getscript 0.12.0__tar.gz

getscript-0.12.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Voxly
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

getscript-0.12.0/PKG-INFO

@@ -0,0 +1,125 @@
+Metadata-Version: 2.4
+Name: getscript
+Version: 0.12.0
+Summary: Fast, Unix-friendly CLI for fetching transcripts from YouTube and Apple Podcasts
+Author: Voxly
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/outerbanks73/cli-tools
+Project-URL: Documentation, https://voxlytranscribes.com/docs/getscript
+Project-URL: Repository, https://github.com/outerbanks73/cli-tools
+Project-URL: Issues, https://github.com/outerbanks73/cli-tools/issues
+Keywords: transcript,youtube,podcast,apple-podcasts,cli
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Multimedia :: Sound/Audio
+Classifier: Topic :: Utilities
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: youtube-transcript-api>=1.0.0
+Requires-Dist: requests>=2.28.0
+Requires-Dist: defusedxml>=0.7.1
+Dynamic: license-file
+
+# getscript
+
+A fast, Unix-friendly CLI for fetching transcripts from YouTube and Apple Podcasts.
+
+## Install
+
+```bash
+pip install .
+```
+
+Requires Python 3.10+.
+
+**Apple Podcasts** transcripts additionally require macOS 15.5+ with Xcode CLI tools.
+
+## Usage
+
+```bash
+# Fetch from URL
+getscript "https://youtube.com/watch?v=VIDEO_ID"
+getscript "https://podcasts.apple.com/...?i=EPISODE_ID"
+
+# Fetch from bare ID
+getscript dQw4w9WgXcQ          # YouTube (11-char ID)
+getscript 1000753754819         # Apple (numeric ID)
+
+# Output formats
+getscript VIDEO_ID --json | jq .
+getscript VIDEO_ID --markdown > notes.md
+getscript VIDEO_ID --timestamps
+getscript EPISODE_ID --ttml      # raw TTML XML (Apple only)
+
+# Write to file
+getscript VIDEO_ID -o transcript.txt
+
+# Search & pick interactively (requires fzf)
+getscript --search "topic keywords"
+getscript --search "topic" --apple
+getscript --search "topic" --list          # print results, no fzf
+getscript --search "topic" --limit 20
+
+# YouTube auth options
+getscript VIDEO_ID --proxy socks5://127.0.0.1:1080
+getscript VIDEO_ID --cookies ~/cookies.txt
+
+# Transcripts are automatically indexed at voxlytranscribes.com
+# To disable:
+getscript VIDEO_ID --no-upload
+GETSCRIPT_UPLOAD=0 getscript VIDEO_ID
+
+# Shell completions
+getscript --completions bash >> ~/.bashrc
+getscript --completions zsh >> ~/.zshrc
+getscript --completions fish > ~/.config/fish/completions/getscript.fish
+```
+
+## Configuration
+
+Config file: `~/.config/getscript/config.json`
+
+```json
+{
+  "youtube_api_key": "YOUR_KEY",
+  "output_format": "text",
+  "timestamps": false,
+  "search_limit": 10,
+  "no_upload": false
+}
+```
+
+Environment variables:
+- `GETSCRIPT_YOUTUBE_API_KEY` — YouTube Data API v3 key (required for `--search`)
+- `GETSCRIPT_PROXY` — proxy URL for YouTube requests
+- `GETSCRIPT_COOKIE_FILE` — Netscape cookie file for YouTube auth
+- `GETSCRIPT_UPLOAD` — set to `0` to disable automatic shared library indexing
+- `GETSCRIPT_SUPABASE_URL` — custom Supabase URL (for development)
+- `GETSCRIPT_SUPABASE_ANON_KEY` — custom Supabase anon key (for development)
+- `NO_COLOR` — disable colors
+
+Priority: config file < environment variables < CLI flags.
+
+## How it works
+
+**YouTube:** Wraps [youtube-transcript-api](https://github.com/jdepoix/youtube-transcript-api) with proxy and cookie support.
+
+**Apple Podcasts:** Compiles a small Obj-C helper that uses Apple's private AMSMescal framework (FairPlay) to obtain a bearer token, then fetches TTML transcripts from the AMP API. The token is cached for 30 days at `~/.cache/getscript/apple_token`.
+
+## Dependencies
+
+- `youtube-transcript-api` — YouTube transcript fetching
+- `requests` — HTTP sessions for cookie-based auth
+- `fzf` (optional, system binary) — interactive search result selection
+
+## License
+
+MIT

getscript-0.12.0/README.md

@@ -0,0 +1,95 @@
+# getscript
+
+A fast, Unix-friendly CLI for fetching transcripts from YouTube and Apple Podcasts.
+
+## Install
+
+```bash
+pip install .
+```
+
+Requires Python 3.10+.
+
+**Apple Podcasts** transcripts additionally require macOS 15.5+ with Xcode CLI tools.
+
+## Usage
+
+```bash
+# Fetch from URL
+getscript "https://youtube.com/watch?v=VIDEO_ID"
+getscript "https://podcasts.apple.com/...?i=EPISODE_ID"
+
+# Fetch from bare ID
+getscript dQw4w9WgXcQ          # YouTube (11-char ID)
+getscript 1000753754819         # Apple (numeric ID)
+
+# Output formats
+getscript VIDEO_ID --json | jq .
+getscript VIDEO_ID --markdown > notes.md
+getscript VIDEO_ID --timestamps
+getscript EPISODE_ID --ttml      # raw TTML XML (Apple only)
+
+# Write to file
+getscript VIDEO_ID -o transcript.txt
+
+# Search & pick interactively (requires fzf)
+getscript --search "topic keywords"
+getscript --search "topic" --apple
+getscript --search "topic" --list          # print results, no fzf
+getscript --search "topic" --limit 20
+
+# YouTube auth options
+getscript VIDEO_ID --proxy socks5://127.0.0.1:1080
+getscript VIDEO_ID --cookies ~/cookies.txt
+
+# Transcripts are automatically indexed at voxlytranscribes.com
+# To disable:
+getscript VIDEO_ID --no-upload
+GETSCRIPT_UPLOAD=0 getscript VIDEO_ID
+
+# Shell completions
+getscript --completions bash >> ~/.bashrc
+getscript --completions zsh >> ~/.zshrc
+getscript --completions fish > ~/.config/fish/completions/getscript.fish
+```
+
+## Configuration
+
+Config file: `~/.config/getscript/config.json`
+
+```json
+{
+  "youtube_api_key": "YOUR_KEY",
+  "output_format": "text",
+  "timestamps": false,
+  "search_limit": 10,
+  "no_upload": false
+}
+```
+
+Environment variables:
+- `GETSCRIPT_YOUTUBE_API_KEY` — YouTube Data API v3 key (required for `--search`)
+- `GETSCRIPT_PROXY` — proxy URL for YouTube requests
+- `GETSCRIPT_COOKIE_FILE` — Netscape cookie file for YouTube auth
+- `GETSCRIPT_UPLOAD` — set to `0` to disable automatic shared library indexing
+- `GETSCRIPT_SUPABASE_URL` — custom Supabase URL (for development)
+- `GETSCRIPT_SUPABASE_ANON_KEY` — custom Supabase anon key (for development)
+- `NO_COLOR` — disable colors
+
+Priority: config file < environment variables < CLI flags.
+
+## How it works
+
+**YouTube:** Wraps [youtube-transcript-api](https://github.com/jdepoix/youtube-transcript-api) with proxy and cookie support.
+
+**Apple Podcasts:** Compiles a small Obj-C helper that uses Apple's private AMSMescal framework (FairPlay) to obtain a bearer token, then fetches TTML transcripts from the AMP API. The token is cached for 30 days at `~/.cache/getscript/apple_token`.
+
+## Dependencies
+
+- `youtube-transcript-api` — YouTube transcript fetching
+- `requests` — HTTP sessions for cookie-based auth
+- `fzf` (optional, system binary) — interactive search result selection
+
+## License
+
+MIT

getscript-0.12.0/getscript/__init__.py

@@ -0,0 +1,6 @@
+from importlib.metadata import version, PackageNotFoundError
+
+try:
+    __version__ = version("getscript")
+except PackageNotFoundError:
+    __version__ = "0.12.0"  # fallback for editable installs without metadata

getscript-0.12.0/getscript/apple.py

@@ -0,0 +1,255 @@
+"""Apple Podcasts transcript fetching."""
+
+import json
+import os
+import shutil
+import subprocess
+import sys
+import tempfile
+import defusedxml.ElementTree as ET
+from datetime import datetime
+from urllib.error import HTTPError
+from urllib.request import Request, urlopen
+
+CACHE_VALIDITY = 60 * 60 * 24 * 30  # 30 days
+
+# Obj-C source for bearer token via AMSMescal (FairPlay signing).
+# Compiled and run as a subprocess to isolate potential segfaults
+# from the thenWithBlock: cleanup in Apple's promise implementation.
+OBJC_TOKEN_SOURCE = r'''
+#import <Foundation/Foundation.h>
+#import <objc/runtime.h>
+#import <objc/message.h>
+#import <dlfcn.h>
+
+// Cast objc_msgSend to typed function pointers to avoid selector validation
+typedef id (*msg_id)(id, SEL, ...);
+typedef id (*msg_id_id)(id, SEL, id, ...);
+typedef id (*msg_id_id_id)(id, SEL, id, id, ...);
+typedef void (*msg_void_id_str)(id, SEL, id, NSString *);
+
+int main() {
+    @autoreleasepool {
+        dlopen("/System/Library/PrivateFrameworks/PodcastsFoundation.framework/PodcastsFoundation", RTLD_LAZY);
+
+        Class AMSMescal = objc_getClass("AMSMescal");
+        Class AMSMescalSession = objc_getClass("AMSMescalSession");
+        Class AMSURLRequestClass = objc_getClass("AMSURLRequest");
+        Class IMURLBag = objc_getClass("IMURLBag");
+
+        if (!AMSMescal || !AMSMescalSession || !AMSURLRequestClass || !IMURLBag) {
+            fprintf(stderr, "Failed to load required Apple private frameworks. macOS 15.5+ required.\n");
+            return 1;
+        }
+
+        NSString *storeFront = @"143441-1,42 t:podcasts1";
+        NSDateFormatter *formatter = [[NSDateFormatter alloc] init];
+        [formatter setDateFormat:@"yyyy-MM-dd'T'HH:mm:ss'Z'"];
+        [formatter setTimeZone:[NSTimeZone timeZoneWithAbbreviation:@"UTC"]];
+        NSString *timestamp = [formatter stringFromDate:[NSDate date]];
+
+        NSURL *tokenURL = [NSURL URLWithString:@"https://sf-api-token-service.itunes.apple.com/apiToken?clientClass=apple&clientId=com.apple.podcasts.macos&os=OS%20X&osVersion=15.5&productVersion=1.1.0&version=2"];
+        NSMutableURLRequest *nsRequest = [NSMutableURLRequest requestWithURL:tokenURL];
+
+        id urlRequest = ((msg_id_id)objc_msgSend)(
+            [AMSURLRequestClass alloc],
+            sel_registerName("initWithRequest:"),
+            nsRequest
+        );
+        ((msg_void_id_str)objc_msgSend)(urlRequest, sel_registerName("setValue:forHTTPHeaderField:"), timestamp, @"x-request-timestamp");
+        ((msg_void_id_str)objc_msgSend)(urlRequest, sel_registerName("setValue:forHTTPHeaderField:"), storeFront, @"X-Apple-Store-Front");
+
+        NSDictionary *policy = @{
+            @"fields": @[@"clientId"],
+            @"headers": @[@"x-apple-store-front", @"x-apple-client-application", @"x-request-timestamp"]
+        };
+        id signature = ((msg_id_id_id)objc_msgSend)(
+            (id)AMSMescal,
+            sel_registerName("_signedActionDataFromRequest:policy:"),
+            urlRequest, policy
+        );
+
+        id session = ((msg_id)objc_msgSend)((id)AMSMescalSession, sel_registerName("defaultSession"));
+        id urlBag = ((msg_id)objc_msgSend)([IMURLBag alloc], sel_registerName("init"));
+
+        dispatch_semaphore_t sema = dispatch_semaphore_create(0);
+
+        id signedPromise = ((msg_id_id_id)objc_msgSend)(session, sel_registerName("signData:bag:"), signature, urlBag);
+
+        ((msg_id_id)objc_msgSend)(signedPromise, sel_registerName("thenWithBlock:"), ^(id result) {
+            NSString *sig = [(NSData *)result base64EncodedStringWithOptions:0];
+
+            NSMutableURLRequest *signedRequest = [NSMutableURLRequest requestWithURL:tokenURL];
+            [signedRequest setValue:timestamp forHTTPHeaderField:@"x-request-timestamp"];
+            [signedRequest setValue:storeFront forHTTPHeaderField:@"X-Apple-Store-Front"];
+            [signedRequest setValue:sig forHTTPHeaderField:@"X-Apple-ActionSignature"];
+
+            NSURLSessionDataTask *task = [[NSURLSession sharedSession] dataTaskWithRequest:signedRequest completionHandler:^(NSData *data, NSURLResponse *response, NSError *error) {
+                NSDictionary *json = [NSJSONSerialization JSONObjectWithData:data options:0 error:nil];
+                printf("%s", [json[@"token"] UTF8String]);
+                dispatch_semaphore_signal(sema);
+            }];
+            [task resume];
+            dispatch_semaphore_wait(sema, DISPATCH_TIME_FOREVER);
+        });
+
+        dispatch_semaphore_wait(sema, DISPATCH_TIME_FOREVER);
+    }
+    return 0;
+}
+'''
+
+
+def _get_cache_path(cache_dir: str) -> str:
+    return os.path.join(cache_dir, "apple_token")
+
+
+def get_bearer_token(cache_dir: str) -> str:
+    """Get bearer token, using cached version if valid."""
+    cache_path = _get_cache_path(cache_dir)
+
+    if os.path.exists(cache_path):
+        age = datetime.now().timestamp() - os.path.getmtime(cache_path)
+        if age < CACHE_VALIDITY:
+            with open(cache_path) as f:
+                token = f.read().strip()
+            if token.startswith("ey"):
+                return token
+
+    token = _compile_and_fetch_token()
+    if token:
+        os.makedirs(os.path.dirname(cache_path), exist_ok=True)
+        with open(cache_path, "w") as f:
+            f.write(token)
+        os.chmod(cache_path, 0o600)
+    return token
+
+
+def _compile_and_fetch_token() -> str | None:
+    """Compile Obj-C helper, run it, return bearer token."""
+    if sys.platform != "darwin":
+        print(
+            "Apple Podcasts transcripts require macOS with Xcode CLI tools.",
+            file=sys.stderr,
+        )
+        return None
+
+    tmpdir = tempfile.mkdtemp(prefix="getscript-")
+    src_path = os.path.join(tmpdir, "token.m")
+    bin_path = os.path.join(tmpdir, "token")
+
+    try:
+        with open(src_path, "w") as src:
+            src.write(OBJC_TOKEN_SOURCE)
+
+        comp = subprocess.run(
+            [
+                "clang",
+                "-o",
+                bin_path,
+                src_path,
+                "-Wno-objc-method-access",
+                "-framework",
+                "Foundation",
+                "-F/System/Library/PrivateFrameworks",
+                "-framework",
+                "AppleMediaServices",
+                "-fobjc-arc",
+            ],
+            capture_output=True,
+            text=True,
+        )
+        if comp.returncode != 0:
+            print(f"Compilation failed: {comp.stderr}", file=sys.stderr)
+            return None
+
+        result = subprocess.run([bin_path], capture_output=True, text=True, timeout=30)
+
+        token = result.stdout.strip()
+        if not token.startswith("ey"):
+            print(f"Invalid token. stderr: {result.stderr}", file=sys.stderr)
+            return None
+
+        return token
+    except subprocess.TimeoutExpired:
+        print("Token fetch timed out", file=sys.stderr)
+        return None
+    finally:
+        shutil.rmtree(tmpdir, ignore_errors=True)
+
+
+def fetch_ttml(episode_id: str, bearer_token: str) -> str:
+    """Fetch TTML transcript from Apple's AMP API."""
+    url = (
+        f"https://amp-api.podcasts.apple.com/v1/catalog/us/podcast-episodes/"
+        f"{episode_id}/transcripts?fields=ttmlToken,ttmlAssetUrls"
+        f"&include%5Bpodcast-episodes%5D=podcast&l=en-US&with=entitlements"
+    )
+
+    req = Request(url)
+    req.add_header("Authorization", f"Bearer {bearer_token}")
+
+    try:
+        with urlopen(req, timeout=15) as resp:
+            data = json.loads(resp.read())
+    except HTTPError as e:
+        body = e.read().decode() if e.fp else ""
+        raise Exception(f"AMP API returned {e.code}: {body}")
+
+    if "errors" in data:
+        raise Exception(f"API error: {data['errors']}")
+
+    attrs = data["data"][0]["attributes"]
+    ttml_url = attrs["ttmlAssetUrls"]["ttml"]
+
+    with urlopen(ttml_url, timeout=15) as resp:
+        return resp.read().decode("utf-8")
+
+
+def ttml_to_segments(ttml_content: str) -> list[dict]:
+    """Parse TTML XML into segment dicts with timestamps."""
+    root = ET.fromstring(ttml_content)
+    segments = []
+
+    for elem in root.iter():
+        tag = elem.tag.split("}")[-1] if "}" in elem.tag else elem.tag
+
+        if tag == "p":
+            words = []
+            # Use itertext() to get all text content without duplication
+            for text_chunk in elem.itertext():
+                stripped = text_chunk.strip()
+                if stripped:
+                    words.append(stripped)
+            if words:
+                text = " ".join(words)
+                begin = elem.get("begin", "")
+                end = elem.get("end", "")
+                segment = {"text": text}
+                if begin:
+                    segment["start"] = _parse_ttml_time(begin)
+                if end:
+                    segment["end"] = _parse_ttml_time(end)
+                    if "start" in segment:
+                        segment["duration"] = segment["end"] - segment["start"]
+                segments.append(segment)
+
+    return segments
+
+
+def ttml_to_text(ttml_content: str) -> str:
+    """Extract plain text from Apple Podcasts TTML XML."""
+    segments = ttml_to_segments(ttml_content)
+    return " ".join(s["text"] for s in segments)
+
+
+def _parse_ttml_time(time_str: str) -> float:
+    """Parse TTML time format (HH:MM:SS.mmm) to seconds."""
+    parts = time_str.split(":")
+    if len(parts) == 3:
+        h, m, s = parts
+        return int(h) * 3600 + int(m) * 60 + float(s)
+    if len(parts) == 2:
+        m, s = parts
+        return int(m) * 60 + float(s)
+    return float(time_str)