Spaces:
Sleeping
Sleeping
| """Gradio Space: YouTube topic -> captioned .docx tutorial. | |
| Orchestrates the pipeline stages and streams progress/status to the UI. Heavy ML | |
| imports (torch/transformers/faster-whisper) are lazy inside the pipeline modules, so app | |
| startup stays fast. | |
| """ | |
| from __future__ import annotations | |
| import base64 | |
| import binascii | |
| import os | |
| import re | |
| import shutil | |
| import tempfile | |
| import gradio as gr | |
| from pipeline import ( | |
| captions as captions_mod, | |
| docx_builder, | |
| download as download_mod, | |
| frames as frames_mod, | |
| search as search_mod, | |
| sentiment as sentiment_mod, | |
| transcribe as transcribe_mod, | |
| tutorial as tutorial_mod, | |
| ) | |
| LLM_CHOICES = [ | |
| "deepseek-ai/DeepSeek-V3", | |
| "meta-llama/Llama-3.3-70B-Instruct", | |
| "openai/gpt-oss-120b", | |
| ] | |
| VLM_CHOICES = [ | |
| "Qwen/Qwen2.5-VL-72B-Instruct", | |
| "Qwen/Qwen2.5-VL-7B-Instruct", | |
| "meta-llama/Llama-3.2-90B-Vision-Instruct", | |
| ] | |
| def _looks_like_netscape(text: str) -> bool: | |
| """True if ``text`` is already a tab-separated Netscape cookie file.""" | |
| head = text.lstrip() | |
| return head.startswith("#") or "\tTRUE\t" in text or "\tFALSE\t" in text | |
| def _maybe_b64_decode(text: str) -> str | None: | |
| """If ``text`` is base64 that decodes to a cookie file, return the decoded text. | |
| HF secret fields can turn the required TAB characters into spaces, which breaks the | |
| Netscape format. Pasting base64 of the file avoids that; we auto-detect and decode it. | |
| """ | |
| compact = "".join(text.split()) | |
| if len(compact) < 16 or re.search(r"[^A-Za-z0-9+/=]", compact): | |
| return None | |
| try: | |
| decoded = base64.b64decode(compact, validate=True).decode("utf-8", "replace") | |
| except (binascii.Error, ValueError): | |
| return None | |
| return decoded if _looks_like_netscape(decoded) else None | |
| def _cookiefile(workdir: str, raw: str | None = None) -> str | None: | |
| """Materialize cookies to a Netscape cookie file on disk; return its path or None. | |
| ``raw`` is the per-user UI value; if empty we fall back to the operator-wide | |
| ``YT_COOKIES`` secret. Accepts either raw cookies.txt contents (tabs preserved) or a | |
| base64 encoding of them. A missing header line is added so yt-dlp accepts the file. | |
| """ | |
| data = (raw or "").strip() or os.environ.get("YT_COOKIES") | |
| if not data or not data.strip(): | |
| return None | |
| if not _looks_like_netscape(data): | |
| decoded = _maybe_b64_decode(data) | |
| if decoded: | |
| data = decoded | |
| if not data.lstrip().startswith(("# Netscape", "# HTTP")): | |
| data = "# Netscape HTTP Cookie File\n" + data.lstrip("\n") | |
| if not data.endswith("\n"): | |
| data += "\n" | |
| path = os.path.join(workdir, "cookies.txt") | |
| with open(path, "w", encoding="utf-8", newline="\n") as fh: | |
| fh.write(data) | |
| return path | |
| def _resolve_proxy(raw: str | None = None) -> str | None: | |
| """Per-user proxy URL, falling back to the operator-wide YT_PROXY secret.""" | |
| proxy = (raw or "").strip() or os.environ.get("YT_PROXY", "").strip() | |
| return proxy or None | |
| def _resolve_pot(po_token: str | None, visitor_data: str | None) -> tuple[str | None, str | None]: | |
| """Per-user PO token + visitor data, falling back to YT_POT / YT_VISITOR_DATA secrets.""" | |
| pot = (po_token or "").strip() or os.environ.get("YT_POT", "").strip() | |
| vis = (visitor_data or "").strip() or os.environ.get("YT_VISITOR_DATA", "").strip() | |
| return (pot or None), (vis or None) | |
| def _ranking_rows(scored: list[dict]) -> list[list]: | |
| rows = [] | |
| for rank, v in enumerate(scored, start=1): | |
| rows.append([ | |
| rank, | |
| v.get("title", v["video_id"]), | |
| f"{v['positive_share'] * 100:.0f}%", | |
| v.get("n_comments", 0), | |
| v.get("note", "") or "ok", | |
| v["url"], | |
| ]) | |
| return rows | |
| def _safe_name(text: str) -> str: | |
| return re.sub(r"[^A-Za-z0-9._-]+", "_", text).strip("_")[:60] or "tutorial" | |
| def _collect_keywords(primary_kw, secondary_kw) -> dict: | |
| """Build ``{"primary": str, "secondary": [str, ...]}`` from the two keyword inputs. | |
| Secondary keywords are comma-separated. Duplicates and the primary are removed. | |
| """ | |
| primary = (primary_kw or "").strip() | |
| secondary = [] | |
| seen = {primary.lower()} | |
| for part in (secondary_kw or "").split(","): | |
| kw = part.strip() | |
| if kw and kw.lower() not in seen: | |
| seen.add(kw.lower()) | |
| secondary.append(kw) | |
| return {"primary": primary, "secondary": secondary} | |
| def run_pipeline(topic, hf_token, llm_model, vlm_model, w_llm, w_whisper, lead, | |
| max_minutes, max_shots, primary_kw, secondary_kw, | |
| cookies_text, proxy_url, po_token_in, visitor_data_in, | |
| progress=gr.Progress()): | |
| """Generator that yields (status_md, ranking_df, transcript, docx_file).""" | |
| log: list[str] = [] | |
| def status(msg: str): | |
| log.append(msg) | |
| return "\n\n".join(log) | |
| topic = (topic or "").strip() | |
| if not topic: | |
| raise gr.Error("Please enter a topic.") | |
| if not (hf_token or "").strip(): | |
| raise gr.Error("Please paste your Hugging Face token (used for the LLM + vision model).") | |
| workdir = tempfile.mkdtemp(prefix="ytt_") | |
| frames_dir = os.path.join(workdir, "frames") | |
| video_path = None | |
| try: | |
| cookiefile = _cookiefile(workdir, cookies_text) | |
| proxy = _resolve_proxy(proxy_url) | |
| po_token, visitor_data = _resolve_pot(po_token_in, visitor_data_in) | |
| auth_bits = [] | |
| if cookiefile: | |
| auth_bits.append("cookies") | |
| if proxy: | |
| auth_bits.append("proxy") | |
| if po_token: | |
| auth_bits.append("PO token") | |
| if auth_bits: | |
| yield status("🔐 Using " + " + ".join(auth_bits) + " for YouTube access."), gr.update(), gr.update(), gr.update() | |
| # 1. Search ------------------------------------------------------------------ | |
| progress(0.02, desc="Searching") | |
| yield status(f"🔍 Searching top videos for **{topic}**…"), gr.update(), gr.update(), gr.update() | |
| videos = search_mod.search_top5(topic) | |
| yield status(f"Found {len(videos)} candidate videos."), gr.update(), gr.update(), gr.update() | |
| # 2. Sentiment ranking ------------------------------------------------------- | |
| yield status("💬 Fetching comments and scoring sentiment…"), gr.update(), gr.update(), gr.update() | |
| best, scored = sentiment_mod.rank_by_sentiment( | |
| videos, cookiefile, progress, proxy, po_token, visitor_data) | |
| ranking = gr.update(value=_ranking_rows(scored)) | |
| yield (status(f"🏆 Picked **{best.get('title', best['video_id'])}** " | |
| f"({best['positive_share'] * 100:.0f}% positive)."), | |
| ranking, gr.update(), gr.update()) | |
| # 3. Download + audio -------------------------------------------------------- | |
| progress(0.25, desc="Downloading") | |
| yield status("⬇️ Downloading the chosen video…"), ranking, gr.update(), gr.update() | |
| video_path, duration = download_mod.download_video( | |
| best["url"], workdir, cookiefile, int(max_minutes), proxy, po_token, visitor_data) | |
| wav = download_mod.extract_audio(video_path, workdir) | |
| # 4. Transcribe -------------------------------------------------------------- | |
| progress(0.4, desc="Transcribing") | |
| yield status("📝 Transcribing with Whisper (this is the slow part on CPU)…"), ranking, gr.update(), gr.update() | |
| segs = transcribe_mod.transcribe(wav, progress) | |
| transcript = transcribe_mod.transcript_text(segs) | |
| yield (status(f"Transcript ready ({len(segs)} segments)."), | |
| ranking, gr.update(value=transcript), gr.update()) | |
| # 5. Candidate frames, then DELETE the video -------------------------------- | |
| progress(0.6, desc="Extracting frames") | |
| candidates = frames_mod.extract_candidates(video_path, frames_dir, duration) | |
| frames_mod.delete_video(video_path) | |
| video_path = None | |
| yield (status(f"🎞️ Extracted {len(candidates)} candidate frames and " | |
| f"**deleted the downloaded video**."), | |
| ranking, gr.update(value=transcript), gr.update()) | |
| # 6. Tutorial text ----------------------------------------------------------- | |
| progress(0.72, desc="Writing tutorial") | |
| keywords = _collect_keywords(primary_kw, secondary_kw) | |
| kw_note = f" • primary: '{keywords['primary']}'" if keywords["primary"] else "" | |
| if keywords["secondary"]: | |
| kw_note += f" • secondary: {', '.join(keywords['secondary'])}" | |
| yield status(f"🤖 Generating tutorial with `{llm_model}`{kw_note}…"), ranking, gr.update(value=transcript), gr.update() | |
| tut = tutorial_mod.generate_tutorial(transcript, hf_token.strip(), llm_model, keywords) | |
| if keywords["primary"]: | |
| n = tutorial_mod.count_keyword(tut, keywords["primary"]) | |
| yield (status(f"🔑 Primary keyword '{keywords['primary']}' appears {n}× in the post."), | |
| ranking, gr.update(value=transcript), gr.update()) | |
| # 7. Weighted screenshot selection ------------------------------------------ | |
| selected = frames_mod.select_screenshots( | |
| tut["steps"], segs, candidates, | |
| w_llm=float(w_llm), w_whisper=float(w_whisper), lead=float(lead), | |
| max_shots=int(max_shots), | |
| ) | |
| yield (status(f"🖼️ Selected {len(selected)} screenshots via the weighted indicator."), | |
| ranking, gr.update(value=transcript), gr.update()) | |
| # 8. Captions ---------------------------------------------------------------- | |
| progress(0.85, desc="Captioning") | |
| yield status(f"✍️ Captioning screenshots with `{vlm_model}`…"), ranking, gr.update(value=transcript), gr.update() | |
| caps = captions_mod.caption_frames(selected, tut["steps"], hf_token.strip(), vlm_model, progress) | |
| # 9. DOCX -------------------------------------------------------------------- | |
| progress(0.95, desc="Building document") | |
| out_path = os.path.join(workdir, f"{_safe_name(tut['title'])}.docx") | |
| docx_builder.build_docx(tut, selected, caps, out_path, source_url=best["url"]) | |
| progress(1.0, desc="Done") | |
| yield (status("✅ Done! Download your tutorial below."), | |
| ranking, gr.update(value=transcript), gr.update(value=out_path)) | |
| except gr.Error: | |
| raise | |
| except (download_mod.DownloadError, RuntimeError, ValueError) as exc: | |
| raise gr.Error(str(exc)) | |
| finally: | |
| # Always remove the video if it somehow survived; keep frames/docx until the | |
| # response is sent (Gradio copies the returned file out). | |
| if video_path: | |
| frames_mod.delete_video(video_path) | |
| def build_ui(): | |
| with gr.Blocks(title="YouTube → Tutorial Post") as demo: | |
| gr.Markdown( | |
| "# 📝 YouTube → Tutorial Post Generator\n" | |
| "Enter a topic and your Hugging Face token. The Space picks the best video, " | |
| "transcribes it, and builds a **captioned `.docx` tutorial**. Your token is " | |
| "used only for the LLM + vision-model calls and **billed to your account**." | |
| ) | |
| with gr.Row(): | |
| with gr.Column(scale=2): | |
| topic = gr.Textbox(label="Topic", placeholder="e.g. Excel pivot tables for beginners") | |
| hf_token = gr.Textbox(label="Hugging Face token", type="password", | |
| placeholder="hf_… (Inference Providers permission)") | |
| with gr.Column(scale=1): | |
| llm_model = gr.Dropdown(LLM_CHOICES, value=LLM_CHOICES[0], | |
| label="Tutorial LLM", allow_custom_value=True) | |
| vlm_model = gr.Dropdown(VLM_CHOICES, value=VLM_CHOICES[0], | |
| label="Vision model (captions)", allow_custom_value=True) | |
| with gr.Accordion("YouTube access — cookies / proxy (often required)", open=False): | |
| gr.Markdown( | |
| "⚠️ **YouTube usually blocks the Space's datacenter IP.** To download, give " | |
| "the Space **your own** access below — it is used only for your run and " | |
| "deleted afterward.\n\n" | |
| "- **Use a throwaway Google account, not your main one.** yt-dlp activity " | |
| "can get an account rate-limited or flagged.\n" | |
| "- **Cookies:** export a `youtube.com` cookies.txt (Netscape format) from a " | |
| "logged-in throwaway account and paste it (raw or base64) below.\n" | |
| "- **PO token (free, no proxy):** a Proof-of-Origin token + visitor data " | |
| "can pass the bot-check from a datacenter IP. **See this Space's README → " | |
| "\"PO token\" guide** for how to get and paste them.\n" | |
| "- **Proxy:** a **residential** proxy works; **free *datacenter* proxies " | |
| "(e.g. Webshare's free tier) usually do NOT** get past YouTube's block and " | |
| "have tight bandwidth caps.\n" | |
| "- An operator can instead set Space secrets `YT_COOKIES` / `YT_PROXY` / " | |
| "`YT_POT` / `YT_VISITOR_DATA` as shared defaults." | |
| ) | |
| cookies_text = gr.Textbox( | |
| label="YouTube cookies (cookies.txt contents or base64)", lines=4, | |
| placeholder="# Netscape HTTP Cookie File … (or a base64 blob)") | |
| with gr.Row(): | |
| po_token_in = gr.Textbox( | |
| label="PO token (see README) — CLIENT.CONTEXT+TOKEN", lines=2, scale=3, | |
| placeholder="web.gvs+AbC…, web.player+XyZ…") | |
| visitor_data_in = gr.Textbox( | |
| label="Visitor data (pairs with the PO token)", scale=2, | |
| placeholder="Cgt...%3D%3D") | |
| proxy_url = gr.Textbox( | |
| label="Proxy URL (optional)", type="password", | |
| placeholder="http://user:pass@host:port") | |
| with gr.Accordion("SEO / AEO keywords (optional)", open=False): | |
| gr.Markdown( | |
| "The **primary keyword** is used naturally ~3× in the body and placed in " | |
| "the title, URL slug, meta description, the first 100 words, and one or " | |
| "two H2 headings. Each **secondary keyword** is used once. The post also " | |
| "follows answer-engine best practices (direct answer up top, FAQ, " | |
| "last-updated date, source citation)." | |
| ) | |
| primary_kw = gr.Textbox(label="Primary keyword", | |
| placeholder="e.g. godot ai plugin") | |
| secondary_kw = gr.Textbox(label="Secondary keywords (comma-separated)", | |
| placeholder="e.g. gdscript assistant, ai game tools") | |
| with gr.Accordion("Advanced settings", open=False): | |
| with gr.Row(): | |
| w_llm = gr.Slider(0.0, 1.0, value=0.4, step=0.05, label="Weight: LLM timestamp") | |
| w_whisper = gr.Slider(0.0, 1.0, value=0.6, step=0.05, label="Weight: Whisper timing") | |
| lead = gr.Slider(0.0, 5.0, value=1.0, step=0.5, label="Lead offset (s)") | |
| with gr.Row(): | |
| max_minutes = gr.Slider(2, 60, value=20, step=1, label="Max video length (min)") | |
| max_shots = gr.Slider(1, 15, value=8, step=1, label="Max screenshots") | |
| run_btn = gr.Button("Generate tutorial", variant="primary") | |
| status_md = gr.Markdown(label="Status") | |
| ranking_df = gr.Dataframe( | |
| headers=["#", "Title", "Positive", "Comments", "Note", "URL"], | |
| label="Sentiment ranking", interactive=False, wrap=True, | |
| ) | |
| transcript_box = gr.Textbox(label="Transcript preview", lines=10, max_lines=20) | |
| docx_file = gr.File(label="Download tutorial (.docx)") | |
| run_btn.click( | |
| run_pipeline, | |
| inputs=[topic, hf_token, llm_model, vlm_model, w_llm, w_whisper, lead, | |
| max_minutes, max_shots, primary_kw, secondary_kw, | |
| cookies_text, proxy_url, po_token_in, visitor_data_in], | |
| outputs=[status_md, ranking_df, transcript_box, docx_file], | |
| ) | |
| return demo | |
| if __name__ == "__main__": | |
| build_ui().queue().launch() | |