'Recipe':
+        recipes = [data]
+    else:
+        print("No Recipe object found in JSON.")
+        return
+
+    for recipe in recipes:
+        markdown_fn = f"{recipe.get('name', 'Untitled Recipe')}.md"
+        validate_filename(markdown_fn) # XXX does this check directory traversal?
+        markdown = format_recipe_to_markdown(recipe)
+        print(markdown)
+        with open(os.path.join("recipes-md", markdown_fn), "w") as f:
+            f.write(markdown)
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print("Usage: python recipe_to_md.py <path_to_recipe_json>")
+    else:
+        main(sys.argv[1])
+