Update app.py

app.py

@@ -1,231 +1,240 @@
-import os
-import re
-import json
-import io
-import datetime as dt
-import pandas as pd
-import streamlit as st
-from dotenv import load_dotenv
-import google.generativeai as genai
-
-# --- Setup ---
-load_dotenv()
-DEFAULT_MODEL = "gemini-1.5-flash"
-
-def configure_gemini(api_key: str):
-    """Initializes the Gemini client with the provided API key."""
-    genai.configure(api_key=api_key)
-
-# --- Utilities ---
-def extract_json(text: str) -> dict:
-    """
-    Pulls a JSON object from a string, even if it's wrapped in markdown code fences.
-    Returns a Python dictionary or raises an error if parsing fails.
-    """
-    if not text:
-        raise ValueError("Received an empty response from the model.")
-    
-    # Look for JSON within ```json ... ``` markdown block
-    match = re.search(r"```json\s*(.*?)\s*```", text, re.DOTALL)
-    if match:
-        json_str = match.group(1)
-    else:
-        # Fallback: find the first '{' and last '}'
-        start = text.find('{')
-        end = text.rfind('}')
-        if start == -1 or end == -1:
-            raise json.JSONDecodeError("No JSON object found in the response text.", text, 0)
-        json_str = text[start:end+1]
-    
-    return json.loads(json_str)
-
-def seconds_to_ts(s: int) -> str:
-    """Converts an integer of seconds to a MM:SS timestamp string."""
-    m, sec = divmod(int(s), 60)
-    return f"{m:02d}:{sec:02d}"
-
-def make_prompt(topic: str, idea_count: int, total_seconds: int, scene_count: int) -> str:
-    """Creates the detailed, structured prompt for the generative model."""
-    return f"""
-You are a YouTube Shorts producer for "Contentmaniacs" (nature, cosmos, paradoxes, AI).
-Goal: Create viral, factual, poetic-science Shorts with clear visuals.
-
-Generate EXACTLY {idea_count} ideas for topic: "{topic}".
-
-Return ONLY a single, valid JSON object (no markdown). The root object must contain one key, "ideas", which is a list of idea objects.
-
-The schema for each idea object in the list is:
-{{
-  "title": "string (<= 60 chars, no quotes)",
-  "keywords": ["kw1","kw2","kw3"],
-  "description": "1–2 lines, SEO-rich, natural language",
-  "hashtags": ["Shorts","YouTubeShorts","Contentmaniacs","<up to 7 topical>"],
-  "thumbnail_prompt": "clear 9:16 visual brief (no text)",
-  "video_plan": {{
-    "duration_seconds": {total_seconds},
-    "scenes_count": {scene_count},
-    "scenes": [
-      {{
-        "scene_no": 1,
-        "start_sec": 0,
-        "end_sec": 0,
-        "voiceover": "1–2 punchy lines, simple language",
-        "on_screen_text": "few words, optional, no hashtags",
-        "visual_direction": "what to show (subject, motion, environment, mood, lighting)",
-        "shot_type": "macro | wide | medium | timelapse | drone | slow-mo | infographic",
-        "prompt": "text-to-video/image prompt for Canva/Runway (no text overlay)",
-        "broll_ideas": ["alt idea 1","alt idea 2"],
-        "sfx_music": "sound design notes (subtle, cinematic, ambient, etc.)"
-      }}
-    ]
-  }},
-  "full_transcript": "Combine all voiceover lines into a clean 45–60s transcript."
-}}
-
-RULES:
-- Factual, inspiring, no clickbait lies.
-- Keep each scene's voiceover short (<= 18 words).
-- Distribute time evenly across scenes so end_sec of last scene == duration_seconds.
-- Output MUST be a single, valid JSON object only.
-"""
-
-def idea_json_to_overview_rows(topic: str, idea: dict) -> dict:
-    """Creates a dictionary for the overview DataFrame from a single idea JSON."""
-    return {
-        "Topic": topic,
-        "Title": (idea.get("title") or "").strip(),
-        "Keywords": ", ".join(idea.get("keywords") or []),
-        "Description": (idea.get("description") or "").strip(),
-        "Hashtags": " ".join(("#" + h.lstrip("#")) for h in (idea.get("hashtags") or [])),
-        "ThumbnailPrompt": (idea.get("thumbnail_prompt") or "").strip(),
-        "DurationSec": idea.get("video_plan", {}).get("duration_seconds", "")
-    }
-
-def idea_json_to_scenes_df(topic: str, idea: dict) -> pd.DataFrame:
-    """Creates a DataFrame for the scene-by-scene shot list."""
-    scenes = idea.get("video_plan", {}).get("scenes", []) or []
-    rows = []
-    for sc in scenes:
-        rows.append({
-            "Topic": topic,
-            "Title": idea.get("title", ""),
-            "SceneNo": sc.get("scene_no", ""),
-            "Start": seconds_to_ts(sc.get("start_sec", 0)),
-            "End": seconds_to_ts(sc.get("end_sec", 0)),
-            "Voiceover": (sc.get("voiceover") or "").strip(),
-            "OnScreenText": (sc.get("on_screen_text") or "").strip(),
-            "VisualDirection": (sc.get("visual_direction") or "").strip(),
-            "ShotType": (sc.get("shot_type") or "").strip(),
-            "Prompt": (sc.get("prompt") or "").strip(),
-            "BrollIdeas": ", ".join(sc.get("broll_ideas") or []),
-            "SFX_Music": (sc.get("sfx_music") or "").strip()
-        })
-    return pd.DataFrame(rows)
-
-def df_to_csv_bytes(df: pd.DataFrame) -> bytes:
-    """Converts a DataFrame to UTF-8 encoded CSV bytes for downloading."""
-    return df.to_csv(index=False).encode("utf-8")
-
-def transcript_bytes(title: str, transcript: str) -> bytes:
-    """Creates bytes for a simple text file containing the title and transcript."""
-    content = f"TITLE\n{title}\n\nFULL TRANSCRIPT\n{transcript}\n"
-    return content.encode("utf-8")
-
-# --- Streamlit UI ---
-st.set_page_config(page_title="Contentmaniacs Producer", page_icon="🎬", layout="wide")
-st.title("🎬 Contentmaniacs — Shorts Producer")
-st.caption("Generate ideas → transcript → scene prompts with one click.")
-
-# API key
-env_key = os.getenv("GEMINI_API_KEY", "")
-api_key = st.text_input("Gemini API Key", value=env_key, type="password", help="Find your key at makersuite.google.com")
-
-# Inputs
-c1, c2, c3, c4 = st.columns([2, 1, 1, 1])
-with c1:
-    topic = st.text_input("Topic", placeholder="Cosmic paradoxes, Deep ocean mysteries, AI vs Humans…")
-with c2:
-    idea_count = st.number_input("Ideas", min_value=1, max_value=5, value=1, step=1)
-with c3:
-    total_seconds = st.number_input("Video length (sec)", min_value=30, max_value=90, value=60, step=5)
-with c4:
-    scene_count = st.number_input("Scenes", min_value=3, max_value=10, value=6, step=1)
-
-model_name = st.selectbox("Model", [DEFAULT_MODEL, "gemini-1.5-pro"], index=0)
-go = st.button("✨ Generate")
-
-if go:
-    if not api_key:
-        st.error("Please paste your Gemini API key.")
-        st.stop()
-    if not topic.strip():
-        st.error("Please enter a topic.")
-        st.stop()
-
-    try:
-        configure_gemini(api_key)
-        model = genai.GenerativeModel(model_name)
-        prompt = make_prompt(topic.strip(), int(idea_count), int(total_seconds), int(scene_count))
-        
-        with st.spinner("Producing ideas, transcript and scenes…"):
-            resp = model.generate_content(prompt)
-            data = extract_json(resp.text)
-
-        ideas = data.get("ideas", [])
-        if not ideas:
-            st.warning("No ideas returned. Try again with a simpler topic or check the model's response format.")
-            st.stop()
-
-        # Display each idea in its own tab
-        tab_names = [f"Idea {i+1}" for i in range(len(ideas))]
-        tabs = st.tabs(tab_names)
-        ts = dt.datetime.now().strftime("%Y%m%d_%H%M%S")
-
-        for i, (tab, idea) in enumerate(zip(tabs, ideas), start=1):
-            with tab:
-                overview_row = idea_json_to_overview_rows(topic.strip(), idea)
-                scenes_df = idea_json_to_scenes_df(topic.strip(), idea)
-                transcript = idea.get("full_transcript", "").strip()
-                title = overview_row["Title"]
-
-                st.subheader("Overview")
-                st.dataframe(pd.DataFrame([overview_row]), use_container_width=True)
-
-                st.subheader("Scenes / Shot List")
-                st.dataframe(scenes_df, use_container_width=True)
-
-                # Download buttons
-                colA, colB, colC = st.columns(3)
-                file_prefix = f"idea{i}_{ts}"
-                with colA:
-                    st.download_button(
-                        "⬇️ Download Scenes CSV",
-                        data=df_to_csv_bytes(scenes_df),
-                        file_name=f"scenes_{file_prefix}.csv",
-                        mime="text/csv"
-                    )
-                with colB:
-                    st.download_button(
-                        "⬇️ Download Transcript TXT",
-                        data=transcript_bytes(title, transcript),
-                        file_name=f"transcript_{file_prefix}.txt",
-                        mime="text/plain"
-                    )
-                with colC:
-                    st.download_button(
-                        "⬇️ Download Overview CSV",
-                        data=df_to_csv_bytes(pd.DataFrame([overview_row])),
-                        file_name=f"overview_{file_prefix}.csv",
-                        mime="text/csv"
-                    )
-
-                with st.expander("👀 Quick copy: Transcript"):
-                    st.code(transcript or "No transcript returned.", language="markdown")
-
-                with st.expander("🎯 Thumbnail Prompt"):
-                    st.markdown(overview_row["ThumbnailPrompt"] or "_No prompt returned._")
-
-    except json.JSONDecodeError:
-        st.error("The model response wasn’t valid JSON. Click 'Generate' again or try a simpler topic.")
-    except Exception as e:
+import os
+import re
+import json
+import io
+import datetime as dt
+import pandas as pd
+import streamlit as st
+from dotenv import load_dotenv
+import google.generativeai as genai
+
+# --- Setup ---
+load_dotenv()
+DEFAULT_MODEL = "gemini-1.5-flash"
+
+def configure_gemini(api_key: str):
+    """Initializes the Gemini client with the provided API key."""
+    genai.configure(api_key=api_key)
+
+# --- Utilities ---
+def extract_json(text: str) -> dict:
+    """
+    Pulls a JSON object from a string, even if it's wrapped in markdown code fences.
+    Returns a Python dictionary or raises an error if parsing fails.
+    """
+    if not text:
+        raise ValueError("Received an empty response from the model.")
+    
+    # Look for JSON within ```json ... ``` markdown block
+    match = re.search(r"```json\s*(.*?)\s*```", text, re.DOTALL)
+    if match:
+        json_str = match.group(1)
+    else:
+        # Fallback: find the first '{' and last '}'
+        start = text.find('{')
+        end = text.rfind('}')
+        if start == -1 or end == -1:
+            raise json.JSONDecodeError("No JSON object found in the response text.", text, 0)
+        json_str = text[start:end+1]
+    
+    return json.loads(json_str)
+
+def seconds_to_ts(s: int) -> str:
+    """Converts an integer of seconds to a MM:SS timestamp string."""
+    m, sec = divmod(int(s), 60)
+    return f"{m:02d}:{sec:02d}"
+
+def make_prompt(topic: str, idea_count: int, total_seconds: int, scene_count: int) -> str:
+    """Creates the detailed, structured prompt for the generative model."""
+    return f"""
+You are a YouTube Shorts producer for "Contentmaniacs" (nature, cosmos, paradoxes, AI).
+Goal: Create viral, factual, poetic-science Shorts with clear visuals.
+
+Generate EXACTLY {idea_count} ideas for topic: "{topic}".
+
+Return ONLY a single, valid JSON object (no markdown). The root object must contain one key, "ideas", which is a list of idea objects.
+
+The schema for each idea object in the list is:
+{{
+  "title": "string (<= 60 chars, no quotes)",
+  "keywords": ["kw1","kw2","kw3"],
+  "description": "1–2 lines, SEO-rich, natural language",
+  "hashtags": ["Shorts","YouTubeShorts","Contentmaniacs","<up to 7 topical>"],
+  "thumbnail_prompt": "clear 9:16 visual brief (no text)",
+  "video_plan": {{
+    "duration_seconds": {total_seconds},
+    "scenes_count": {scene_count},
+    "scenes": [
+      {{
+        "scene_no": 1,
+        "start_sec": 0,
+        "end_sec": 0,
+        "voiceover": "1–2 punchy lines, simple language",
+        "on_screen_text": "few words, optional, no hashtags",
+        "visual_direction": "what to show (subject, motion, environment, mood, lighting)",
+        "shot_type": "macro | wide | medium | timelapse | drone | slow-mo | infographic",
+        "prompt": "text-to-video/image prompt for Canva/Runway (no text overlay)",
+        "broll_ideas": ["alt idea 1","alt idea 2"],
+        "sfx_music": "sound design notes (subtle, cinematic, ambient, etc.)"
+      }}
+    ]
+  }},
+  "full_transcript": "Combine all voiceover lines into a clean 45–60s transcript."
+}}
+
+RULES:
+- Factual, inspiring, no clickbait lies.
+- Keep each scene's voiceover short (<= 18 words).
+- Distribute time evenly across scenes so end_sec of last scene == duration_seconds.
+- Output MUST be a single, valid JSON object only.
+"""
+
+def idea_json_to_overview_rows(topic: str, idea: dict) -> dict:
+    """Creates a dictionary for the overview DataFrame from a single idea JSON."""
+    return {
+        "Topic": topic,
+        "Title": (idea.get("title") or "").strip(),
+        "Keywords": ", ".join(idea.get("keywords") or []),
+        "Description": (idea.get("description") or "").strip(),
+        "Hashtags": " ".join(("#" + h.lstrip("#")) for h in (idea.get("hashtags") or [])),
+        "ThumbnailPrompt": (idea.get("thumbnail_prompt") or "").strip(),
+        "DurationSec": idea.get("video_plan", {}).get("duration_seconds", "")
+    }
+
+def idea_json_to_scenes_df(topic: str, idea: dict) -> pd.DataFrame:
+    """Creates a DataFrame for the scene-by-scene shot list."""
+    scenes = idea.get("video_plan", {}).get("scenes", []) or []
+    rows = []
+    for sc in scenes:
+        rows.append({
+            "Topic": topic,
+            "Title": idea.get("title", ""),
+            "SceneNo": sc.get("scene_no", ""),
+            "Start": seconds_to_ts(sc.get("start_sec", 0)),
+            "End": seconds_to_ts(sc.get("end_sec", 0)),
+            "Voiceover": (sc.get("voiceover") or "").strip(),
+            "OnScreenText": (sc.get("on_screen_text") or "").strip(),
+            "VisualDirection": (sc.get("visual_direction") or "").strip(),
+            "ShotType": (sc.get("shot_type") or "").strip(),
+            "Prompt": (sc.get("prompt") or "").strip(),
+            "BrollIdeas": ", ".join(sc.get("broll_ideas") or []),
+            "SFX_Music": (sc.get("sfx_music") or "").strip()
+        })
+    return pd.DataFrame(rows)
+
+def df_to_csv_bytes(df: pd.DataFrame) -> bytes:
+    """Converts a DataFrame to UTF-8 encoded CSV bytes for downloading."""
+    return df.to_csv(index=False).encode("utf-8")
+
+def transcript_bytes(title: str, transcript: str) -> bytes:
+    """Creates bytes for a simple text file containing the title and transcript."""
+    content = f"TITLE\n{title}\n\nFULL TRANSCRIPT\n{transcript}\n"
+    return content.encode("utf-8")
+
+# --- Streamlit UI ---
+st.set_page_config(page_title="Contentmaniacs Producer", page_icon="🎬", layout="wide")
+st.title("🎬 Contentmaniacs — Shorts Producer")
+st.caption("Generate ideas → transcript → scene prompts with one click.")
+
+# Load Gemini API key from Hugging Face Secrets or local .env file
+try:
+    # This is for deployed apps on Hugging Face
+    api_key = st.secrets["GEMINI_API_KEY"]
+except (KeyError, FileNotFoundError):
+    # This is for local development
+    api_key = os.getenv("GEMINI_API_KEY", "")
+
+if not api_key:
+    st.error("⚠️ Gemini API key is missing! Please set it in your .env file locally, or in the Hugging Face Space secrets.")
+    st.stop()
+
+# Inputs
+c1, c2, c3, c4 = st.columns([2, 1, 1, 1])
+with c1:
+    topic = st.text_input("Topic", placeholder="Cosmic paradoxes, Deep ocean mysteries, AI vs Humans…")
+with c2:
+    idea_count = st.number_input("Ideas", min_value=1, max_value=5, value=1, step=1)
+with c3:
+    total_seconds = st.number_input("Video length (sec)", min_value=30, max_value=90, value=60, step=5)
+with c4:
+    scene_count = st.number_input("Scenes", min_value=3, max_value=10, value=6, step=1)
+
+model_name = st.selectbox("Model", [DEFAULT_MODEL, "gemini-1.5-pro"], index=0)
+go = st.button("✨ Generate")
+
+if go:
+    if not api_key:
+        st.error("Please paste your Gemini API key.")
+        st.stop()
+    if not topic.strip():
+        st.error("Please enter a topic.")
+        st.stop()
+
+    try:
+        configure_gemini(api_key)
+        model = genai.GenerativeModel(model_name)
+        prompt = make_prompt(topic.strip(), int(idea_count), int(total_seconds), int(scene_count))
+        
+        with st.spinner("Producing ideas, transcript and scenes…"):
+            resp = model.generate_content(prompt)
+            data = extract_json(resp.text)
+
+        ideas = data.get("ideas", [])
+        if not ideas:
+            st.warning("No ideas returned. Try again with a simpler topic or check the model's response format.")
+            st.stop()
+
+        # Display each idea in its own tab
+        tab_names = [f"Idea {i+1}" for i in range(len(ideas))]
+        tabs = st.tabs(tab_names)
+        ts = dt.datetime.now().strftime("%Y%m%d_%H%M%S")
+
+        for i, (tab, idea) in enumerate(zip(tabs, ideas), start=1):
+            with tab:
+                overview_row = idea_json_to_overview_rows(topic.strip(), idea)
+                scenes_df = idea_json_to_scenes_df(topic.strip(), idea)
+                transcript = idea.get("full_transcript", "").strip()
+                title = overview_row["Title"]
+
+                st.subheader("Overview")
+                st.dataframe(pd.DataFrame([overview_row]), use_container_width=True)
+
+                st.subheader("Scenes / Shot List")
+                st.dataframe(scenes_df, use_container_width=True)
+
+                # Download buttons
+                colA, colB, colC = st.columns(3)
+                file_prefix = f"idea{i}_{ts}"
+                with colA:
+                    st.download_button(
+                        "⬇️ Download Scenes CSV",
+                        data=df_to_csv_bytes(scenes_df),
+                        file_name=f"scenes_{file_prefix}.csv",
+                        mime="text/csv"
+                    )
+                with colB:
+                    st.download_button(
+                        "⬇️ Download Transcript TXT",
+                        data=transcript_bytes(title, transcript),
+                        file_name=f"transcript_{file_prefix}.txt",
+                        mime="text/plain"
+                    )
+                with colC:
+                    st.download_button(
+                        "⬇️ Download Overview CSV",
+                        data=df_to_csv_bytes(pd.DataFrame([overview_row])),
+                        file_name=f"overview_{file_prefix}.csv",
+                        mime="text/csv"
+                    )
+
+                with st.expander("👀 Quick copy: Transcript"):
+                    st.code(transcript or "No transcript returned.", language="markdown")
+
+                with st.expander("🎯 Thumbnail Prompt"):
+                    st.markdown(overview_row["ThumbnailPrompt"] or "_No prompt returned._")
+
+    except json.JSONDecodeError:
+        st.error("The model response wasn’t valid JSON. Click 'Generate' again or try a simpler topic.")
+        st.code(resp.text) # Show the faulty text
+    except Exception as e:
         st.error(f"An unexpected error occurred: {e}")