Bump version, update changelog and readme

issue #24

CHANGELOG.md

@@ -0,0 +1,83 @@
+Twitch Downloader change log
+============================
+
+1.10.0 (2020-08-07)
+-------------------
+
+* Add `--quality` option to `download` command, allows specifying the video
+  quality to download. In this case, twitch-dl will require no user input. (#22)
+* Fix download of clips which contain numbers in their slug (#24)
+* Fix URL to video displayed by `videos` command (it was missing /videos/)
+
+1.9.0 (2020-06-10)
+------------------
+
+* **Breaking**: wrongly named `--max_workers` option changed to `--max-workers`.
+  The shorthand option `-w` remains the same.
+* Fix bug where `videos` command would crash if there was no game info (#21)
+* Allow unicode characters in filenames, no longer strips e.g. cyrillic script
+
+1.8.0 (2020-05-17)
+------------------
+
+* Fix videos command (#18)
+* **Breaking**: `videos` command no longer takes the `--offset` parameter due to
+  API changes
+* Add paging to `videos` command to replace offset
+* Add `--game` option to `videos` command to filter by game
+
+1.7.0 (2020-04-25)
+------------------
+
+* Support for specifying broadcast type when listing videos (#13)
+
+1.6.0 (2020-04-11)
+------------------
+
+* Support for downloading clips (#15)
+
+1.5.1 (2020-04-11)
+------------------
+
+* Fix VOD naming issue (#12)
+* Nice console output while downloading
+
+1.5.0 (2020-04-10)
+------------------
+
+* Fix video downloads after Twitch deprecated access token access
+* Don't print errors when retrying download, only if all fails
+
+1.4.0 (2019-08-23)
+------------------
+
+* Fix usage of deprecated v3 API
+* Use m3u8 lib for parsing playlists
+* Add `--keep` option not preserve downloaded VODs
+
+1.3.1 (2019-08-13)
+------------------
+
+* No changes, bumped to fix issue with pypi
+
+1.3.0 (2019-08-13)
+------------------
+
+* Add `--sort` and `--offset` options to `videos` command, allows paging (#7)
+* Show video URL in `videos` command output
+
+1.2.0 (2019-07-05)
+------------------
+
+* Add `--format` option to `download` command for specifying the output format (#6)
+* Add `--version` option for printing program version
+
+1.1.0 (2019-06-06)
+------------------
+
+* Allow limiting download by start and end time
+
+1.0.0 (2019-04-30)
+------------------
+
+* Initial release

Makefile

@@ -1,22 +1,15 @@
 default : clean dist
 
 dist :
-	@echo "\nMaking source"
-	@echo "-------------"
-	@python setup.py sdist
-
-	@echo "\nMaking wheel"
-	@echo "-------------"
-	@python setup.py bdist_wheel --universal
-
-	@echo "\nDone."
+	python setup.py sdist --formats=gztar,zip
+	python setup.py bdist_wheel --python-tag=py3
 
 clean :
 	find . -name "*pyc" | xargs rm -rf $1
 	rm -rf build dist MANIFEST htmlcov deb_dist twitch-dl*.tar.gz twitch-dl.1.man
 
 publish :
-	twine upload dist/*
+	twine upload dist/*.tar.gz dist/*.whl
 
 coverage:
 	py.test --cov=toot --cov-report html tests/

README.md

@@ -13,6 +13,12 @@ Resources
 * Issues: https://github.com/ihabunek/twitch-dl/issues
 * Python package: https://pypi.org/project/twitch-dl/
 
+Requirements
+------------
+
+* Python 3.5+
+* [ffmpeg](https://ffmpeg.org/) must be installed and in the path
+
 Usage
 -----
 
@@ -43,6 +49,12 @@ Bananasaurus_Rex playing Dead Space
 Published 2018-01-21 @ 05:47:03  Length: 5h 7min
 ```
 
+Use the `--game` option to specify one or more games to show:
+
+```
+twitch-dl videos --game "doom eternal" --game "cave story" bananasaurus_rex
+```
+
 Download a stream by ID or URL:
 
 ```
@@ -50,6 +62,27 @@ twitch-dl download 221837124
 twitch-dl download https://www.twitch.tv/videos/221837124
 ```
 
+Specify video quality to download:
+
+```
+twitch-dl download -q 720p 221837124
+```
+
+Download a clip by slug or URL:
+
+```
+twitch-dl download VenomousTameWormHumbleLife
+twitch-dl download https://www.twitch.tv/bananasaurus_rex/clip/VenomousTameWormHumbleLife
+```
+
+Specify clip quality to download:
+
+```
+twitch-dl download -q 720 VenomousTameWormHumbleLife
+```
+
+Note that twitch names for clip qualities have no trailing "p".
+
 Man page
 --------
 

setup.cfg

@@ -1,2 +0,0 @@
-[bdist_wheel]
-universal=1

setup.py

@@ -2,27 +2,35 @@
 
 from setuptools import setup
 
+long_description = """
+Quickly download videos from twitch.tv.
+
+Works simliarly to youtube-dl but downloads multiple VODs in parallel which
+makes it faster.
+"""
 
 setup(
     name='twitch-dl',
-    version='0.1.0',
+    version='1.10.0',
     description='Twitch downloader',
-    long_description="A simple script for downloading videos from Twitch",
+    long_description=long_description.strip(),
     author='Ivan Habunek',
     author_email='ivan@habunek.com',
     url='https://github.com/ihabunek/twitch-dl/',
     keywords='twitch vod video download',
     license='GPLv3',
     classifiers=[
-        'Development Status :: 4 - Beta',
+        'Development Status :: 5 - Production/Stable',
         'License :: OSI Approved :: GNU General Public License v3 (GPLv3)',
         'Programming Language :: Python :: 3',
         'Programming Language :: Python :: 3.5',
         'Programming Language :: Python :: 3.6',
+        'Programming Language :: Python :: 3.7',
     ],
     packages=['twitchdl'],
     python_requires='>=3.5',
     install_requires=[
+        "m3u8>=0.3.12,<0.4",
         "requests>=2.13,<3.0",
     ],
     entry_points={

stdeb.cfg

@@ -1,3 +1,3 @@
 [DEFAULT]
-X-Python3-Version: >= 3.3
+X-Python3-Version: >= 3.5
 Copyright-File: LICENSE

twitch-dl.1.scd

@@ -24,18 +24,45 @@ List recent videos from bananasaurus\_rex's channel:
 twitch-dl videos bananasaurus_rex
 ```
 
-Download by URL:
+Download video by URL:
 
 ```
 twitch-dl download https://www.twitch.tv/videos/377220226
 ```
 
-Download by ID:
+Download video by ID:
 
 ```
 twitch-dl download 377220226
 ```
 
+Specify output format:
+
+```
+twitch-dl download --format=avi 377220226
+```
+
+Partial download by setting start and end time (hh:mm or hh:mm:ss):
+
+```
+twitch-dl download --start=00:10 --end=02:15 377220226
+```
+
+Download clip by URL:
+
+```
+twitch-dl download https://www.twitch.tv/bananasaurus_rex/clip/VenomousTameWormHumbleLife
+```
+
+Download clip by slug:
+
+```
+twitch-dl download VenomousTameWormHumbleLife
+```
+
+Note that clips are a single download, and don't benefit from the paralelism
+used when downloading videos.
+
 # SEE ALSO
 
 youtube-dl(1)

twitchdl/__init__.py

@@ -1,3 +1,3 @@
-__version__ = "0.1.0"
+__version__ = "1.9.0"
 
-CLIENT_ID = "miwy5zk23vh2he94san0bzj5ks1r0p"
+CLIENT_ID = "kimne78kx3ncx6brgo4mv6wki5h1ko"

twitchdl/commands.py

@@ -1,134 +1,113 @@
+import m3u8
 import os
 import pathlib
 import re
+import requests
+import shutil
 import subprocess
 import tempfile
 
-from datetime import datetime
-from concurrent.futures import ThreadPoolExecutor, as_completed
-from functools import partial
+from pathlib import Path
+from urllib.parse import urlparse
 
-from twitchdl import twitch
-from twitchdl.download import download_file
+from twitchdl import twitch, utils
+from twitchdl.download import download_file, download_files
 from twitchdl.exceptions import ConsoleError
-from twitchdl.output import print_out
-from twitchdl.utils import slugify
+from twitchdl.output import print_out, print_video
 
 
-def read_int(msg, min, max, default):
-    msg = msg + " [default {}]: ".format(default)
+def _continue():
+    print_out(
+        "\nThere are more videos. "
+        "Press <green><b>Enter</green> to continue, "
+        "<yellow><b>Ctrl+C</yellow> to break."
+    )
 
-    while True:
-        try:
-            val = input(msg)
-            if not val:
-                return default
-            if min <= int(val) <= max:
-                return int(val)
-        except ValueError:
-            pass
+    try:
+        input()
+    except KeyboardInterrupt:
+        return False
+
+    return True
 
 
-def format_size(bytes_):
-    if bytes_ < 1024:
-        return str(bytes_)
+def _get_game_ids(names):
+    if not names:
+        return []
 
-    kilo = bytes_ / 1024
-    if kilo < 1024:
-        return "{:.1f}K".format(kilo)
+    game_ids = []
+    for name in names:
+        print_out("<dim>Looking up game '{}'...</dim>".format(name))
+        game_id = twitch.get_game_id(name)
+        if not game_id:
+            raise ConsoleError("Game '{}' not found".format(name))
+        game_ids.append(int(game_id))
 
-    mega = kilo / 1024
-    if mega < 1024:
-        return "{:.1f}M".format(mega)
-
-    return "{:.1f}G".format(mega / 1024)
+    return game_ids
 
 
-def format_duration(total_seconds):
-    total_seconds = int(total_seconds)
-    hours = total_seconds // 3600
-    remainder = total_seconds % 3600
-    minutes = remainder // 60
-    seconds = total_seconds % 60
+def videos(args):
+    game_ids = _get_game_ids(args.game)
 
-    if hours:
-        return "{} h {} min".format(hours, minutes)
+    print_out("<dim>Loading videos...</dim>")
+    generator = twitch.channel_videos_generator(
+        args.channel_name, args.limit, args.sort, args.type, game_ids=game_ids)
 
-    if minutes:
-        return "{} min {} sec".format(minutes, seconds)
+    first = 1
 
-    return "{} sec".format(seconds)
+    for videos, has_more in generator:
+        count = len(videos["edges"]) if "edges" in videos else 0
+        total = videos["totalCount"]
+        last = first + count - 1
+
+        print_out("-" * 80)
+        print_out("<yellow>Showing videos {}-{} of {}</yellow>".format(first, last, total))
+
+        for video in videos["edges"]:
+            print_video(video["node"])
+
+        if not has_more or not _continue():
+            break
+
+        first += count
+    else:
+        print_out("<yellow>No videos found</yellow>")
 
 
-def _print_video(video):
-    published_at = video['published_at'].replace('T', ' @ ').replace('Z', '')
-    length = format_duration(video['length'])
-    name = video['channel']['display_name']
+def _parse_playlists(playlists_m3u8):
+    playlists = m3u8.loads(playlists_m3u8)
 
-    print_out("\n<bold>{}</bold>".format(video['_id'][1:]))
-    print_out("<green>{}</green>".format(video["title"]))
-    print_out("<cyan>{}</cyan> playing <cyan>{}</cyan>".format(name, video['game']))
-    print_out("Published <cyan>{}</cyan>  Length: <cyan>{}</cyan> ".format(published_at, length))
+    for p in playlists.playlists:
+        name = p.media[0].name if p.media else ""
+        resolution = "x".join(str(r) for r in p.stream_info.resolution)
+        yield name, resolution, p.uri
 
 
-def videos(channel_name, **kwargs):
-    videos = twitch.get_channel_videos(channel_name)
+def _get_playlist_by_name(playlists, quality):
+    for name, _, uri in playlists:
+        if name == quality:
+            return uri
 
-    print("Found {} videos".format(videos["_total"]))
-
-    for video in videos['videos']:
-        _print_video(video)
+    available = ", ".join([name for (name, _, _) in playlists])
+    msg = "Quality '{}' not found. Available qualities are: {}".format(quality, available)
+    raise ConsoleError(msg)
 
 
-def _select_quality(playlists):
+def _select_playlist_interactive(playlists):
     print_out("\nAvailable qualities:")
-    for no, v in playlists.items():
-        print_out("{}) {}".format(no, v[0]))
+    for n, (name, resolution, uri) in enumerate(playlists):
+        print_out("{}) {} [{}]".format(n + 1, name, resolution))
 
-    keys = list(playlists.keys())
-    no = read_int("Choose quality", min=min(keys), max=max(keys), default=keys[0])
-
-    return playlists[no]
+    no = utils.read_int("Choose quality", min=1, max=len(playlists) + 1, default=1)
+    _, _, uri = playlists[no - 1]
+    return uri
 
 
-def _print_progress(futures):
-    counter = 1
-    total = len(futures)
-    total_size = 0
-    start_time = datetime.now()
-
-    for future in as_completed(futures):
-        size = future.result()
-        percentage = 100 * counter // total
-        total_size += size
-        duration = (datetime.now() - start_time).seconds
-        speed = total_size // duration if duration else 0
-        remaining = (total - counter) * duration / counter
-
-        msg = "Downloaded VOD {}/{} ({}%) total <cyan>{}B</cyan> at <cyan>{}B/s</cyan> remaining <cyan>{}</cyan>".format(
-            counter, total, percentage, format_size(total_size), format_size(speed), format_duration(remaining))
-
-        print_out("\r" + msg.ljust(80), end='')
-        counter += 1
-
-
-def _download_files(base_url, directory, filenames, max_workers):
-    urls = [base_url.format(f) for f in filenames]
-    paths = ["/".join([directory, f]) for f in filenames]
-    partials = (partial(download_file, url, path) for url, path in zip(urls, paths))
-
-    with ThreadPoolExecutor(max_workers=max_workers) as executor:
-        futures = [executor.submit(fn) for fn in partials]
-        _print_progress(futures)
-
-    return paths
-
-
-def _join_vods(directory, paths, target):
+def _join_vods(directory, file_paths, target):
     input_path = "{}/files.txt".format(directory)
 
     with open(input_path, 'w') as f:
-        for path in paths:
+        for path in file_paths:
             f.write('file {}\n'.format(os.path.basename(path)))
 
     result = subprocess.run([
@@ -152,57 +131,164 @@ def _video_target_filename(video, format):
         date,
         video['_id'][1:],
         video['channel']['name'],
-        slugify(video['title']),
+        utils.slugify(video['title']),
     ])
 
     return name + "." + format
 
 
-def parse_video_id(video_id):
-    """This can be either a integer ID or an URL to the video on twitch."""
-    if re.search(r"^\d+$", video_id):
-        return int(video_id)
+def _get_files(playlist, start, end):
+    """Extract files for download from playlist."""
+    vod_start = 0
+    for segment in playlist.segments:
+        vod_end = vod_start + segment.duration
 
-    match = re.search(r"^https://www.twitch.tv/videos/(\d+)(\?.+)?$", video_id)
-    if match:
-        return int(match.group(1))
+        # `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
 
-    raise ConsoleError("Invalid video ID given, expected integer ID or Twitch URL")
+        if start_condition and end_condition:
+            yield segment.uri
+
+        vod_start = vod_end
 
 
-def download(video_id, max_workers, format='mkv', **kwargs):
-    video_id = parse_video_id(video_id)
+def _crete_temp_dir(base_uri):
+    """Create a temp dir to store downloads if it doesn't exist."""
+    path = urlparse(base_uri).path
+    directory = '{}/twitch-dl{}'.format(tempfile.gettempdir(), path)
+    pathlib.Path(directory).mkdir(parents=True, exist_ok=True)
+    return directory
 
-    print_out("Looking up video...")
+
+VIDEO_PATTERNS = [
+    r"^(?P<id>\d+)?$",
+    r"^https://www.twitch.tv/videos/(?P<id>\d+)(\?.+)?$",
+]
+
+CLIP_PATTERNS = [
+    r"^(?P<slug>[A-Za-z0-9]+)$",
+    r"^https://www.twitch.tv/\w+/clip/(?P<slug>[A-Za-z0-9]+)(\?.+)?$",
+    r"^https://clips.twitch.tv/(?P<slug>[A-Za-z0-9]+)(\?.+)?$",
+]
+
+
+def download(args):
+    for pattern in CLIP_PATTERNS:
+        match = re.match(pattern, args.video)
+        if match:
+            clip_slug = match.group('slug')
+            return _download_clip(clip_slug, args)
+
+    for pattern in VIDEO_PATTERNS:
+        match = re.match(pattern, args.video)
+        if match:
+            video_id = match.group('id')
+            return _download_video(video_id, args)
+
+    raise ConsoleError("Invalid video: {}".format(args.video))
+
+
+def _get_clip_url(clip, args):
+    qualities = clip["videoQualities"]
+
+    # Quality given as an argument
+    if args.quality:
+        selected_quality = args.quality.rstrip("p")  # allow 720p as well as 720
+        for q in qualities:
+            if q["quality"] == selected_quality:
+                return q["sourceURL"]
+
+        available = ", ".join([str(q["quality"]) for q in qualities])
+        msg = "Quality '{}' not found. Available qualities are: {}".format(args.quality, available)
+        raise ConsoleError(msg)
+
+    # Ask user to select quality
+    print_out("\nAvailable qualities:")
+    for n, q in enumerate(qualities):
+        print_out("{}) {} [{} fps]".format(n + 1, q["quality"], q["frameRate"]))
+    print_out()
+
+    no = utils.read_int("Choose quality", min=1, max=len(qualities), default=1)
+    selected_quality = qualities[no - 1]
+    return selected_quality["sourceURL"]
+
+
+def _download_clip(slug, args):
+    print_out("<dim>Looking up clip...</dim>")
+    clip = twitch.get_clip(slug)
+
+    print_out("Found: <green>{}</green> by <yellow>{}</yellow>, playing <blue>{}</blue> ({})".format(
+        clip["title"],
+        clip["broadcaster"]["displayName"],
+        clip["game"]["name"],
+        utils.format_duration(clip["durationSeconds"])
+    ))
+
+    url = _get_clip_url(clip, args)
+    print_out("<dim>Selected URL: {}</dim>".format(url))
+
+    url_path = urlparse(url).path
+    extension = Path(url_path).suffix
+    filename = "{}_{}{}".format(
+        clip["broadcaster"]["login"],
+        utils.slugify(clip["title"]),
+        extension
+    )
+
+    print_out("Downloading clip...")
+    download_file(url, filename)
+
+    print_out("Downloaded: {}".format(filename))
+
+
+def _download_video(video_id, args):
+    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>")
     video = twitch.get_video(video_id)
 
     print_out("Found: <blue>{}</blue> by <yellow>{}</yellow>".format(
         video['title'], video['channel']['display_name']))
 
-    print_out("Fetching access token...")
+    print_out("<dim>Fetching access token...</dim>")
     access_token = twitch.get_access_token(video_id)
 
-    print_out("Fetching playlists...")
-    playlists = twitch.get_playlists(video_id, access_token)
-    quality, playlist_url = _select_quality(playlists)
+    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_out("\nFetching playlist...")
-    base_url, filenames = twitch.get_playlist_urls(playlist_url)
+    print_out("<dim>Fetching playlist...</dim>")
+    response = requests.get(playlist_uri)
+    response.raise_for_status()
+    playlist = m3u8.loads(response.text)
 
-    # Create a temp dir to store downloads if it doesn't exist
-    directory = '{}/twitch-dl/{}/{}'.format(tempfile.gettempdir(), video_id, quality)
-    pathlib.Path(directory).mkdir(parents=True, exist_ok=True)
-    print_out("Download dir: {}".format(directory))
+    base_uri = re.sub("/[^/]+$", "/", playlist_uri)
+    target_dir = _crete_temp_dir(base_uri)
+    filenames = list(_get_files(playlist, args.start, args.end))
 
-    print_out("Downloading VODs with {} workers...".format(max_workers))
-    paths = _download_files(base_url, directory, filenames, max_workers)
+    # Save playlists for debugging purposes
+    with open(target_dir + "playlists.m3u8", "w") as f:
+        f.write(playlists_m3u8)
+    with open(target_dir + "playlist.m3u8", "w") as f:
+        f.write(response.text)
+
+    print_out("\nDownloading {} VODs using {} workers to {}".format(
+        len(filenames), args.max_workers, target_dir))
+    file_paths = download_files(base_uri, target_dir, filenames, args.max_workers)
 
     print_out("\n\nJoining files...")
-    target = _video_target_filename(video, format)
-    _join_vods(directory, paths, target)
+    target = _video_target_filename(video, args.format)
+    _join_vods(target_dir, file_paths, target)
 
-    print_out("\nDeleting vods...")
-    for path in paths:
-        os.unlink(path)
+    if args.keep:
+        print_out("\nTemporary files not deleted: {}".format(target_dir))
+    else:
+        print_out("\nDeleting temporary files...")
+        shutil.rmtree(target_dir)
 
-    print_out("\nDownloaded: {}".format(target))
+    print_out("Downloaded: {}".format(target))

twitchdl/console.py

@@ -1,17 +1,51 @@
 # -*- coding: utf-8 -*-
 
-from argparse import ArgumentParser
+import sys
+
+from argparse import ArgumentParser, ArgumentTypeError
 from collections import namedtuple
 
 from twitchdl.exceptions import ConsoleError
 from twitchdl.output import print_err
-from . import commands
+from twitchdl.twitch import GQLError
+from . import commands, __version__
 
 
 Command = namedtuple("Command", ["name", "description", "arguments"])
 
 CLIENT_WEBSITE = 'https://github.com/ihabunek/twitch-dl'
 
+
+def time(value):
+    """Parse a time string (hh:mm or hh:mm:ss) to number of seconds."""
+    parts = [int(p) for p in value.split(":")]
+
+    if not 2 <= len(parts) <= 3:
+        raise ArgumentTypeError()
+
+    hours = parts[0]
+    minutes = parts[1]
+    seconds = parts[2] if len(parts) > 2 else 0
+
+    if hours < 0 or not (0 <= minutes <= 59) or not (0 <= seconds <= 59):
+        raise ArgumentTypeError()
+
+    return hours * 3600 + minutes * 60 + seconds
+
+
+def limit(value):
+    """Validates the number of videos to fetch."""
+    try:
+        value = int(value)
+    except ValueError:
+        raise ArgumentTypeError("must be an integer")
+
+    if not 1 <= int(value) <= 100:
+        raise ArgumentTypeError("must be between 1 and 100")
+
+    return value
+
+
 COMMANDS = [
     Command(
         name="videos",
@@ -21,21 +55,69 @@ COMMANDS = [
                 "help": "channel name",
                 "type": str,
             }),
+            (["-g", "--game"], {
+                "help": "Show videos of given game (can be given multiple times)",
+                "action": "append",
+                "type": str,
+            }),
+            (["-l", "--limit"], {
+                "help": "Number of videos to fetch (default 10, max 100)",
+                "type": limit,
+                "default": 10,
+            }),
+            (["-s", "--sort"], {
+                "help": "Sorting order of videos. (default: time)",
+                "type": str,
+                "choices": ["views", "time"],
+                "default": "time",
+            }),
+            (["-t", "--type"], {
+                "help": "Broadcast type. (default: archive)",
+                "type": str,
+                "choices": ["archive", "highlight", "upload"],
+                "default": "archive",
+            }),
         ],
     ),
     Command(
         name="download",
         description="Download a video",
         arguments=[
-            (["video_id"], {
-                "help": "video ID",
+            (["video"], {
+                "help": "video ID, clip slug, or URL",
                 "type": str,
             }),
-            (["-w", "--max_workers"], {
-                "help": "maximal number of threads for downloading vods concurrently (default 5)",
+            (["-w", "--max-workers"], {
+                "help": "maximal number of threads for downloading vods "
+                        "concurrently (default 20)",
                 "type": int,
                 "default": 20,
             }),
+            (["-s", "--start"], {
+                "help": "Download video from this time (hh:mm or hh:mm:ss)",
+                "type": time,
+                "default": None,
+            }),
+            (["-e", "--end"], {
+                "help": "Download video up to this time (hh:mm or hh:mm:ss)",
+                "type": time,
+                "default": None,
+            }),
+            (["-f", "--format"], {
+                "help": "Video format to convert into, passed to ffmpeg as the "
+                        "target file extension (default: mkv)",
+                "type": str,
+                "default": "mkv",
+            }),
+            (["-k", "--keep"], {
+                "help": "Don't delete downloaded VODs and playlists after merging.",
+                "action": "store_true",
+                "default": False,
+            }),
+            (["-q", "--quality"], {
+                "help": "Video quality.",
+                "type": str,
+            }),
         ],
     ),
 ]
@@ -58,6 +140,8 @@ def get_parser():
     description = "A script for downloading videos from Twitch"
 
     parser = ArgumentParser(prog='twitch-dl', description=description, epilog=CLIENT_WEBSITE)
+    parser.add_argument("--version", help="show version number", action='store_true')
+
     subparsers = parser.add_subparsers(title="commands")
 
     for command in COMMANDS:
@@ -76,11 +160,21 @@ def main():
     parser = get_parser()
     args = parser.parse_args()
 
+    if args.version:
+        print("twitch-dl v{}".format(__version__))
+        return
+
     if "func" not in args:
         parser.print_help()
         return
 
     try:
-        args.func(**args.__dict__)
+        args.func(args)
     except ConsoleError as e:
         print_err(e)
+        sys.exit(1)
+    except GQLError as e:
+        print_err(e)
+        for err in e.errors:
+            print_err("*", err["message"])
+        sys.exit(1)

twitchdl/download.py

@@ -1,11 +1,17 @@
 import os
 import requests
 
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from datetime import datetime
+from functools import partial
 from requests.exceptions import RequestException
+from twitchdl.output import print_out
+from twitchdl.utils import format_size, format_duration
 
 
 CHUNK_SIZE = 1024
 CONNECT_TIMEOUT = 5
+RETRY_COUNT = 5
 
 
 class DownloadFailed(Exception):
@@ -25,14 +31,57 @@ def _download(url, path):
     return size
 
 
-def download_file(url, path, retries=3):
+def download_file(url, path, retries=RETRY_COUNT):
     if os.path.exists(path):
-        return 0
+        return os.path.getsize(path)
 
     for _ in range(retries):
         try:
             return _download(url, path)
-        except RequestException as e:
-            print("Download failed: {}".format(e))
+        except RequestException:
+            pass
 
     raise DownloadFailed(":(")
+
+
+def _print_progress(futures):
+    downloaded_count = 0
+    downloaded_size = 0
+    max_msg_size = 0
+    start_time = datetime.now()
+    total_count = len(futures)
+
+    for future in as_completed(futures):
+        size = future.result()
+        downloaded_count += 1
+        downloaded_size += size
+
+        percentage = 100 * downloaded_count // total_count
+        est_total_size = int(total_count * downloaded_size / downloaded_count)
+        duration = (datetime.now() - start_time).seconds
+        speed = downloaded_size // duration if duration else 0
+        remaining = (total_count - downloaded_count) * duration / downloaded_count
+
+        msg = " ".join([
+            "Downloaded VOD {}/{}".format(downloaded_count, total_count),
+            "({}%)".format(percentage),
+            "<cyan>{}</cyan>".format(format_size(downloaded_size)),
+            "of <cyan>~{}</cyan>".format(format_size(est_total_size)),
+            "at <cyan>{}/s</cyan>".format(format_size(speed)) if speed > 0 else "",
+            "remaining <cyan>~{}</cyan>".format(format_duration(remaining)) if speed > 0 else "",
+        ])
+
+        max_msg_size = max(len(msg), max_msg_size)
+        print_out("\r" + msg.ljust(max_msg_size), end="")
+
+
+def download_files(base_url, directory, filenames, max_workers):
+    urls = [base_url + f for f in filenames]
+    paths = ["{}{:05d}.vod".format(directory, k) for k, _ in enumerate(filenames)]
+    partials = (partial(download_file, url, path) for url, path in zip(urls, paths))
+
+    with ThreadPoolExecutor(max_workers=max_workers) as executor:
+        futures = [executor.submit(fn) for fn in partials]
+        _print_progress(futures)
+
+    return paths

twitchdl/output.py

@@ -3,14 +3,20 @@
 import sys
 import re
 
+from twitchdl import utils
+
+
 START_CODES = {
-    'bold': '\033[1m',
-    'red': '\033[31m',
-    'green': '\033[32m',
-    'yellow': '\033[33m',
-    'blue': '\033[34m',
-    'magenta': '\033[35m',
-    'cyan': '\033[36m',
+    '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'
@@ -49,3 +55,22 @@ def print_err(*args, **kwargs):
     args = ["<red>{}</red>".format(a) 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_video(video):
+    published_at = video["publishedAt"].replace("T", " @ ").replace("Z", "")
+    length = utils.format_duration(video["lengthSeconds"])
+    channel = video["creator"]["channel"]["displayName"]
+    playing = (
+        " playing <blue>{}</blue>".format(video["game"]["name"])
+        if video["game"] else ""
+    )
+
+    # Can't find URL in video object, strange
+    url = "https://twitch.tv/videos/{}".format(video["id"])
+
+    print_out("\n<b>{}</b>".format(video["id"]))
+    print_out("<green>{}</green>".format(video["title"]))
+    print_out("<blue>{}</blue> {}".format(channel, playing))
+    print_out("Published <blue>{}</blue>  Length: <blue>{}</blue> ".format(published_at, length))
+    print_out("<i>{}</i>".format(url))

twitchdl/parse.py

@@ -1,28 +0,0 @@
-import re
-
-from collections import OrderedDict
-
-
-def parse_playlists(data):
-    media_pattern = re.compile(r'^#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="(?P<group>\w+)",NAME="(?P<name>\w+)"')
-
-    playlists = OrderedDict()
-    n = 1
-    name = None
-    for line in data.split():
-        match = re.match(media_pattern, line)
-        if match:
-            name = match.group('name')
-        elif line.startswith('http'):
-            playlists[n] = (name, line)
-            n += 1
-
-    return playlists
-
-
-def parse_playlist(url, data):
-    base_url = re.sub("/[^/]+$", "/{}", url)
-
-    filenames = [line for line in data.split() if re.match(r"\d+\.ts", line)]
-
-    return base_url, filenames

twitchdl/twitch.py

@@ -1,46 +1,180 @@
+"""
+Twitch API access.
+"""
+
 import requests
 
 from twitchdl import CLIENT_ID
-from twitchdl.parse import parse_playlists, parse_playlist
+from twitchdl.exceptions import ConsoleError
 
 
-def authenticated_get(url, params={}):
-    headers = {'Client-ID': CLIENT_ID}
+class GQLError(Exception):
+    def __init__(self, errors):
+        super().__init__("GraphQL query failed")
+        self.errors = errors
+
+
+def authenticated_get(url, params={}, headers={}):
+    headers['Client-ID'] = CLIENT_ID
 
     response = requests.get(url, params, headers=headers)
+    if response.status_code == 400:
+        data = response.json()
+        raise ConsoleError(data["message"])
+
     response.raise_for_status()
 
     return response
 
 
+def authenticated_post(url, data=None, json=None, headers={}):
+    headers['Client-ID'] = CLIENT_ID
+
+    response = requests.post(url, data=data, json=json, headers=headers)
+    if response.status_code == 400:
+        data = response.json()
+        raise ConsoleError(data["message"])
+
+    response.raise_for_status()
+
+    return response
+
+
+def kraken_get(url, params={}, headers={}):
+    """
+    Add accept header required by kraken API v5.
+    see: https://discuss.dev.twitch.tv/t/change-in-access-to-deprecated-kraken-twitch-apis/22241
+    """
+    headers["Accept"] = "application/vnd.twitchtv.v5+json"
+    return authenticated_get(url, params, headers)
+
+
+def gql_query(query):
+    url = "https://gql.twitch.tv/gql"
+    response = authenticated_post(url, json={"query": query}).json()
+
+    if "errors" in response:
+        raise GQLError(response["errors"])
+
+    return response
+
+
 def get_video(video_id):
     """
     https://dev.twitch.tv/docs/v5/reference/videos#get-video
     """
-    url = "https://api.twitch.tv/kraken/videos/%d" % video_id
+    url = "https://api.twitch.tv/kraken/videos/{}".format(video_id)
 
-    return authenticated_get(url).json()
+    return kraken_get(url).json()
 
 
-def get_channel_videos(channel_name, limit=20):
+def get_clip(slug):
+    query = """
+    {{
+        clip(slug: "{}") {{
+            title
+            durationSeconds
+            game {{
+                name
+            }}
+            broadcaster {{
+                login
+                displayName
+            }}
+            videoQualities {{
+                frameRate
+                quality
+                sourceURL
+            }}
+        }}
+    }}
     """
-    https://dev.twitch.tv/docs/v5/reference/channels#get-channel-videos
-    """
-    url = "https://api.twitch.tv/kraken/channels/%s/videos" % channel_name
 
-    return authenticated_get(url, {
-        "broadcast_type": "archive",
+    response = gql_query(query.format(slug))
+    return response["data"]["clip"]
+
+
+def get_channel_videos(channel_id, limit, sort, type="archive", game_ids=[], after=None):
+    query = """
+    {{
+        user(login: "{channel_id}") {{
+            videos(
+                first: {limit},
+                type: {type},
+                sort: {sort},
+                after: "{after}",
+                options: {{
+                    gameIDs: {game_ids}
+                }}
+            ) {{
+                totalCount
+                pageInfo {{
+                    hasNextPage
+                }}
+                edges {{
+                    cursor
+                    node {{
+                        id
+                        title
+                        publishedAt
+                        broadcastType
+                        lengthSeconds
+                        game {{
+                            name
+                        }}
+                        creator {{
+                            channel {{
+                                displayName
+                            }}
+                        }}
+                    }}
+                }}
+            }}
+        }}
+    }}
+    """
+
+    query = query.format(**{
+        "channel_id": channel_id,
+        "game_ids": game_ids,
+        "after": after,
         "limit": limit,
-    }).json()
+        "sort": sort.upper(),
+        "type": type.upper(),
+    })
+
+    response = gql_query(query)
+    return response["data"]["user"]["videos"]
+
+
+def channel_videos_generator(channel_id, limit, sort, type, game_ids=None):
+    cursor = None
+    while True:
+        videos = get_channel_videos(
+            channel_id, limit, sort, type, game_ids=game_ids, after=cursor)
+
+        if not videos["edges"]:
+            break
+
+        has_next = videos["pageInfo"]["hasNextPage"]
+        cursor = videos["edges"][-1]["cursor"] if has_next else None
+
+        yield videos, has_next
+
+        if not cursor:
+            break
 
 
 def get_access_token(video_id):
-    url = "https://api.twitch.tv/api/vods/%d/access_token" % video_id
+    url = "https://api.twitch.tv/api/vods/{}/access_token".format(video_id)
 
     return authenticated_get(url).json()
 
 
 def get_playlists(video_id, access_token):
+    """
+    For a given video return a playlist which contains possible video qualities.
+    """
     url = "http://usher.twitch.tv/vod/{}".format(video_id)
 
     response = requests.get(url, params={
@@ -50,16 +184,19 @@ def get_playlists(video_id, access_token):
         "player": "twitchweb",
     })
     response.raise_for_status()
-
-    data = response.content.decode('utf-8')
-
-    return parse_playlists(data)
+    return response.content.decode('utf-8')
 
 
-def get_playlist_urls(url):
-    response = requests.get(url)
-    response.raise_for_status()
+def get_game_id(name):
+    query = """
+    {{
+        game(name: "{}") {{
+            id
+        }}
+    }}
+    """
 
-    data = response.content.decode('utf-8')
-
-    return parse_playlist(url, data)
+    response = gql_query(query.format(name.strip()))
+    game = response["data"]["game"]
+    if game:
+        return game["id"]

twitchdl/utils.py

@@ -2,10 +2,62 @@ import re
 import unicodedata
 
 
+def _format_size(value, digits, unit):
+    if digits > 0:
+        return "{{:.{}f}}{}".format(digits, unit).format(value)
+    else:
+        return "{{:d}}{}".format(unit).format(value)
+
+
+def format_size(bytes_, digits=1):
+    if bytes_ < 1024:
+        return _format_size(bytes_, digits, "B")
+
+    kilo = bytes_ / 1024
+    if kilo < 1024:
+        return _format_size(kilo, digits, "kB")
+
+    mega = kilo / 1024
+    if mega < 1024:
+        return _format_size(mega, digits, "MB")
+
+    return _format_size(mega / 1024, digits, "GB")
+
+
+def format_duration(total_seconds):
+    total_seconds = int(total_seconds)
+    hours = total_seconds // 3600
+    remainder = total_seconds % 3600
+    minutes = remainder // 60
+    seconds = total_seconds % 60
+
+    if hours:
+        return "{} h {} min".format(hours, minutes)
+
+    if minutes:
+        return "{} min {} sec".format(minutes, seconds)
+
+    return "{} sec".format(seconds)
+
+
+def read_int(msg, min, max, default):
+    msg = msg + " [default {}]: ".format(default)
+
+    while True:
+        try:
+            val = input(msg)
+            if not val:
+                return default
+            if min <= int(val) <= max:
+                return int(val)
+        except ValueError:
+            pass
+
+
 def slugify(value):
     re_pattern = re.compile(r'[^\w\s-]', flags=re.U)
     re_spaces = re.compile(r'[-\s]+', flags=re.U)
     value = str(value)
-    value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore').decode('ascii')
+    value = unicodedata.normalize('NFKC', value)
     value = re_pattern.sub('', value).strip().lower()
-    return re_spaces.sub('-', value)
+    return re_spaces.sub('_', value)