🤖 Automated Diachronic Workflow

# automated_workflow.py import urllib.request import json from pathlib import Path class DiachronicAutomation: def __init__(self): self.corpus_dir = Path("AthensDiaLingCorpus") self.corpus_dir.mkdir(exist_ok=True) # Fixed Perseus URLs self.perseus_texts = { 'iliad': 'urn:cts:greekLit:tlg0012.tlg001.perseus-grc2:1.1', 'odyssey': 'urn:cts:greekLit:tlg0012.tlg002.perseus-grc2:1.1', 'nt_matthew': 'urn:cts:greekLit:tlg0031.tlg001.perseus-grc2:1.1', 'aeneid': 'urn:cts:latinLit:phi0690.phi003.perseus-lat2:1.1' } def collect_perseus_text(self, text_key): """Auto-collect from Perseus with fixed URLs""" if text_key in self.perseus_texts: urn = self.perseus_texts[text_key] url = f"https://scaife-cts.perseus.org/api/cts?request=GetPassage&urn={urn}" try: with urllib.request.urlopen(url) as response: data = response.read().decode('utf-8') print(f"✅ Downloaded {text_key}") return data except Exception as e: print(f"❌ Error: {e}") # Fallback to web interface print(f"Visit: https://scaife.perseus.org/reader/{urn}") return None def parse_text(self, text): """Basic parsing""" # Tokenize tokens = text.split() # Basic word frequency freq = {} for token in tokens: freq[token] = freq.get(token, 0) + 1 return {"tokens": len(tokens), "unique": len(freq), "frequency": freq} def run_workflow(self, text_key): print(f"🚀 Starting automated workflow for {text_key}") # Step 1: Collect print("📚 Collecting text...") text = self.collect_perseus_text(text_key) if text: # Step 2: Parse print("🔍 Parsing...") parsed = self.parse_text(text) # Step 3: Save print("💾 Saving results...") output_path = self.corpus_dir / f"{text_key}_results.json" with open(output_path, 'w', encoding='utf-8') as f: json.dump(parsed, f, indent=2, ensure_ascii=False) print(f"✅ Complete! Results saved to {output_path}") return parsed else: print("❌ Collection failed. Please use web interface.") # Usage automation = DiachronicAutomation() automation.run_workflow("iliad")