Add testing on github

fixes #146

.github/workflows/test.yml

@@ -0,0 +1,27 @@
+name: Run tests
+
+on: [push, pull_request]
+
+jobs:
+  test:
+    runs-on: ubuntu-22.04
+    strategy:
+      matrix:
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -e ".[test]"
+      - name: Run tests
+        run: |
+          pytest
+      - name: Validate minimum required version
+        run: |
+          vermin --no-tips twitchdl

CHANGELOG.md

@@ -3,11 +3,28 @@ twitch-dl changelog
 
 <!-- Do not edit. This file is automatically generated from changelog.yaml.-->
 
-### [2.2.0 (TBA)](https://github.com/ihabunek/twitch-dl/releases/tag/2.2.0)
+### [2.2.2 (2024-04-23)](https://github.com/ihabunek/twitch-dl/releases/tag/2.2.2)
 
-* **Requires python 3.8 or later**
-* Migrated to click lib for cli parsing
-* Add shell auto completion
+* Fix more compat issues Python < 3.10 (#152)
+
+### [2.2.1 (2024-04-23)](https://github.com/ihabunek/twitch-dl/releases/tag/2.2.1)
+
+* Fix compat with Python < 3.10 (#152)
+* Fix division by zero in progress calculation when video duration is reported
+  as 0
+
+### [2.2.0 (2024-04-10)](https://github.com/ihabunek/twitch-dl/releases/tag/2.2.0)
+
+* **Requires Python 3.8+**
+* Migrated to Click library for generating the commandline interface
+* Add shell auto completion, see 'Shell completion' in docs.
+* Add setting defaults via environment variables, see 'Environment variables' in
+  docs
+* Add `download --concat` option to avoid using ffmeg for joinig vods and concat
+  them instead. This will produce a `.ts` file by default.
+* Add `download --dry-run` option to skip actual download (thanks @metacoma)
+* Add video description to metadata (#129)
+* Add `clips --compact` option for listing clips in one-per-line mode
 
 ### [2.1.4 (2024-01-06)](https://github.com/ihabunek/twitch-dl/releases/tag/2.1.4)
 

changelog.yaml

@@ -1,12 +1,25 @@
-2.2.0:
-  date: TBA
+2.2.2:
+  date: 2024-04-23
   changes:
-    - "**Requires python 3.8 or later**"
+    - "Fix more compat issues Python < 3.10 (#152)"
+
+2.2.1:
+  date: 2024-04-23
+  changes:
+    - "Fix compat with Python < 3.10 (#152)"
+    - "Fix division by zero in progress calculation when video duration is reported as 0"
+
+2.2.0:
+  date: 2024-04-10
+  changes:
+    - "**Requires Python 3.8+**"
     - "Migrated to Click library for generating the commandline interface"
-    - "Add shell auto completion, see: https://twitch-dl.bezdomni.net/shell_completion.html"
-    - "Add setting defaults via environment variables, see: https://twitch-dl.bezdomni.net/environment_variables.html"
+    - "Add shell auto completion, see 'Shell completion' in docs."
+    - "Add setting defaults via environment variables, see 'Environment variables' in docs"
     - "Add `download --concat` option to avoid using ffmeg for joinig vods and concat them instead. This will produce a `.ts` file by default."
+    - "Add `download --dry-run` option to skip actual download (thanks @metacoma)"
     - "Add video description to metadata (#129)"
+    - "Add `clips --compact` option for listing clips in one-per-line mode"
 
 2.1.4:
   date: 2024-01-06

docs/changelog.md

@@ -3,11 +3,28 @@ twitch-dl changelog
 
 <!-- Do not edit. This file is automatically generated from changelog.yaml.-->
 
-### [2.2.0 (TBA)](https://github.com/ihabunek/twitch-dl/releases/tag/2.2.0)
+### [2.2.2 (2024-04-23)](https://github.com/ihabunek/twitch-dl/releases/tag/2.2.2)
 
-* **Requires python 3.8 or later**
-* Migrated to click lib for cli parsing
-* Add shell auto completion
+* Fix more compat issues Python < 3.10 (#152)
+
+### [2.2.1 (2024-04-23)](https://github.com/ihabunek/twitch-dl/releases/tag/2.2.1)
+
+* Fix compat with Python < 3.10 (#152)
+* Fix division by zero in progress calculation when video duration is reported
+  as 0
+
+### [2.2.0 (2024-04-10)](https://github.com/ihabunek/twitch-dl/releases/tag/2.2.0)
+
+* **Requires Python 3.8+**
+* Migrated to Click library for generating the commandline interface
+* Add shell auto completion, see 'Shell completion' in docs.
+* Add setting defaults via environment variables, see 'Environment variables' in
+  docs
+* Add `download --concat` option to avoid using ffmeg for joinig vods and concat
+  them instead. This will produce a `.ts` file by default.
+* Add `download --dry-run` option to skip actual download (thanks @metacoma)
+* Add video description to metadata (#129)
+* Add `clips --compact` option for listing clips in one-per-line mode
 
 ### [2.1.4 (2024-01-06)](https://github.com/ihabunek/twitch-dl/releases/tag/2.1.4)
 

docs/commands/clips.md

@@ -18,6 +18,11 @@ twitch-dl clips [OPTIONS] CHANNEL_NAME
     <td>Fetch all clips, overrides --limit</td>
 </tr>
 
+<tr>
+    <td class="code">-c, --compact</td>
+    <td>Show clips in compact mode, one line per video</td>
+</tr>
+
 <tr>
     <td class="code">-d, --download</td>
     <td>Download clips in given period (in source quality)</td>
@@ -25,7 +30,7 @@ twitch-dl clips [OPTIONS] CHANNEL_NAME
 
 <tr>
     <td class="code">-l, --limit INTEGER</td>
-    <td>Number of clips to fetch [max: 100] [default: <code>10</code>]</td>
+    <td>Number of clips to fetch. Defaults to 40 in compact mode, 10 otherwise.</td>
 </tr>
 
 <tr>

docs/commands/download.md

@@ -28,7 +28,7 @@ twitch-dl download [OPTIONS] [IDS]...
 
 <tr>
     <td class="code">--concat</td>
-    <td>Do not use ffmpeg to join files, concat them instead</td>
+    <td>Do not use ffmpeg to join files, concat them instead. This will produce a .ts file by default.</td>
 </tr>
 
 <tr>

pyproject.toml

@@ -43,6 +43,11 @@ dev = [
     "vermin",
 ]
 
+test = [
+    "pytest",
+    "vermin",
+]
+
 [project.urls]
 "Homepage" = "https://twitch-dl.bezdomni.net/"
 "Source" = "https://github.com/ihabunek/twitch-dl"
@@ -53,6 +58,8 @@ twitch-dl = "twitchdl.cli:cli"
 [tool.pyright]
 include = ["twitchdl"]
 typeCheckingMode = "strict"
+pythonVersion = "3.8"
 
 [tool.ruff]
 line-length = 100
+target-version = "py38"

scripts/tag_version

@@ -11,12 +11,10 @@ Usage: tag_version [version]
 import subprocess
 import sys
 import textwrap
-import yaml
-import twitchdl
-
 from datetime import date
 from os import path
-from pkg_resources import get_distribution
+
+import yaml
 
 path = path.join(path.dirname(path.dirname(path.abspath(__file__))), "changelog.yaml")
 with open(path, "r") as f:
@@ -33,15 +31,6 @@ if not changelog_item:
     print(f"Version `{version}` not found in changelog.", file=sys.stderr)
     sys.exit(1)
 
-if twitchdl.__version__ != version:
-    print(f"twitchdl.__version__ is `{twitchdl.__version__}`, expected {version}.", file=sys.stderr)
-    sys.exit(1)
-
-dist_version = get_distribution('twitch-dl').version
-if dist_version != version:
-    print(f"Version in setup.py is `{dist_version}`, expected {version}.", file=sys.stderr)
-    sys.exit(1)
-
 release_date = changelog_item["date"]
 changes = changelog_item["changes"]
 description = changelog_item["description"] if "description" in changelog_item else None

tests/test_api.py

@@ -3,9 +3,10 @@ These tests depend on the channel having some videos and clips published.
 """
 
 import httpx
-import m3u8
+
 from twitchdl import twitch
-from twitchdl.commands.download import _parse_playlists, get_clip_authenticated_url
+from twitchdl.commands.download import get_clip_authenticated_url
+from twitchdl.playlists import enumerate_vods, load_m3u8, parse_playlists
 
 TEST_CHANNEL = "bananasaurus_rex"
 
@@ -17,22 +18,25 @@ def test_get_videos():
 
     video_id = videos["edges"][0]["node"]["id"]
     video = twitch.get_video(video_id)
+    assert video is not None
     assert video["id"] == video_id
 
     access_token = twitch.get_access_token(video_id)
     assert "signature" in access_token
     assert "value" in access_token
 
-    playlists = twitch.get_playlists(video_id, access_token)
-    assert playlists.startswith("#EXTM3U")
+    playlists_txt = twitch.get_playlists(video_id, access_token)
+    assert playlists_txt.startswith("#EXTM3U")
 
-    name, res, url = next(_parse_playlists(playlists))
-    playlist = httpx.get(url).text
-    assert playlist.startswith("#EXTM3U")
+    playlists = parse_playlists(playlists_txt)
+    playlist_url = playlists[0].url
 
-    playlist = m3u8.loads(playlist)
-    vod_path = playlist.segments[0].uri
-    assert vod_path == "0.ts"
+    playlist_txt = httpx.get(playlist_url).text
+    assert playlist_txt.startswith("#EXTM3U")
+
+    playlist_m3u8 = load_m3u8(playlist_txt)
+    vods = enumerate_vods(playlist_m3u8)
+    assert vods[0].path == "0.ts"
 
 
 def test_get_clips():
@@ -45,6 +49,7 @@ def test_get_clips():
 
     slug = clips["edges"][0]["node"]["slug"]
     clip = twitch.get_clip(slug)
+    assert clip is not None
     assert clip["slug"] == slug
 
     assert get_clip_authenticated_url(slug, "source")

twitchdl/cli.py

@@ -1,12 +1,14 @@
-import click
 import logging
 import platform
 import re
 import sys
+from typing import Optional, Tuple
+
+import click
 
 from twitchdl import __version__
-from twitchdl.commands.clips import ClipsPeriod
 from twitchdl.entities import DownloadOptions
+from twitchdl.twitch import ClipsPeriod, VideosSort, VideosType
 
 # Tweak the Click context
 # https://click.palletsprojects.com/en/8.1.x/api/#context
@@ -29,13 +31,13 @@ json_option = click.option(
 )
 
 
-def validate_positive(_ctx: click.Context, _param: click.Parameter, value: int | None):
+def validate_positive(_ctx: click.Context, _param: click.Parameter, value: Optional[int]):
     if value is not None and value <= 0:
         raise click.BadParameter("must be greater than 0")
     return value
 
 
-def validate_time(_ctx: click.Context, _param: click.Parameter, value: str) -> int | None:
+def validate_time(_ctx: click.Context, _param: click.Parameter, value: str) -> Optional[int]:
     """Parse a time string (hh:mm or hh:mm:ss) to number of seconds."""
     if not value:
         return None
@@ -55,7 +57,7 @@ def validate_time(_ctx: click.Context, _param: click.Parameter, value: str) -> i
     return hours * 3600 + minutes * 60 + seconds
 
 
-def validate_rate(_ctx: click.Context, _param: click.Parameter, value: str) -> int | None:
+def validate_rate(_ctx: click.Context, _param: click.Parameter, value: str) -> Optional[int]:
     if not value:
         return None
 
@@ -84,7 +86,7 @@ def validate_rate(_ctx: click.Context, _param: click.Parameter, value: str) -> i
 def cli(ctx: click.Context, color: bool, debug: bool):
     """twitch-dl - twitch.tv downloader
 
-    https://toot.bezdomni.net/
+    https://twitch-dl.bezdomni.net/
     """
     ctx.color = color
 
@@ -100,6 +102,12 @@ def cli(ctx: click.Context, color: bool, debug: bool):
     help="Fetch all clips, overrides --limit",
     is_flag=True,
 )
+@click.option(
+    "-c",
+    "--compact",
+    help="Show clips in compact mode, one line per video",
+    is_flag=True,
+)
 @click.option(
     "-d",
     "--download",
@@ -109,9 +117,8 @@ def cli(ctx: click.Context, color: bool, debug: bool):
 @click.option(
     "-l",
     "--limit",
-    help="Number of clips to fetch [max: 100]",
+    help="Number of clips to fetch. Defaults to 40 in compact mode, 10 otherwise.",
     type=int,
-    default=10,
     callback=validate_positive,
 )
 @click.option(
@@ -134,10 +141,11 @@ def cli(ctx: click.Context, color: bool, debug: bool):
 def clips(
     channel_name: str,
     all: bool,
+    compact: bool,
     download: bool,
     json: bool,
-    limit: int,
-    pager: int | None,
+    limit: Optional[int],
+    pager: Optional[int],
     period: ClipsPeriod,
 ):
     """List or download clips for given CHANNEL_NAME."""
@@ -146,6 +154,7 @@ def clips(
     clips(
         channel_name,
         all=all,
+        compact=compact,
         download=download,
         json=json,
         limit=limit,
@@ -246,20 +255,20 @@ def clips(
     default=5,
 )
 def download(
-    ids: tuple[str, ...],
-    auth_token: str | None,
-    chapter: int | None,
+    ids: Tuple[str, ...],
+    auth_token: Optional[str],
+    chapter: Optional[int],
     concat: bool,
     dry_run: bool,
-    end: int | None,
+    end: Optional[int],
     format: str,
     keep: bool,
     no_join: bool,
     overwrite: bool,
     output: str,
-    quality: str | None,
-    rate_limit: str | None,
-    start: int | None,
+    quality: Optional[str],
+    rate_limit: Optional[int],
+    start: Optional[int],
     max_workers: int,
 ):
     """Download videos or clips.
@@ -365,12 +374,12 @@ def videos(
     channel_name: str,
     all: bool,
     compact: bool,
-    games_tuple: tuple[str, ...],
+    games_tuple: Tuple[str, ...],
     json: bool,
-    limit: int | None,
-    pager: int | None,
-    sort: str,
-    type: str,
+    limit: Optional[int],
+    pager: Optional[int],
+    sort: VideosSort,
+    type: VideosType,
 ):
     """List or download clips for given CHANNEL_NAME."""
     from twitchdl.commands.videos import videos

twitchdl/commands/clips.py

@@ -1,30 +1,33 @@
 import re
 import sys
-
-from typing import Literal
-from itertools import islice
 from os import path
+from typing import Callable, Generator, Optional
+
+import click
 
 from twitchdl import twitch, utils
 from twitchdl.commands.download import get_clip_authenticated_url
 from twitchdl.download import download_file
-from twitchdl.output import print_out, print_clip, print_json
-
-ClipsPeriod = Literal["last_day", "last_week", "last_month", "all_time"]
+from twitchdl.output import green, print_clip, print_clip_compact, print_json, print_paged, yellow
+from twitchdl.twitch import Clip, ClipsPeriod
 
 
 def clips(
     channel_name: str,
     *,
     all: bool = False,
+    compact: bool = False,
     download: bool = False,
     json: bool = False,
-    limit: int = 10,
-    pager: int | None = None,
+    limit: Optional[int] = None,
+    pager: Optional[int] = None,
     period: ClipsPeriod = "all_time",
 ):
+    # Set different defaults for limit for compact display
+    default_limit = 40 if compact else 10
+
     # Ignore --limit if --pager or --all are given
-    limit = sys.maxsize if all or pager else limit
+    limit = sys.maxsize if all or pager else (limit or default_limit)
 
     generator = twitch.channel_clips_generator(channel_name, period, limit)
 
@@ -34,24 +37,15 @@ def clips(
     if download:
         return _download_clips(generator)
 
+    print_fn = print_clip_compact if compact else print_clip
+
     if pager:
-        return _print_paged(generator, pager)
+        return print_paged("Clips", generator, print_fn, pager)
 
-    return _print_all(generator, all)
+    return _print_all(generator, print_fn, all)
 
 
-def _continue():
-    print_out("Press <green><b>Enter</green> to continue, <yellow><b>Ctrl+C</yellow> to break.")
-
-    try:
-        input()
-    except KeyboardInterrupt:
-        return False
-
-    return True
-
-
-def _target_filename(clip):
+def _target_filename(clip: Clip):
     url = clip["videoQualities"][0]["sourceURL"]
     _, ext = path.splitext(url)
     ext = ext.lstrip(".")
@@ -61,63 +55,41 @@ def _target_filename(clip):
         raise ValueError(f"Failed parsing date from: {clip['createdAt']}")
     date = "".join(match.groups())
 
-    name = "_".join([
-        date,
-        clip["id"],
-        clip["broadcaster"]["login"],
-        utils.slugify(clip["title"]),
-    ])
+    name = "_".join(
+        [
+            date,
+            clip["id"],
+            clip["broadcaster"]["login"],
+            utils.slugify(clip["title"]),
+        ]
+    )
 
     return f"{name}.{ext}"
 
 
-def _download_clips(generator):
+def _download_clips(generator: Generator[Clip, None, None]):
     for clip in generator:
         target = _target_filename(clip)
 
         if path.exists(target):
-            print_out(f"Already downloaded: <green>{target}</green>")
+            click.echo(f"Already downloaded: {green(target)}")
         else:
             url = get_clip_authenticated_url(clip["slug"], "source")
-            print_out(f"Downloading: <yellow>{target}</yellow>")
+            click.echo(f"Downloading: {yellow(target)}")
             download_file(url, target)
 
 
-def _print_all(generator, all: bool):
+def _print_all(
+    generator: Generator[Clip, None, None],
+    print_fn: Callable[[Clip], None],
+    all: bool,
+):
     for clip in generator:
-        print_out()
-        print_clip(clip)
+        print_fn(clip)
 
     if not all:
-        print_out(
-            "\n<dim>There may be more clips. " +
-            "Increase the --limit, use --all or --pager to see the rest.</dim>"
+        click.secho(
+            "\nThere may be more clips. "
+            + "Increase the --limit, use --all or --pager to see the rest.",
+            dim=True,
         )
-
-
-def _print_paged(generator, page_size):
-    iterator = iter(generator)
-    page = list(islice(iterator, page_size))
-
-    first = 1
-    last = first + len(page) - 1
-
-    while True:
-        print_out("-" * 80)
-
-        print_out()
-        for clip in page:
-            print_clip(clip)
-            print_out()
-
-        last = first + len(page) - 1
-
-        print_out("-" * 80)
-        print_out(f"<yellow>Clips {first}-{last}</yellow>")
-
-        first = first + len(page)
-        last = first + 1
-
-        page = list(islice(iterator, page_size))
-        if not page or not _continue():
-            break

twitchdl/commands/download.py

@@ -1,27 +1,35 @@
 import asyncio
-import platform
-import httpx
-import m3u8
 import os
+import platform
 import re
 import shutil
 import subprocess
 import tempfile
-
 from os import path
 from pathlib import Path
-from typing import List, Optional, OrderedDict
-from urllib.parse import urlparse, urlencode
+from typing import Dict, List
+from urllib.parse import urlencode, urlparse
+
+import click
+import httpx
 
 from twitchdl import twitch, utils
 from twitchdl.download import download_file
-from twitchdl.entities import Data, DownloadOptions
+from twitchdl.entities import DownloadOptions
 from twitchdl.exceptions import ConsoleError
 from twitchdl.http import download_all
-from twitchdl.output import print_out
+from twitchdl.output import blue, bold, green, print_log, yellow
+from twitchdl.playlists import (
+    enumerate_vods,
+    load_m3u8,
+    make_join_playlist,
+    parse_playlists,
+    select_playlist,
+)
+from twitchdl.twitch import Chapter, Clip, ClipAccessToken, Video
 
 
-def download(ids: list[str], args: DownloadOptions):
+def download(ids: List[str], args: DownloadOptions):
     for video_id in ids:
         download_one(video_id, args)
 
@@ -38,73 +46,40 @@ def download_one(video: str, args: DownloadOptions):
     raise ConsoleError(f"Invalid input: {video}")
 
 
-def _parse_playlists(playlists_m3u8):
-    playlists = m3u8.loads(playlists_m3u8)
-
-    for p in sorted(playlists.playlists, key=lambda p: p.stream_info.resolution is None):
-        if p.stream_info.resolution:
-            name = p.media[0].name
-            description = "x".join(str(r) for r in p.stream_info.resolution)
-        else:
-            name = p.media[0].group_id
-            description = None
-
-        yield name, description, p.uri
-
-
-def _get_playlist_by_name(playlists, quality):
-    if quality == "source":
-        _, _, uri = playlists[0]
-        return uri
-
-    for name, _, uri in playlists:
-        if name == quality:
-            return uri
-
-    available = ", ".join([name for (name, _, _) in playlists])
-    msg = f"Quality '{quality}' not found. Available qualities are: {available}"
-    raise ConsoleError(msg)
-
-
-def _select_playlist_interactive(playlists):
-    print_out("\nAvailable qualities:")
-    for n, (name, resolution, uri) in enumerate(playlists):
-        if resolution:
-            print_out(f"{n + 1}) <b>{name}</b> <dim>({resolution})</dim>")
-        else:
-            print_out(f"{n + 1}) <b>{name}</b>")
-
-    no = utils.read_int("Choose quality", min=1, max=len(playlists) + 1, default=1)
-    _, _, uri = playlists[no - 1]
-    return uri
-
-
-def _join_vods(playlist_path: str, target: str, overwrite: bool, video):
+def _join_vods(playlist_path: str, target: str, overwrite: bool, video: Video):
     description = video["description"] or ""
     description = description.strip()
 
     command = [
         "ffmpeg",
-        "-i", playlist_path,
-        "-c", "copy",
-        "-metadata", f"artist={video['creator']['displayName']}",
-        "-metadata", f"title={video['title']}",
-        "-metadata", f"description={description}",
-        "-metadata", "encoded_by=twitch-dl",
+        "-i",
+        playlist_path,
+        "-c",
+        "copy",
+        "-metadata",
+        f"artist={video['creator']['displayName']}",
+        "-metadata",
+        f"title={video['title']}",
+        "-metadata",
+        f"description={description}",
+        "-metadata",
+        "encoded_by=twitch-dl",
         "-stats",
-        "-loglevel", "warning",
+        "-loglevel",
+        "warning",
         f"file:{target}",
     ]
 
     if overwrite:
         command.append("-y")
 
-    print_out(f"<dim>{' '.join(command)}</dim>")
+    click.secho(f"{' '.join(command)}", dim=True)
     result = subprocess.run(command)
     if result.returncode != 0:
         raise ConsoleError("Joining files failed")
 
-def _concat_vods(vod_paths: list[str], target: str):
+
+def _concat_vods(vod_paths: List[str], target: str):
     tool = "type" if platform.system() == "Windows" else "cat"
     command = [tool] + vod_paths
 
@@ -114,8 +89,8 @@ def _concat_vods(vod_paths: list[str], target: str):
             raise ConsoleError(f"Joining files failed: {result.stderr}")
 
 
-def get_video_substitutions(video: Data, format: str) -> Data:
-    date, time = video['publishedAt'].split("T")
+def get_video_placeholders(video: Video, format: str) -> Dict[str, str]:
+    date, time = video["publishedAt"].split("T")
     game = video["game"]["name"] if video["game"] else "Unknown"
 
     return {
@@ -133,8 +108,8 @@ def get_video_substitutions(video: Data, format: str) -> Data:
     }
 
 
-def _video_target_filename(video: Data, args: DownloadOptions):
-    subs = get_video_substitutions(video, args.format)
+def _video_target_filename(video: Video, args: DownloadOptions):
+    subs = get_video_placeholders(video, args.format)
 
     try:
         return args.output.format(**subs)
@@ -143,7 +118,7 @@ def _video_target_filename(video: Data, args: DownloadOptions):
         raise ConsoleError(f"Invalid key {e} used in --output. Supported keys are: {supported}")
 
 
-def _clip_target_filename(clip, args: DownloadOptions):
+def _clip_target_filename(clip: Clip, args: DownloadOptions):
     date, time = clip["createdAt"].split("T")
     game = clip["game"]["name"] if clip["game"] else "Unknown"
 
@@ -173,26 +148,6 @@ def _clip_target_filename(clip, args: DownloadOptions):
         raise ConsoleError(f"Invalid key {e} used in --output. Supported keys are: {supported}")
 
 
-def _get_vod_paths(playlist, start: Optional[int], end: Optional[int]) -> List[str]:
-    """Extract unique VOD paths for download from playlist."""
-    files = []
-    vod_start = 0
-    for segment in playlist.segments:
-        vod_end = vod_start + segment.duration
-
-        # `vod_end > start` is used here becuase it's better to download a bit
-        # more than a bit less, similar for the end condition
-        start_condition = not start or vod_end > start
-        end_condition = not end or vod_start < end
-
-        if start_condition and end_condition and segment.uri not in files:
-            files.append(segment.uri)
-
-        vod_start = vod_end
-
-    return files
-
-
 def _crete_temp_dir(base_uri: str) -> str:
     """Create a temp dir to store downloads if it doesn't exist."""
     path = urlparse(base_uri).path.lstrip("/")
@@ -201,8 +156,8 @@ def _crete_temp_dir(base_uri: str) -> str:
     return str(temp_dir)
 
 
-def _get_clip_url(clip, quality):
-    qualities = clip["videoQualities"]
+def _get_clip_url(access_token: ClipAccessToken, quality: str) -> str:
+    qualities = access_token["videoQualities"]
 
     # Quality given as an argument
     if quality:
@@ -219,18 +174,18 @@ def _get_clip_url(clip, quality):
         raise ConsoleError(msg)
 
     # Ask user to select quality
-    print_out("\nAvailable qualities:")
+    click.echo("\nAvailable qualities:")
     for n, q in enumerate(qualities):
-        print_out(f"{n + 1}) {q['quality']} [{q['frameRate']} fps]")
-    print_out()
+        click.echo(f"{n + 1}) {bold(q['quality'])} [{q['frameRate']} fps]")
+    click.echo()
 
     no = utils.read_int("Choose quality", min=1, max=len(qualities), default=1)
     selected_quality = qualities[no - 1]
     return selected_quality["sourceURL"]
 
 
-def get_clip_authenticated_url(slug, quality):
-    print_out("<dim>Fetching access token...</dim>")
+def get_clip_authenticated_url(slug: str, quality: str):
+    print_log("Fetching access token...")
     access_token = twitch.get_clip_access_token(slug)
 
     if not access_token:
@@ -238,150 +193,141 @@ def get_clip_authenticated_url(slug, quality):
 
     url = _get_clip_url(access_token, quality)
 
-    query = urlencode({
-        "sig": access_token["playbackAccessToken"]["signature"],
-        "token": access_token["playbackAccessToken"]["value"],
-    })
+    query = urlencode(
+        {
+            "sig": access_token["playbackAccessToken"]["signature"],
+            "token": access_token["playbackAccessToken"]["value"],
+        }
+    )
 
     return f"{url}?{query}"
 
 
 def _download_clip(slug: str, args: DownloadOptions) -> None:
-    print_out("<dim>Looking up clip...</dim>")
+    print_log("Looking up clip...")
     clip = twitch.get_clip(slug)
 
     if not clip:
         raise ConsoleError(f"Clip '{slug}' not found")
 
-
     title = clip["title"]
     user = clip["broadcaster"]["displayName"]
     game = clip["game"]["name"] if clip["game"] else "Unknown"
     duration = utils.format_duration(clip["durationSeconds"])
-
-    print_out(
-        f"Found: <green>{title}</green> by <yellow>{user}</yellow>, "+
-        f"playing <blue>{game}</blue> ({duration})"
-    )
+    click.echo(f"Found: {green(title)} by {yellow(user)}, playing {blue(game)} ({duration})")
 
     target = _clip_target_filename(clip, args)
-    print_out(f"Target: <blue>{target}</blue>")
+    click.echo(f"Target: {blue(target)}")
 
     if not args.overwrite and path.exists(target):
-        response = input("File exists. Overwrite? [Y/n]: ")
-        if response.lower().strip() not in ["", "y"]:
-            raise ConsoleError("Aborted")
+        response = click.prompt("File exists. Overwrite? [Y/n]", default="Y", show_default=False)
+        if response.lower().strip() != "y":
+            raise click.Abort()
         args.overwrite = True
 
     url = get_clip_authenticated_url(slug, args.quality)
-    print_out(f"<dim>Selected URL: {url}</dim>")
+    print_log(f"Selected URL: {url}")
 
-    print_out("<dim>Downloading clip...</dim>")
-
-    if (args.dry_run is False):
+    if args.dry_run:
+        click.echo("Dry run, clip not downloaded.")
+    else:
+        print_log("Downloading clip...")
         download_file(url, target)
-
-    print_out(f"Downloaded: <blue>{target}</blue>")
+        click.echo(f"Downloaded: {blue(target)}")
 
 
-def _download_video(video_id, args: DownloadOptions) -> None:
+def _download_video(video_id: str, args: DownloadOptions) -> None:
     if args.start and args.end and args.end <= args.start:
         raise ConsoleError("End time must be greater than start time")
 
-    print_out("<dim>Looking up video...</dim>")
+    print_log("Looking up video...")
     video = twitch.get_video(video_id)
 
     if not video:
         raise ConsoleError(f"Video {video_id} not found")
 
-    title = video['title']
-    user = video['creator']['displayName']
-    print_out(f"Found: <blue>{title}</blue> by <yellow>{user}</yellow>")
+    click.echo(f"Found: {blue(video['title'])} by {yellow(video['creator']['displayName'])}")
 
     target = _video_target_filename(video, args)
-    print_out(f"Output: <blue>{target}</blue>")
+    click.echo(f"Output: {blue(target)}")
 
     if not args.overwrite and path.exists(target):
-        response = input("File exists. Overwrite? [Y/n]: ")
-        if response.lower().strip() not in ["", "y"]:
-            raise ConsoleError("Aborted")
+        response = click.prompt("File exists. Overwrite? [Y/n]", default="Y", show_default=False)
+        if response.lower().strip() != "y":
+            raise click.Abort()
         args.overwrite = True
 
     # Chapter select or manual offset
     start, end = _determine_time_range(video_id, args)
 
-    print_out("<dim>Fetching access token...</dim>")
+    print_log("Fetching access token...")
     access_token = twitch.get_access_token(video_id, auth_token=args.auth_token)
 
-    print_out("<dim>Fetching playlists...</dim>")
-    playlists_m3u8 = twitch.get_playlists(video_id, access_token)
-    playlists = list(_parse_playlists(playlists_m3u8))
-    playlist_uri = (_get_playlist_by_name(playlists, args.quality) if args.quality
-            else _select_playlist_interactive(playlists))
+    print_log("Fetching playlists...")
+    playlists_text = twitch.get_playlists(video_id, access_token)
+    playlists = parse_playlists(playlists_text)
+    playlist = select_playlist(playlists, args.quality)
 
-    print_out("<dim>Fetching playlist...</dim>")
-    response = httpx.get(playlist_uri)
-    response.raise_for_status()
-    playlist = m3u8.loads(response.text)
+    print_log("Fetching playlist...")
+    vods_text = http_get(playlist.url)
+    vods_m3u8 = load_m3u8(vods_text)
+    vods = enumerate_vods(vods_m3u8, start, end)
 
-    base_uri = re.sub("/[^/]+$", "/", playlist_uri)
+    base_uri = re.sub("/[^/]+$", "/", playlist.url)
     target_dir = _crete_temp_dir(base_uri)
-    vod_paths = _get_vod_paths(playlist, start, end)
 
     # Save playlists for debugging purposes
     with open(path.join(target_dir, "playlists.m3u8"), "w") as f:
-        f.write(playlists_m3u8)
+        f.write(playlists_text)
     with open(path.join(target_dir, "playlist.m3u8"), "w") as f:
-        f.write(response.text)
+        f.write(vods_text)
 
-    print_out(f"\nDownloading {len(vod_paths)} VODs using {args.max_workers} workers to {target_dir}")
-    sources = [base_uri + path for path in vod_paths]
-    targets = [os.path.join(target_dir, f"{k:05d}.ts") for k, _ in enumerate(vod_paths)]
+    click.echo(f"\nDownloading {len(vods)} VODs using {args.max_workers} workers to {target_dir}")
+
+    sources = [base_uri + vod.path for vod in vods]
+    targets = [os.path.join(target_dir, f"{vod.index:05d}.ts") for vod in vods]
     asyncio.run(download_all(sources, targets, args.max_workers, rate_limit=args.rate_limit))
 
-    # Make a modified playlist which references downloaded VODs
-    # Keep only the downloaded segments and skip the rest
-    org_segments = playlist.segments.copy()
-
-    path_map = OrderedDict(zip(vod_paths, targets))
-    playlist.segments.clear()
-    for segment in org_segments:
-        if segment.uri in path_map:
-            segment.uri = path_map[segment.uri]
-            playlist.segments.append(segment)
-
-    playlist_path = path.join(target_dir, "playlist_downloaded.m3u8")
-    playlist.dump(playlist_path)
-
-    print_out("")
+    join_playlist = make_join_playlist(vods_m3u8, vods, targets)
+    join_playlist_path = path.join(target_dir, "playlist_downloaded.m3u8")
+    join_playlist.dump(join_playlist_path)  # type: ignore
+    click.echo()
 
     if args.no_join:
-        print_out("<dim>Skipping joining files...</dim>")
-        print_out(f"VODs downloaded to:\n<blue>{target_dir}</blue>")
+        print_log("Skipping joining files...")
+        click.echo(f"VODs downloaded to:\n{blue(target_dir)}")
         return
 
     if args.concat:
-        print_out("<dim>Concating files...</dim>")
+        print_log("Concating files...")
         _concat_vods(targets, target)
     else:
-        print_out("<dim>Joining files...</dim>")
-        _join_vods(playlist_path, target, args.overwrite, video)
+        print_log("Joining files...")
+        _join_vods(join_playlist_path, target, args.overwrite, video)
+
+    click.echo()
 
     if args.keep:
-        print_out(f"\n<dim>Temporary files not deleted: {target_dir}</dim>")
+        click.echo(f"Temporary files not deleted: {target_dir}")
     else:
-        print_out("\n<dim>Deleting temporary files...</dim>")
+        print_log("Deleting temporary files...")
         shutil.rmtree(target_dir)
 
-    print_out(f"\nDownloaded: <green>{target}</green>")
+    click.echo(f"\nDownloaded: {green(target)}")
 
 
-def _determine_time_range(video_id, args: DownloadOptions):
+def http_get(url: str) -> str:
+    response = httpx.get(url)
+    response.raise_for_status()
+    return response.text
+
+
+def _determine_time_range(video_id: str, args: DownloadOptions):
     if args.start or args.end:
         return args.start, args.end
 
     if args.chapter is not None:
-        print_out("<dim>Fetching chapters...</dim>")
+        print_log("Fetching chapters...")
         chapters = twitch.get_video_chapters(video_id)
 
         if not chapters:
@@ -393,9 +339,11 @@ def _determine_time_range(video_id, args: DownloadOptions):
             try:
                 chapter = chapters[args.chapter - 1]
             except IndexError:
-                raise ConsoleError(f"Chapter {args.chapter} does not exist. This video has {len(chapters)} chapters.")
+                raise ConsoleError(
+                    f"Chapter {args.chapter} does not exist. This video has {len(chapters)} chapters."
+                )
 
-        print_out(f'Chapter selected: <blue>{chapter["description"]}</blue>\n')
+        click.echo(f'Chapter selected: {blue(chapter["description"])}\n')
         start = chapter["positionMilliseconds"] // 1000
         duration = chapter["durationMilliseconds"] // 1000
         return start, start + duration
@@ -403,11 +351,11 @@ def _determine_time_range(video_id, args: DownloadOptions):
     return None, None
 
 
-def _choose_chapter_interactive(chapters):
-    print_out("\nChapters:")
+def _choose_chapter_interactive(chapters: List[Chapter]):
+    click.echo("\nChapters:")
     for index, chapter in enumerate(chapters):
         duration = utils.format_time(chapter["durationMilliseconds"] // 1000)
-        print_out(f'{index + 1}) <b>{chapter["description"]}</b> <dim>({duration})</dim>')
+        click.echo(f'{index + 1}) {bold(chapter["description"])} ({duration})')
     index = utils.read_int("Select a chapter", 1, len(chapters))
     chapter = chapters[index - 1]
     return chapter

twitchdl/commands/info.py

@@ -1,11 +1,17 @@
+from typing import List
+
+import click
 import m3u8
 
-from twitchdl import utils, twitch
-from twitchdl.commands.download import get_video_substitutions
+from twitchdl import twitch, utils
+from twitchdl.commands.download import get_video_placeholders
 from twitchdl.exceptions import ConsoleError
-from twitchdl.output import print_video, print_clip, print_json, print_out, print_log
+from twitchdl.output import bold, print_clip, print_json, print_log, print_table, print_video
+from twitchdl.playlists import parse_playlists
+from twitchdl.twitch import Chapter, Clip, Video
 
-def info(id: str, *, json: bool = False, format="mkv"):
+
+def info(id: str, *, json: bool = False):
     video_id = utils.parse_video_identifier(id)
     if video_id:
         print_log("Fetching video...")
@@ -23,16 +29,10 @@ def info(id: str, *, json: bool = False, format="mkv"):
         print_log("Fetching chapters...")
         chapters = twitch.get_video_chapters(video_id)
 
-        substitutions = get_video_substitutions(video, format)
-
         if json:
             video_json(video, playlists, chapters)
         else:
             video_info(video, playlists, chapters)
-
-            print_out("\nOutput format placeholders:")
-            for k, v in substitutions.items():
-                print(f" * {k} = {v}")
         return
 
     clip_slug = utils.parse_clip_identifier(id)
@@ -51,25 +51,29 @@ def info(id: str, *, json: bool = False, format="mkv"):
     raise ConsoleError(f"Invalid input: {id}")
 
 
-def video_info(video, playlists, chapters):
-    print_out()
+def video_info(video: Video, playlists: str, chapters: List[Chapter]):
+    click.echo()
     print_video(video)
 
-    print_out()
-    print_out("Playlists:")
-    for p in m3u8.loads(playlists).playlists:
-        print_out(f"<b>{p.stream_info.video}</b> {p.uri}")
+    click.echo("Playlists:")
+    for p in parse_playlists(playlists):
+        click.echo(f"{bold(p.name)} {p.url}")
 
     if chapters:
-        print_out()
-        print_out("Chapters:")
+        click.echo()
+        click.echo("Chapters:")
         for chapter in chapters:
             start = utils.format_time(chapter["positionMilliseconds"] // 1000, force_hours=True)
             duration = utils.format_time(chapter["durationMilliseconds"] // 1000)
-            print_out(f'{start} <b>{chapter["description"]}</b> ({duration})')
+            click.echo(f'{start} {bold(chapter["description"])} ({duration})')
+
+    placeholders = get_video_placeholders(video, format="mkv")
+    placeholders = [[f"{{{k}}}", v] for k, v in placeholders.items()]
+    click.echo("")
+    print_table(["Placeholder", "Value"], placeholders)
 
 
-def video_json(video, playlists, chapters):
+def video_json(video: Video, playlists: str, chapters: List[Chapter]):
     playlists = m3u8.loads(playlists).playlists
 
     video["playlists"] = [
@@ -78,8 +82,9 @@ def video_json(video, playlists, chapters):
             "resolution": p.stream_info.resolution,
             "codecs": p.stream_info.codecs,
             "video": p.stream_info.video,
-            "uri": p.uri
-        } for p in playlists
+            "uri": p.uri,
+        }
+        for p in playlists
     ]
 
     video["chapters"] = chapters
@@ -87,11 +92,11 @@ def video_json(video, playlists, chapters):
     print_json(video)
 
 
-def clip_info(clip):
-    print_out()
+def clip_info(clip: Clip):
+    click.echo()
     print_clip(clip)
-    print_out()
-    print_out("Download links:")
+    click.echo()
+    click.echo("Download links:")
 
     for q in clip["videoQualities"]:
-        print_out("<b>{quality}p{frameRate}</b> {sourceURL}".format(**q))
+        click.echo(f"{bold(q['quality'])} [{q['frameRate']} fps] {q['sourceURL']}")

twitchdl/commands/videos.py

@@ -1,8 +1,11 @@
 import sys
+from typing import List, Optional
+
+import click
 
 from twitchdl import twitch
 from twitchdl.exceptions import ConsoleError
-from twitchdl.output import print_out, print_paged_videos, print_video, print_json, print_video_compact
+from twitchdl.output import print_json, print_log, print_paged, print_video, print_video_compact
 
 
 def videos(
@@ -10,12 +13,12 @@ def videos(
     *,
     all: bool,
     compact: bool,
-    games: list[str],
+    games: List[str],
     json: bool,
-    limit: int | None,
-    pager: int | None,
-    sort: str,
-    type: str,
+    limit: Optional[int],
+    pager: Optional[int],
+    sort: twitch.VideosSort,
+    type: twitch.VideosType,
 ):
     game_ids = _get_game_ids(games)
 
@@ -26,23 +29,21 @@ def videos(
     max_videos = sys.maxsize if all or pager else limit
 
     total_count, generator = twitch.channel_videos_generator(
-        channel_name, max_videos, sort, type, game_ids=game_ids)
+        channel_name, max_videos, sort, type, game_ids=game_ids
+    )
 
     if json:
         videos = list(generator)
-        print_json({
-            "count": len(videos),
-            "totalCount": total_count,
-            "videos": videos
-        })
+        print_json({"count": len(videos), "totalCount": total_count, "videos": videos})
         return
 
     if total_count == 0:
-        print_out("<yellow>No videos found</yellow>")
+        click.echo("No videos found")
         return
 
     if pager:
-        print_paged_videos(generator, pager, total_count)
+        print_fn = print_video_compact if compact else print_video
+        print_paged("Videos", generator, print_fn, pager, total_count)
         return
 
     count = 0
@@ -50,28 +51,29 @@ def videos(
         if compact:
             print_video_compact(video)
         else:
-            print_out()
+            click.echo()
             print_video(video)
         count += 1
 
-    print_out()
-    print_out("-" * 80)
-    print_out(f"<yellow>Videos 1-{count} of {total_count}</yellow>")
+    click.echo()
+    click.echo("-" * 80)
+    click.echo(f"Videos 1-{count} of {total_count}")
 
     if total_count > count:
-        print_out()
-        print_out(
-            "<dim>There are more videos. Increase the --limit, use --all or --pager to see the rest.</dim>"
+        click.secho(
+            "\nThere are more videos. "
+            + "Increase the --limit, use --all or --pager to see the rest.",
+            dim=True,
         )
 
 
-def _get_game_ids(names):
+def _get_game_ids(names: List[str]) -> List[str]:
     if not names:
         return []
 
     game_ids = []
     for name in names:
-        print_out(f"<dim>Looking up game '{name}'...</dim>")
+        print_log(f"Looking up game '{name}'...")
         game_id = twitch.get_game_id(name)
         if not game_id:
             raise ConsoleError(f"Game '{name}' not found")

twitchdl/download.py

@@ -1,4 +1,5 @@
 import os
+
 import httpx
 
 from twitchdl.exceptions import ConsoleError

twitchdl/entities.py

@@ -1,25 +1,25 @@
 from dataclasses import dataclass
-from typing import Any
+from typing import Any, Mapping, Optional
 
 
 @dataclass
 class DownloadOptions:
-    auth_token: str | None
-    chapter: int | None
+    auth_token: Optional[str]
+    chapter: Optional[int]
     concat: bool
     dry_run: bool
-    end: int | None
+    end: Optional[int]
     format: str
     keep: bool
     no_join: bool
     overwrite: bool
     output: str
-    quality: str | None
-    rate_limit: str | None
-    start: int | None
+    quality: Optional[str]
+    rate_limit: Optional[int]
+    start: Optional[int]
     max_workers: int
 
 
 # Type for annotating decoded JSON
 # TODO: make data classes for common structs
-Data = dict[str, Any]
+Data = Mapping[str, Any]

twitchdl/exceptions.py

@@ -1,5 +1,7 @@
 import click
 
+
 class ConsoleError(click.ClickException):
     """Raised when an error occurs and script exectuion should halt."""
+
     pass

twitchdl/http.py

@@ -1,12 +1,12 @@
 import asyncio
-import httpx
 import logging
 import os
 import time
-
 from abc import ABC, abstractmethod
 from typing import List, Optional
 
+import httpx
+
 from twitchdl.progress import Progress
 
 logger = logging.getLogger(__name__)
@@ -62,6 +62,7 @@ class LimitingTokenBucket(TokenBucket):
 
 class EndlessTokenBucket(TokenBucket):
     """Used when download speed is not limited."""
+
     def advance(self, size: int):
         pass
 
@@ -122,12 +123,22 @@ async def download_all(
     targets: List[str],
     workers: int,
     *,
-    rate_limit: Optional[int] = None
+    rate_limit: Optional[int] = None,
 ):
     progress = Progress(len(sources))
     token_bucket = LimitingTokenBucket(rate_limit) if rate_limit else EndlessTokenBucket()
     async with httpx.AsyncClient(timeout=TIMEOUT) as client:
         semaphore = asyncio.Semaphore(workers)
-        tasks = [download_with_retries(client, semaphore, task_id, source, target, progress, token_bucket)
-                 for task_id, (source, target) in enumerate(zip(sources, targets))]
+        tasks = [
+            download_with_retries(
+                client,
+                semaphore,
+                task_id,
+                source,
+                target,
+                progress,
+                token_bucket,
+            )
+            for task_id, (source, target) in enumerate(zip(sources, targets))
+        ]
         await asyncio.gather(*tasks)

twitchdl/output.py

@@ -1,112 +1,56 @@
 import json
-import sys
-import re
-
 from itertools import islice
+from typing import Any, Callable, Generator, List, Optional, TypeVar
+
+import click
+
 from twitchdl import utils
-from typing import Any, Match
+from twitchdl.twitch import Clip, Video
 
-
-START_CODES = {
-    'b': '\033[1m',
-    'dim': '\033[2m',
-    'i': '\033[3m',
-    'u': '\033[4m',
-    'red': '\033[91m',
-    'green': '\033[92m',
-    'yellow': '\033[93m',
-    'blue': '\033[94m',
-    'magenta': '\033[95m',
-    'cyan': '\033[96m',
-}
-
-END_CODE = '\033[0m'
-
-START_PATTERN = "<(" + "|".join(START_CODES.keys()) + ")>"
-END_PATTERN = "</(" + "|".join(START_CODES.keys()) + ")>"
-
-USE_ANSI_COLOR = "--no-color" not in sys.argv
-
-
-def start_code(match: Match[str]) -> str:
-    name = match.group(1)
-    return START_CODES[name]
-
-
-def colorize(text: str) -> str:
-    text = re.sub(START_PATTERN, start_code, text)
-    text = re.sub(END_PATTERN, END_CODE, text)
-
-    return text
-
-
-def strip_tags(text: str) -> str:
-    text = re.sub(START_PATTERN, '', text)
-    text = re.sub(END_PATTERN, '', text)
-
-    return text
+T = TypeVar("T")
 
 
 def truncate(string: str, length: int) -> str:
     if len(string) > length:
-        return string[:length - 1] + "…"
+        return string[: length - 1] + "…"
 
     return string
 
 
-def print_out(*args, **kwargs):
-    args = [colorize(a) if USE_ANSI_COLOR else strip_tags(a) for a in args]
-    print(*args, **kwargs)
-
-
 def print_json(data: Any):
-    print(json.dumps(data))
+    click.echo(json.dumps(data))
 
 
-def print_err(*args, **kwargs):
-    args = [f"<red>{arg}</red>" for arg in args]
-    args = [colorize(a) if USE_ANSI_COLOR else strip_tags(a) for a in args]
-    print(*args, file=sys.stderr, **kwargs)
+def print_log(message: Any):
+    click.secho(message, err=True, dim=True)
 
 
-def print_log(*args, **kwargs):
-    args = [f"<dim>{a}</dim>" for a in args]
-    args = [colorize(a) if USE_ANSI_COLOR else strip_tags(a) for a in args]
-    print(*args, file=sys.stderr, **kwargs)
+def print_table(headers: List[str], data: List[List[str]]):
+    widths = [[len(cell) for cell in row] for row in data + [headers]]
+    widths = [max(width) for width in zip(*widths)]
+    underlines = ["-" * width for width in widths]
+
+    def print_row(row: List[str]):
+        for idx, cell in enumerate(row):
+            width = widths[idx]
+            click.echo(cell.ljust(width), nl=False)
+            click.echo("  ", nl=False)
+        click.echo()
+
+    print_row(headers)
+    print_row(underlines)
+
+    for row in data:
+        print_row(row)
 
 
-def print_video(video):
-    published_at = video["publishedAt"].replace("T", " @ ").replace("Z", "")
-    length = utils.format_duration(video["lengthSeconds"])
-
-    channel = f"<blue>{video['creator']['displayName']}</blue>" if video["creator"] else ""
-    playing = f"playing <blue>{video['game']['name']}</blue>" if video["game"] else ""
-
-    # Can't find URL in video object, strange
-    url = f"https://www.twitch.tv/videos/{video['id']}"
-
-    print_out(f"<b>Video {video['id']}</b>")
-    print_out(f"<green>{video['title']}</green>")
-
-    if channel or playing:
-        print_out(" ".join([channel, playing]))
-
-    if video["description"]:
-        print_out(f"Description: {video['description']}")
-
-    print_out(f"Published <blue>{published_at}</blue>  Length: <blue>{length}</blue> ")
-    print_out(f"<i>{url}</i>")
-
-
-def print_video_compact(video):
-    id = video["id"]
-    date = video["publishedAt"][:10]
-    game = video["game"]["name"] if video["game"] else ""
-    title = truncate(video["title"], 80).ljust(80)
-    print_out(f'<b>{id}</b> {date} <green>{title}</green> <blue>{game}</blue>')
-
-
-def print_paged_videos(generator, page_size, total_count):
+def print_paged(
+    label: str,
+    generator: Generator[T, Any, Any],
+    print_fn: Callable[[T], None],
+    page_size: int,
+    total_count: Optional[int] = None,
+):
     iterator = iter(generator)
     page = list(islice(iterator, page_size))
 
@@ -114,48 +58,89 @@ def print_paged_videos(generator, page_size, total_count):
     last = first + len(page) - 1
 
     while True:
-        print_out("-" * 80)
+        click.echo("-" * 80)
 
-        print_out()
-        for video in page:
-            print_video(video)
-            print_out()
+        click.echo()
+        for item in page:
+            print_fn(item)
 
         last = first + len(page) - 1
 
-        print_out("-" * 80)
-        print_out(f"<yellow>Videos {first}-{last} of {total_count}</yellow>")
+        click.echo("-" * 80)
+        click.echo(f"{label} {first}-{last} of {total_count or '???'}")
 
         first = first + len(page)
         last = first + 1
 
         page = list(islice(iterator, page_size))
-        if not page or not _continue():
+        if not page or not prompt_continue():
             break
 
 
-def print_clip(clip):
+def print_video(video: Video):
+    published_at = video["publishedAt"].replace("T", " @ ").replace("Z", "")
+    length = utils.format_duration(video["lengthSeconds"])
+
+    channel = blue(video["creator"]["displayName"]) if video["creator"] else ""
+    playing = f"playing {blue(video['game']['name'])}" if video["game"] else ""
+
+    # Can't find URL in video object, strange
+    url = f"https://www.twitch.tv/videos/{video['id']}"
+
+    click.secho(f"Video {video['id']}", bold=True)
+    click.secho(video["title"], fg="green")
+
+    if channel or playing:
+        click.echo(" ".join([channel, playing]))
+
+    if video["description"]:
+        click.echo(f"Description: {video['description']}")
+
+    click.echo(f"Published {blue(published_at)}  Length: {blue(length)} ")
+    click.secho(url, italic=True)
+    click.echo()
+
+
+def print_video_compact(video: Video):
+    id = video["id"]
+    date = video["publishedAt"][:10]
+    game = video["game"]["name"] if video["game"] else ""
+    title = truncate(video["title"], 80).ljust(80)
+    click.echo(f"{bold(id)} {date} {green(title)} {blue(game)}")
+
+
+def print_clip(clip: Clip):
     published_at = clip["createdAt"].replace("T", " @ ").replace("Z", "")
     length = utils.format_duration(clip["durationSeconds"])
     channel = clip["broadcaster"]["displayName"]
-    playing = (
-        f"playing <blue>{clip['game']['name']}</blue>"
-        if clip["game"] else ""
+    playing = f"playing {blue(clip['game']['name'])}" if clip["game"] else ""
+
+    click.echo(f"Clip {bold(clip['slug'])}")
+    click.secho(clip["title"], fg="green")
+    click.echo(f"{blue(channel)} {playing}")
+    click.echo(
+        f"Published {blue(published_at)}"
+        + f"  Length: {blue(length)}"
+        + f"  Views: {blue(clip['viewCount'])}"
     )
-
-    print_out(f"Clip <b>{clip['slug']}</b>")
-    print_out(f"<green>{clip['title']}</green>")
-    print_out(f"<blue>{channel}</blue> {playing}")
-    print_out(
-        f"Published <blue>{published_at}</blue>" +
-        f"  Length: <blue>{length}</blue>" +
-        f"  Views: <blue>{clip["viewCount"]}</blue>"
-    )
-    print_out(f"<i>{clip['url']}</i>")
+    click.secho(clip["url"], italic=True)
+    click.echo()
 
 
-def _continue():
-    print_out("Press <green><b>Enter</green> to continue, <yellow><b>Ctrl+C</yellow> to break.")
+def print_clip_compact(clip: Clip):
+    slug = clip["slug"]
+    date = clip["createdAt"][:10]
+    title = truncate(clip["title"], 50).ljust(50)
+    game = clip["game"]["name"] if clip["game"] else ""
+    game = truncate(game, 30).ljust(30)
+
+    click.echo(f"{date} {green(title)} {blue(game)} {bold(slug)}")
+
+
+def prompt_continue():
+    enter = click.style("Enter", bold=True, fg="green")
+    ctrl_c = click.style("Ctrl+C", bold=True, fg="yellow")
+    click.echo(f"Press {enter} to continue, {ctrl_c} to break.")
 
     try:
         input()
@@ -163,3 +148,30 @@ def _continue():
         return False
 
     return True
+
+
+# Shorthand functions for coloring output
+
+
+def blue(text: Any) -> str:
+    return click.style(text, fg="blue")
+
+
+def cyan(text: Any) -> str:
+    return click.style(text, fg="cyan")
+
+
+def green(text: Any) -> str:
+    return click.style(text, fg="green")
+
+
+def yellow(text: Any) -> str:
+    return click.style(text, fg="yellow")
+
+
+def bold(text: Any) -> str:
+    return click.style(text, bold=True)
+
+
+def dim(text: Any) -> str:
+    return click.style(text, dim=True)

twitchdl/playlists.py

@@ -0,0 +1,135 @@
+"""
+Parse and manipulate m3u8 playlists.
+"""
+
+from dataclasses import dataclass
+from typing import Generator, List, Optional, OrderedDict
+
+import click
+import m3u8
+
+from twitchdl import utils
+from twitchdl.output import bold, dim
+
+
+@dataclass
+class Playlist:
+    name: str
+    resolution: Optional[str]
+    url: str
+
+
+@dataclass
+class Vod:
+    index: int
+    """Ordinal number of the VOD in the playlist"""
+    path: str
+    """Path part of the VOD URL"""
+    duration: int
+    """Segment duration in seconds"""
+
+
+def parse_playlists(playlists_m3u8: str) -> List[Playlist]:
+    def _parse(source: str) -> Generator[Playlist, None, None]:
+        document = load_m3u8(source)
+
+        for p in document.playlists:
+            from pprint import pp
+
+            pp(p.__dict__)
+            pp(p.stream_info.__dict__)
+            if p.stream_info.resolution:
+                name = p.media[0].name
+                resolution = "x".join(str(r) for r in p.stream_info.resolution)
+            else:
+                name = p.media[0].group_id
+                resolution = None
+
+            yield Playlist(name, resolution, p.uri)
+
+    # Move audio to bottom, it has no resolution
+    return sorted(_parse(playlists_m3u8), key=lambda p: p.resolution is None)
+
+
+def load_m3u8(playlist_m3u8: str) -> m3u8.M3U8:
+    return m3u8.loads(playlist_m3u8)
+
+
+def enumerate_vods(
+    document: m3u8.M3U8,
+    start: Optional[int] = None,
+    end: Optional[int] = None,
+) -> List[Vod]:
+    """Extract VODs for download from document."""
+    vods = []
+    vod_start = 0
+
+    for index, segment in enumerate(document.segments):
+        vod_end = vod_start + segment.duration
+
+        # `vod_end > start` is used here becuase it's better to download a bit
+        # more than a bit less, similar for the end condition
+        start_condition = not start or vod_end > start
+        end_condition = not end or vod_start < end
+
+        if start_condition and end_condition:
+            vods.append(Vod(index, segment.uri, segment.duration))
+
+        vod_start = vod_end
+
+    return vods
+
+
+def make_join_playlist(
+    playlist: m3u8.M3U8,
+    vods: List[Vod],
+    targets: List[str],
+) -> m3u8.Playlist:
+    """
+    Make a modified playlist which references downloaded VODs
+    Keep only the downloaded segments and skip the rest
+    """
+    org_segments = playlist.segments.copy()
+
+    path_map = OrderedDict(zip([v.path for v in vods], targets))
+    playlist.segments.clear()
+    for segment in org_segments:
+        if segment.uri in path_map:
+            segment.uri = path_map[segment.uri]
+            playlist.segments.append(segment)
+
+    return playlist
+
+
+def select_playlist(playlists: List[Playlist], quality: Optional[str]) -> Playlist:
+    return (
+        select_playlist_by_name(playlists, quality)
+        if quality is not None
+        else select_playlist_interactive(playlists)
+    )
+
+
+def select_playlist_by_name(playlists: List[Playlist], quality: str) -> Playlist:
+    if quality == "source":
+        return playlists[0]
+
+    for playlist in playlists:
+        if playlist.name == quality:
+            return playlist
+
+    available = ", ".join([p.name for p in playlists])
+    msg = f"Quality '{quality}' not found. Available qualities are: {available}"
+    raise click.ClickException(msg)
+
+
+def select_playlist_interactive(playlists: List[Playlist]) -> Playlist:
+    click.echo("\nAvailable qualities:")
+    for n, playlist in enumerate(playlists):
+        if playlist.resolution:
+            click.echo(f"{n + 1}) {bold(playlist.name)} {dim(f'({playlist.resolution})')}")
+        else:
+            click.echo(f"{n + 1}) {bold(playlist.name)}")
+
+    no = utils.read_int("Choose quality", min=1, max=len(playlists) + 1, default=1)
+    playlist = playlists[no - 1]
+    return playlist

twitchdl/progress.py

@@ -1,12 +1,13 @@
 import logging
 import time
-
 from collections import deque
 from dataclasses import dataclass, field
 from statistics import mean
-from typing import Dict, NamedTuple, Optional, Deque
+from typing import Deque, Dict, NamedTuple, Optional
 
-from twitchdl.output import print_out
+import click
+
+from twitchdl.output import blue
 from twitchdl.utils import format_size, format_time
 
 logger = logging.getLogger(__name__)
@@ -93,18 +94,28 @@ class Progress:
 
         task = self.tasks[task_id]
         if task.size != task.downloaded:
-            logger.warn(f"Taks {task_id} ended with {task.downloaded}b downloaded, expected {task.size}b.")
+            logger.warn(
+                f"Taks {task_id} ended with {task.downloaded}b downloaded, expected {task.size}b."
+            )
 
         self.vod_downloaded_count += 1
         self.print()
 
     def _calculate_total(self):
-        self.estimated_total = int(mean(t.size for t in self.tasks.values()) * self.vod_count) if self.tasks else None
+        self.estimated_total = (
+            int(mean(t.size for t in self.tasks.values()) * self.vod_count) if self.tasks else None
+        )
 
     def _calculate_progress(self):
         self.speed = self._calculate_speed()
-        self.progress_perc = int(100 * self.progress_bytes / self.estimated_total) if self.estimated_total else 0
-        self.remaining_time = int((self.estimated_total - self.progress_bytes) / self.speed) if self.estimated_total and self.speed else None
+        self.progress_perc = (
+            int(100 * self.progress_bytes / self.estimated_total) if self.estimated_total else 0
+        )
+        self.remaining_time = (
+            int((self.estimated_total - self.progress_bytes) / self.speed)
+            if self.estimated_total and self.speed
+            else None
+        )
 
     def _calculate_speed(self):
         if len(self.samples) < 2:
@@ -116,7 +127,7 @@ class Progress:
         size = last_sample.downloaded - first_sample.downloaded
         duration = last_sample.timestamp - first_sample.timestamp
 
-        return size / duration
+        return size / duration if duration > 0 else None
 
     def print(self):
         now = time.time()
@@ -125,13 +136,20 @@ class Progress:
         if now - self.last_printed < 0.1:
             return
 
-        progress = " ".join([
-            f"Downloaded {self.vod_downloaded_count}/{self.vod_count} VODs",
-            f"<blue>{self.progress_perc}%</blue>",
-            f"of <blue>~{format_size(self.estimated_total)}</blue>" if self.estimated_total else "",
-            f"at <blue>{format_size(self.speed)}/s</blue>" if self.speed else "",
-            f"ETA <blue>{format_time(self.remaining_time)}</blue>" if self.remaining_time is not None else "",
-        ])
+        click.echo(f"\rDownloaded {self.vod_downloaded_count}/{self.vod_count} VODs", nl=False)
+        click.secho(f" {self.progress_perc}%", fg="blue", nl=False)
+
+        if self.estimated_total is not None:
+            total = f"~{format_size(self.estimated_total)}"
+            click.echo(f" of {blue(total)}", nl=False)
+
+        if self.speed is not None:
+            speed = f"{format_size(self.speed)}/s"
+            click.echo(f" at {blue(speed)}", nl=False)
+
+        if self.remaining_time is not None:
+            click.echo(f" ETA {blue(format_time(self.remaining_time))}", nl=False)
+
+        click.echo("    ", nl=False)
 
-        print_out(f"\r{progress}     ", end="")
         self.last_printed = now

twitchdl/twitch.py

@@ -2,17 +2,85 @@
 Twitch API access.
 """
 
-import httpx
 import json
-import click
+from typing import Dict, Generator, List, Literal, Mapping, Optional, Tuple, TypedDict
+
+import click
+import httpx
 
-from typing import Dict
 from twitchdl import CLIENT_ID
+from twitchdl.entities import Data
 from twitchdl.exceptions import ConsoleError
 
+ClipsPeriod = Literal["last_day", "last_week", "last_month", "all_time"]
+VideosSort = Literal["views", "time"]
+VideosType = Literal["archive", "highlight", "upload"]
+
+
+class AccessToken(TypedDict):
+    signature: str
+    value: str
+
+
+class User(TypedDict):
+    login: str
+    displayName: str
+
+
+class Game(TypedDict):
+    id: str
+    name: str
+
+
+class VideoQuality(TypedDict):
+    frameRate: str
+    quality: str
+    sourceURL: str
+
+
+class ClipAccessToken(TypedDict):
+    id: str
+    playbackAccessToken: AccessToken
+    videoQualities: List[VideoQuality]
+
+
+class Clip(TypedDict):
+    id: str
+    slug: str
+    title: str
+    createdAt: str
+    viewCount: int
+    durationSeconds: int
+    url: str
+    videoQualities: List[VideoQuality]
+    game: Game
+    broadcaster: User
+
+
+class Video(TypedDict):
+    id: str
+    title: str
+    description: str
+    publishedAt: str
+    broadcastType: str
+    lengthSeconds: int
+    game: Game
+    creator: User
+
+
+class Chapter(TypedDict):
+    id: str
+    durationMilliseconds: int
+    positionMilliseconds: int
+    type: str
+    description: str
+    subDescription: str
+    thumbnailURL: str
+    game: Game
+
 
 class GQLError(click.ClickException):
-    def __init__(self, errors: list[str]):
+    def __init__(self, errors: List[str]):
         message = "GraphQL query failed."
         for error in errors:
             message += f"\n* {error}"
@@ -20,7 +88,7 @@ class GQLError(click.ClickException):
 
 
 def authenticated_post(url, data=None, json=None, headers={}):
-    headers['Client-ID'] = CLIENT_ID
+    headers["Client-ID"] = CLIENT_ID
 
     response = httpx.post(url, data=data, json=json, headers=headers)
     if response.status_code == 400:
@@ -61,6 +129,7 @@ VIDEO_FIELDS = """
     broadcastType
     lengthSeconds
     game {
+        id
         name
     }
     creator {
@@ -94,7 +163,7 @@ CLIP_FIELDS = """
 """
 
 
-def get_video(video_id: str):
+def get_video(video_id: str) -> Optional[Video]:
     query = f"""
     {{
         video(id: "{video_id}") {{
@@ -107,7 +176,7 @@ def get_video(video_id: str):
     return response["data"]["video"]
 
 
-def get_clip(slug: str):
+def get_clip(slug: str) -> Optional[Clip]:
     query = f"""
     {{
         clip(slug: "{slug}") {{
@@ -120,7 +189,7 @@ def get_clip(slug: str):
     return response["data"]["clip"]
 
 
-def get_clip_access_token(slug: str):
+def get_clip_access_token(slug: str) -> ClipAccessToken:
     query = f"""
     {{
         "operationName": "VideoAccessToken_Clip",
@@ -140,7 +209,12 @@ def get_clip_access_token(slug: str):
     return response["data"]["clip"]
 
 
-def get_channel_clips(channel_id: str, period: str, limit: int, after: str | None= None):
+def get_channel_clips(
+    channel_id: str,
+    period: ClipsPeriod,
+    limit: int,
+    after: Optional[str] = None,
+):
     """
     List channel clips.
 
@@ -177,8 +251,12 @@ def get_channel_clips(channel_id: str, period: str, limit: int, after: str | Non
     return response["data"]["user"]["clips"]
 
 
-def channel_clips_generator(channel_id, period, limit):
-    def _generator(clips, limit):
+def channel_clips_generator(
+    channel_id: str,
+    period: ClipsPeriod,
+    limit: int,
+) -> Generator[Clip, None, None]:
+    def _generator(clips: Data, limit: int) -> Generator[Clip, None, None]:
         for clip in clips["edges"]:
             if limit < 1:
                 return
@@ -199,11 +277,10 @@ def channel_clips_generator(channel_id, period, limit):
     return _generator(clips, limit)
 
 
-def channel_clips_generator_old(channel_id, period, limit):
+def channel_clips_generator_old(channel_id: str, period: ClipsPeriod, limit: int):
     cursor = ""
     while True:
-        clips = get_channel_clips(
-            channel_id, period, limit, after=cursor)
+        clips = get_channel_clips(channel_id, period, limit, after=cursor)
 
         if not clips["edges"]:
             break
@@ -222,8 +299,8 @@ def get_channel_videos(
     limit: int,
     sort: str,
     type: str = "archive",
-    game_ids: list[str] | None = None,
-    after: str | None = None
+    game_ids: Optional[List[str]] = None,
+    after: Optional[str] = None,
 ):
     game_ids = game_ids or []
 
@@ -262,8 +339,16 @@ def get_channel_videos(
     return response["data"]["user"]["videos"]
 
 
-def channel_videos_generator(channel_id, max_videos, sort, type, game_ids=[]):
-    def _generator(videos, max_videos):
+def channel_videos_generator(
+    channel_id: str,
+    max_videos: int,
+    sort: VideosSort,
+    type: VideosType,
+    game_ids: Optional[List[str]] = None,
+) -> Tuple[int, Generator[Video, None, None]]:
+    game_ids = game_ids or []
+
+    def _generator(videos: Data, max_videos: int) -> Generator[Video, None, None]:
         for video in videos["edges"]:
             if max_videos < 1:
                 return
@@ -284,7 +369,7 @@ def channel_videos_generator(channel_id, max_videos, sort, type, game_ids=[]):
     return videos["totalCount"], _generator(videos, max_videos)
 
 
-def get_access_token(video_id, auth_token=None):
+def get_access_token(video_id: str, auth_token: Optional[str] = None) -> AccessToken:
     query = f"""
     {{
         videoPlaybackAccessToken(
@@ -301,9 +386,9 @@ def get_access_token(video_id, auth_token=None):
     }}
     """
 
-    headers = {}
+    headers: Mapping[str, str] = {}
     if auth_token is not None:
-        headers['authorization'] = f'OAuth {auth_token}'
+        headers["authorization"] = f"OAuth {auth_token}"
 
     try:
         response = gql_query(query, headers=headers)
@@ -323,24 +408,27 @@ def get_access_token(video_id, auth_token=None):
         raise
 
 
-def get_playlists(video_id, access_token):
+def get_playlists(video_id: str, access_token: AccessToken) -> str:
     """
     For a given video return a playlist which contains possible video qualities.
     """
     url = f"https://usher.ttvnw.net/vod/{video_id}"
 
-    response = httpx.get(url, params={
-        "nauth": access_token['value'],
-        "nauthsig": access_token['signature'],
-        "allow_audio_only": "true",
-        "allow_source": "true",
-        "player": "twitchweb",
-    })
+    response = httpx.get(
+        url,
+        params={
+            "nauth": access_token["value"],
+            "nauthsig": access_token["signature"],
+            "allow_audio_only": "true",
+            "allow_source": "true",
+            "player": "twitchweb",
+        },
+    )
     response.raise_for_status()
-    return response.content.decode('utf-8')
+    return response.content.decode("utf-8")
 
 
-def get_game_id(name):
+def get_game_id(name: str):
     query = f"""
     {{
         game(name: "{name.strip()}") {{
@@ -355,30 +443,29 @@ def get_game_id(name):
         return game["id"]
 
 
-def get_video_chapters(video_id: str):
+def get_video_chapters(video_id: str) -> List[Chapter]:
     query = {
         "operationName": "VideoPlayer_ChapterSelectButtonVideo",
-        "variables":
-        {
+        "variables": {
             "includePrivate": False,
-            "videoID": video_id
+            "videoID": video_id,
         },
-        "extensions":
-        {
-            "persistedQuery":
-            {
+        "extensions": {
+            "persistedQuery": {
                 "version": 1,
-                "sha256Hash": "8d2793384aac3773beab5e59bd5d6f585aedb923d292800119e03d40cd0f9b41"
+                "sha256Hash": "8d2793384aac3773beab5e59bd5d6f585aedb923d292800119e03d40cd0f9b41",
             }
-        }
+        },
     }
 
     response = gql_post(json.dumps(query))
     return list(_chapter_nodes(response["data"]["video"]["moments"]))
 
 
-def _chapter_nodes(collection):
-    for edge in collection["edges"]:
+def _chapter_nodes(moments: Data) -> Generator[Chapter, None, None]:
+    for edge in moments["edges"]:
         node = edge["node"]
+        node["game"] = node["details"]["game"]
+        del node["details"]
         del node["moments"]
         yield node

twitchdl/utils.py

@@ -1,5 +1,8 @@
 import re
 import unicodedata
+from typing import Optional, Union
+
+import click
 
 
 def _format_size(value: float, digits: int, unit: str):
@@ -9,7 +12,7 @@ def _format_size(value: float, digits: int, unit: str):
         return f"{int(value)}{unit}"
 
 
-def format_size(bytes_: int, digits: int = 1):
+def format_size(bytes_: Union[int, float], digits: int = 1):
     if bytes_ < 1024:
         return _format_size(bytes_, digits, "B")
 
@@ -24,7 +27,7 @@ def format_size(bytes_: int, digits: int = 1):
     return _format_size(mega / 1024, digits, "GB")
 
 
-def format_duration(total_seconds: int | float) -> str:
+def format_duration(total_seconds: Union[int, float]) -> str:
     total_seconds = int(total_seconds)
     hours = total_seconds // 3600
     remainder = total_seconds % 3600
@@ -40,7 +43,7 @@ def format_duration(total_seconds: int | float) -> str:
     return f"{seconds} sec"
 
 
-def format_time(total_seconds: int | float, force_hours: bool = False) -> str:
+def format_time(total_seconds: Union[int, float], force_hours: bool = False) -> str:
     total_seconds = int(total_seconds)
     hours = total_seconds // 3600
     remainder = total_seconds % 3600
@@ -53,15 +56,10 @@ def format_time(total_seconds: int | float, force_hours: bool = False) -> str:
     return f"{minutes:02}:{seconds:02}"
 
 
-def read_int(msg: str, min: int, max: int, default: int | None = None) -> int:
-    if default:
-        msg = msg + f" [default {default}]"
-
-    msg += ": "
-
+def read_int(msg: str, min: int, max: int, default: Optional[int] = None) -> int:
     while True:
         try:
-            val = input(msg)
+            val = click.prompt(msg, default=default, type=int)
             if default and not val:
                 return default
             if min <= int(val) <= max:
@@ -71,16 +69,16 @@ def read_int(msg: str, min: int, max: int, default: int | None = None) -> int:
 
 
 def slugify(value: str) -> str:
-    value = unicodedata.normalize('NFKC', str(value))
-    value = re.sub(r'[^\w\s_-]', '', value)
-    value = re.sub(r'[\s_-]+', '_', value)
+    value = unicodedata.normalize("NFKC", str(value))
+    value = re.sub(r"[^\w\s_-]", "", value)
+    value = re.sub(r"[\s_-]+", "_", value)
     return value.strip("_").lower()
 
 
 def titlify(value: str) -> str:
-    value = unicodedata.normalize('NFKC', str(value))
-    value = re.sub(r'[^\w\s\[\]().-]', '', value)
-    value = re.sub(r'\s+', ' ', value)
+    value = unicodedata.normalize("NFKC", str(value))
+    value = re.sub(r"[^\w\s\[\]().-]", "", value)
+    value = re.sub(r"\s+", " ", value)
     return value.strip()
 
 
@@ -96,7 +94,7 @@ CLIP_PATTERNS = [
 ]
 
 
-def parse_video_identifier(identifier: str) -> str | None:
+def parse_video_identifier(identifier: str) -> Optional[str]:
     """Given a video ID or URL returns the video ID, or null if not matched"""
     for pattern in VIDEO_PATTERNS:
         match = re.match(pattern, identifier)
@@ -104,7 +102,7 @@ def parse_video_identifier(identifier: str) -> str | None:
             return match.group("id")
 
 
-def parse_clip_identifier(identifier: str) -> str | None:
+def parse_clip_identifier(identifier: str) -> Optional[str]:
     """Given a clip slug or URL returns the clip slug, or null if not matched"""
     for pattern in CLIP_PATTERNS:
         match = re.match(pattern, identifier)

video_before.json

@@ -0,0 +1,203 @@
+{
+  "id": "2115833882",
+  "title": "Games I Feel Like Speedrun Marathon !newyt !Slender !Merch",
+  "description": null,
+  "publishedAt": "2024-04-10T05:01:12Z",
+  "broadcastType": "ARCHIVE",
+  "lengthSeconds": 30163,
+  "game": {
+    "id": "21063",
+    "name": "Saw"
+  },
+  "creator": {
+    "login": "ecdycis",
+    "displayName": "Ecdycis"
+  },
+  "playlists": [
+    {
+      "bandwidth": 6395968,
+      "resolution": [
+        1920,
+        1080
+      ],
+      "codecs": "avc1.64002A,mp4a.40.2",
+      "video": "chunked",
+      "uri": "https://d2nvs31859zcd8.cloudfront.net/3104d817048588f268fa_ecdycis_43996750059_1712725267/chunked/index-muted-GKGIUOE29B.m3u8"
+    },
+    {
+      "bandwidth": 3430341,
+      "resolution": [
+        1280,
+        720
+      ],
+      "codecs": "avc1.4D0020,mp4a.40.2",
+      "video": "720p60",
+      "uri": "https://d2nvs31859zcd8.cloudfront.net/3104d817048588f268fa_ecdycis_43996750059_1712725267/720p60/index-muted-GKGIUOE29B.m3u8"
+    },
+    {
+      "bandwidth": 1448243,
+      "resolution": [
+        852,
+        480
+      ],
+      "codecs": "avc1.4D001F,mp4a.40.2",
+      "video": "480p30",
+      "uri": "https://d2nvs31859zcd8.cloudfront.net/3104d817048588f268fa_ecdycis_43996750059_1712725267/480p30/index-muted-GKGIUOE29B.m3u8"
+    },
+    {
+      "bandwidth": 215544,
+      "resolution": null,
+      "codecs": "mp4a.40.2",
+      "video": "audio_only",
+      "uri": "https://d2nvs31859zcd8.cloudfront.net/3104d817048588f268fa_ecdycis_43996750059_1712725267/audio_only/index-muted-GKGIUOE29B.m3u8"
+    },
+    {
+      "bandwidth": 709051,
+      "resolution": [
+        640,
+        360
+      ],
+      "codecs": "avc1.4D001E,mp4a.40.2",
+      "video": "360p30",
+      "uri": "https://d2nvs31859zcd8.cloudfront.net/3104d817048588f268fa_ecdycis_43996750059_1712725267/360p30/index-muted-GKGIUOE29B.m3u8"
+    },
+    {
+      "bandwidth": 288844,
+      "resolution": [
+        284,
+        160
+      ],
+      "codecs": "avc1.4D000C,mp4a.40.2",
+      "video": "160p30",
+      "uri": "https://d2nvs31859zcd8.cloudfront.net/3104d817048588f268fa_ecdycis_43996750059_1712725267/160p30/index-muted-GKGIUOE29B.m3u8"
+    }
+  ],
+  "chapters": [
+    {
+      "id": "6049e803f47a0b9cf64ce95adcf3d96d",
+      "durationMilliseconds": 4891000,
+      "positionMilliseconds": 0,
+      "type": "GAME_CHANGE",
+      "description": "Saw",
+      "subDescription": "",
+      "thumbnailURL": "",
+      "video": {
+        "id": "2115833882",
+        "lengthSeconds": 30163,
+        "__typename": "Video"
+      },
+      "__typename": "VideoMoment",
+      "game": {
+        "id": "21063",
+        "displayName": "Saw",
+        "boxArtURL": "https://static-cdn.jtvnw.net/ttv-boxart/21063_IGDB-40x53.jpg",
+        "__typename": "Game"
+      }
+    },
+    {
+      "id": "c3be4ce5a7bae802d7a6df02baf62a85",
+      "durationMilliseconds": 6235000,
+      "positionMilliseconds": 4891000,
+      "type": "GAME_CHANGE",
+      "description": "Resident Evil 7: Biohazard",
+      "subDescription": "",
+      "thumbnailURL": "",
+      "video": {
+        "id": "2115833882",
+        "lengthSeconds": 30163,
+        "__typename": "Video"
+      },
+      "__typename": "VideoMoment",
+      "game": {
+        "id": "492934",
+        "displayName": "Resident Evil 7: Biohazard",
+        "boxArtURL": "https://static-cdn.jtvnw.net/ttv-boxart/492934_IGDB-40x53.jpg",
+        "__typename": "Game"
+      }
+    },
+    {
+      "id": "bd584f17bc1f91fc11ed14dcec5e4742",
+      "durationMilliseconds": 3401000,
+      "positionMilliseconds": 11126000,
+      "type": "GAME_CHANGE",
+      "description": "Silent Hill: Homecoming",
+      "subDescription": "",
+      "thumbnailURL": "",
+      "video": {
+        "id": "2115833882",
+        "lengthSeconds": 30163,
+        "__typename": "Video"
+      },
+      "__typename": "VideoMoment",
+      "game": {
+        "id": "18864",
+        "displayName": "Silent Hill: Homecoming",
+        "boxArtURL": "https://static-cdn.jtvnw.net/ttv-boxart/18864_IGDB-40x53.jpg",
+        "__typename": "Game"
+      }
+    },
+    {
+      "id": "9f4be8bc7b5bf398213bc602a4b39c4d",
+      "durationMilliseconds": 3490000,
+      "positionMilliseconds": 14527000,
+      "type": "GAME_CHANGE",
+      "description": "Silent Hill 2",
+      "subDescription": "",
+      "thumbnailURL": "",
+      "video": {
+        "id": "2115833882",
+        "lengthSeconds": 30163,
+        "__typename": "Video"
+      },
+      "__typename": "VideoMoment",
+      "game": {
+        "id": "9891",
+        "displayName": "Silent Hill 2",
+        "boxArtURL": "https://static-cdn.jtvnw.net/ttv-boxart/9891_IGDB-40x53.jpg",
+        "__typename": "Game"
+      }
+    },
+    {
+      "id": "7a42d537681decc10660c33f9071a37f",
+      "durationMilliseconds": 7241000,
+      "positionMilliseconds": 18017000,
+      "type": "GAME_CHANGE",
+      "description": "The Darkness",
+      "subDescription": "",
+      "thumbnailURL": "",
+      "video": {
+        "id": "2115833882",
+        "lengthSeconds": 30163,
+        "__typename": "Video"
+      },
+      "__typename": "VideoMoment",
+      "game": {
+        "id": "8448",
+        "displayName": "The Darkness",
+        "boxArtURL": "https://static-cdn.jtvnw.net/ttv-boxart/8448_IGDB-40x53.jpg",
+        "__typename": "Game"
+      }
+    },
+    {
+      "id": "64418186f436d80b1359d2e6686222ef",
+      "durationMilliseconds": 4905000,
+      "positionMilliseconds": 25258000,
+      "type": "GAME_CHANGE",
+      "description": "Silent Hill 4: The Room",
+      "subDescription": "",
+      "thumbnailURL": "",
+      "video": {
+        "id": "2115833882",
+        "lengthSeconds": 30163,
+        "__typename": "Video"
+      },
+      "__typename": "VideoMoment",
+      "game": {
+        "id": "5804",
+        "displayName": "Silent Hill 4: The Room",
+        "boxArtURL": "https://static-cdn.jtvnw.net/ttv-boxart/5804_IGDB-40x53.jpg",
+        "__typename": "Game"
+      }
+    }
+  ]
+}