Update generate_post.py

generate_post.py

@@ -1,5 +1,6 @@
 import os
 import csv
+import re
 import requests
 from bs4 import BeautifulSoup
 from fpdf import FPDF
@@ -7,31 +8,30 @@ from fpdf import FPDF
 # -------------------------------------------------------------------------
 # CODE & CANVAS BRAND DESIGN TOKENS
 # -------------------------------------------------------------------------
-COLOR_LINEN = (250, 248, 245)      # #FAF8F5 - Default background canvas[span_2](start_span)[span_2](end_span)
+COLOR_LINEN = (250, 248, 245)      # #FAF8F5 - Default background canvas
-COLOR_NAVY = (26, 35, 50)          # #1A2332 - Deep structural headers[span_3](start_span)[span_3](end_span)
+COLOR_NAVY = (26, 35, 50)          # #1A2332 - Deep structural base color
-COLOR_TERRACOTTA = (211, 107, 77)  # #D36B4D - Primary visual accents[span_4](start_span)[span_4](end_span)
+COLOR_TERRACOTTA = (211, 107, 77)  # #D36B4D - Primary visual accents
-COLOR_CHARCOAL = (43, 43, 43)      # #2B2B2B - High-legibility body text[span_5](start_span)[span_5](end_span)
+COLOR_CHARCOAL = (43, 43, 43)      # #2B2B2B - High-legibility body text
-COLOR_BORDER = (229, 222, 201)     # #E5DEC9 - Thin muted gridlines[span_6](start_span)[span_6](end_span)
+COLOR_BORDER = (229, 222, 201)     # #E5DEC9 - Thin muted gridlines
 
-CSV_URL = "https://raw.githubusercontent.com/CodeAndCanvas728/repobase/refs/heads/main/RepoDatabase.csv"
+LOCAL_CSV_PATH = "RepoDatabase.csv"
+REMOTE_CSV_URL = "https://raw.githubusercontent.com/CodeAndCanvas728/repobase/refs/heads/main/RepoDatabase.csv"
 
 class CodeCanvasPDF(FPDF):
     def header(self):
-        # Establish Editorial Minimalism and generous margins
         self.set_fill_color(*COLOR_LINEN)
         self.rect(0, 0, 210, 297, 'F')
         
-        # Subtle top accent line instead of heavy borders
         self.set_draw_color(*COLOR_BORDER)
         self.set_line_width(0.5)
         self.line(15, 15, 195, 15)
         
-        # Standalone Ampersand Shorthand as the brand anchor
+        # Standalone Ampersand Shorthand
         self.set_text_color(*COLOR_TERRACOTTA)
-        self.set_font("Times", "I", 16) # Elegant serif substitution for Georgia
+        self.set_font("Times", "I", 16) # Classic serif
         self.text(15, 25, "&")
         self.set_text_color(*COLOR_NAVY)
-        self.set_font("Helvetica", "B", 8) # Sans-serif for technical meta-tags
+        self.set_font("Helvetica", "B", 8) # Sans-serif technical data
         self.text(23, 23, "CODE & CANVAS | INSIGHTS")
 
     def footer(self):
@@ -40,18 +40,44 @@ class CodeCanvasPDF(FPDF):
         self.text(185, 285, f"Page {self.page_no()}")
 
 def clean_typography(text):
-    """Enforces the strict micro-styling rule: Absolutely no em-dashes."""
+    """Enforces absolute purity of text: No unicode or markdown em-dashes."""
     return text.replace("—", " : ").replace("--", " - ")
 
-def fetch_subject():
+def fetch_and_update_subject():
-    try:
+    """Reads local repository CSV to find an unused row, updates it to 'yes', 
-        response = requests.get(CSV_URL, timeout=10)
+    and writes it back immediately to prevent duplicate scheduling entries."""
-        if response.status_code == 200 and response.text.strip():
+    rows = []
-            lines = response.text.splitlines()
+    selected_subject = None
-            reader = csv.DictReader(lines)
+    file_exists_locally = os.path.exists(LOCAL_CSV_PATH)
+    
+    # 1. Read Database Data
+    if file_exists_locally:
+        with open(LOCAL_CSV_PATH, mode='r', newline='', encoding='utf-8') as f:
+            reader = csv.DictReader(f)
+            fieldnames = reader.fieldnames
             for row in reader:
-                if row.get('Used', '').lower() == 'no':
+                # Find the first unused item matching criteria
-                    return {
+                if not selected_subject and row.get('Used', '').strip().lower() == 'no':
+                    row['Used'] = 'yes'  # State Update Mutation
+                    selected_subject = {
+                        "title": row['Title'],
+                        "desc": row['Description'],
+                        "points": [row['Point1'], row['Point2'], row['Point3']],
+                        "url": row.get('URL', f"https://github.com/search?q={row['Title']}")
+                    }
+                rows.append(row)
+    else:
+        # Fallback tracking if working outside local repository layout
+        print("Warning: Local RepoDatabase.csv not found. Reverting to remote live endpoint.")
+        try:
+            res = requests.get(REMOTE_CSV_URL, timeout=10)
+            if res.status_code == 200:
+                lines = res.text.splitlines()
+                reader = csv.DictReader(lines)
+                fieldnames = reader.fieldnames
+                for row in reader:
+                    if not selected_subject and row.get('Used', '').strip().lower() == 'no':
+                        selected_subject = {
                             "title": row['Title'],
                             "desc": row['Description'],
                             "points": [row['Point1'], row['Point2'], row['Point3']],
@@ -60,62 +86,76 @@ def fetch_subject():
         except Exception:
             pass
 
-    # Fallback Logic: Scrape GitHub Trending AI/LLM Python/Go repositories
+    # 2. Save Updated Database State if modified locally
+    if selected_subject and file_exists_locally:
+        with open(LOCAL_CSV_PATH, mode='w', newline='', encoding='utf-8') as f:
+            writer = csv.DictWriter(f, fieldnames=fieldnames)
+            writer.writeheader()
+            writer.writerows(rows)
+        return selected_subject
+
+    # 3. Dynamic GitHub Scraping Fallback Routine
+    if not selected_subject:
+        print("Database exhausted or unreachable. Querying trending open-source indexes...")
         try:
             fb_res = requests.get("https://github.com/trending", timeout=10)
             soup = BeautifulSoup(fb_res.text, 'html.parser')
             repo = soup.find('article', class_='Box-row')
-        title = repo.find('h2', class_='h3').text.strip().replace('\n', '').replace(' ', '')
+            raw_title = repo.find('h2', class_='h3').text.strip().replace('\n', '').replace(' ', '')
             desc = repo.find('p', class_='col-9').text.strip()
             return {
-            "title": title,
+                "title": raw_title.split('/')[-1],
                 "desc": desc,
-            "points": ["Open-source community standard", "Highly scalable architecture", "Streamlined local environment deployment"],
+                "points": ["Open-source workflow standard", "Highly modular architectural design", "Streamlined environment footprint"],
-            "url": f"https://github.com/{title}"
+                "url": f"https://github.com/{raw_title}"
             }
         except Exception:
+            # Absolute hard-fail recovery state
             return {
                 "title": "Model Context Protocol",
-            "desc": "An open standard enabling secure, structured data communication layers between local environments and LLMs.",
+                "desc": "An open standard enabling secure, structured data communication layers between local environments and generative applications.",
-            "points": ["Eliminates custom integration glue code", "Maintains clean architectural boundaries", "Built for developer tool interoperability"],
+                "points": ["Eliminates custom integration glue code", "Maintains clear architectural boundaries", "Built for cross-tool interoperability"],
                 "url": "https://github.com/modelcontextprotocol"
             }
 
 def generate_assets():
-    data = fetch_subject()
+    data = fetch_and_update_subject()
     title = clean_typography(data['title'])
     desc = clean_typography(data['desc'])
     points = [clean_typography(p) for p in data['points']]
     
+    # Target path configuration
+    os.makedirs("_drafts", exist_ok=True)
+    safe_date = "weekly-draft"
+    
     # -------------------------------------------------------------------------
-    # 1. GENERATE THE BRANDED PDF
+    # PDF COMPILATION BLOCK
     # -------------------------------------------------------------------------
     pdf = CodeCanvasPDF()
     pdf.set_margins(15, 30, 15)
     pdf.add_page()
     
-    # Title Layout (High-contrast Serif Display Style)
+    # Header display layout
     pdf.set_y(40)
     pdf.set_text_color(*COLOR_NAVY)
-    pdf.set_font("Times", "", 28) # Georgia alternative
+    pdf.set_font("Times", "", 26)
     pdf.multi_cell(180, 12, title)
     
-    # Accent Divider Line
+    # Layout dividing grid rules
     pdf.set_draw_color(*COLOR_BORDER)
     pdf.line(15, pdf.get_y() + 5, 80, pdf.get_y() + 5)
     
-    # Brief Informational Summary
+    # Copy layout execution
     pdf.set_y(pdf.get_y() + 15)
     pdf.set_text_color(*COLOR_CHARCOAL)
-    pdf.set_font("Helvetica", "", 11) # Sans-serif structural body text
+    pdf.set_font("Helvetica", "", 11)
     pdf.multi_cell(180, 7, desc)
     
-    # Structured Grid for Key Highlights
+    # Balanced spacing grids for parameters
     pdf.set_y(pdf.get_y() + 15)
     for idx, pt in enumerate(points, 1):
         pdf.set_draw_color(*COLOR_BORDER)
         pdf.set_fill_color(*COLOR_LINEN)
-        # Structural thin-bordered card layouts
         pdf.rect(15, pdf.get_y(), 180, 18, 'DF')
         
         pdf.set_x(20)
@@ -128,11 +168,11 @@ def generate_assets():
         pdf.cell(160, 18, pt)
         pdf.set_y(pdf.get_y() + 22)
         
-    pdf_filename = "linkedin_insight_asset.pdf"
+    pdf_path = f"_drafts/{safe_date}.pdf"
-    pdf.output(pdf_filename)
+    pdf.output(pdf_path)
     
     # -------------------------------------------------------------------------
-    # 2. GENERATE LINKEDIN POST COPY
+    # MARKDOWN CONVERSION BLOCK
     # -------------------------------------------------------------------------
     post_copy = f"""💡 Weekly AI Architecture Breakdown
 
@@ -152,10 +192,11 @@ Repository Link: {data['url']}
 
 #SoftwareArchitecture #DeveloperTools #TechInsights #CodeAndCanvas"""
 
-    print("--- LINKEDIN POST DRAFT ---")
+    md_path = f"_drafts/{safe_date}.md"
-    print(post_copy)
+    with open(md_path, mode='w', encoding='utf-8') as f:
-    print("\n--- ASSET STATUS ---")
+        f.write(post_copy)
-    print(f"Success: {pdf_filename} generated inside your directory following brand design guidelines.")
+
+    print(f"Workflow Complete: Created tracking drafts inside configuration paths.")
 
 if __name__ == "__main__":
     generate_assets()