Bump version

Distinct VODs took from disk and freshly downloaded

CHANGELOG.md

@@ -1,6 +1,28 @@
 Twitch Downloader change log
 ============================
 
+1.17.0 (2021-12-03)
+-------------------
+
+* Fix speed calculation when resuming download (#75, thanks CroquetteTheThe)
+* Add artist and title metadata to resulting video (#80)
+
+1.16.1 (2021-07-31)
+-------------------
+
+* Fix compat with older versions of python (#71)
+
+1.16.0 (2021-06-09)
+-------------------
+
+* Fix clips download caused by Twitch changes (#64, thanks to all participants)
+
+
+1.15.0 (2021-02-15)
+-------------------
+
+* Add support for new format of clip slug (thanks @Loveangel1337)
+
 1.14.1 (2021-01-14)
 -------------------
 

setup.py

@@ -11,7 +11,7 @@ makes it faster.
 
 setup(
     name='twitch-dl',
-    version='1.14.1',
+    version='1.17.0',
     description='Twitch downloader',
     long_description=long_description.strip(),
     author='Ivan Habunek',

tests/test_api.py

@@ -0,0 +1,30 @@
+"""
+These tests depend on the channel having some videos and clips published.
+"""
+
+from twitchdl import twitch
+
+TEST_CHANNEL = "bananasaurus_rex"
+
+
+def test_get_videos():
+    videos = twitch.get_channel_videos(TEST_CHANNEL, 3, "time")
+    assert videos["pageInfo"]
+    assert len(videos["edges"]) > 0
+
+    video_id = videos["edges"][0]["node"]["id"]
+    video = twitch.get_video(video_id)
+    assert video["id"] == video_id
+
+
+def test_get_clips():
+    """
+    This test depends on the channel having some videos published.
+    """
+    clips = twitch.get_channel_clips(TEST_CHANNEL, "all_time", 3)
+    assert clips["pageInfo"]
+    assert len(clips["edges"]) > 0
+
+    clip_slug = clips["edges"][0]["node"]["slug"]
+    clip = twitch.get_clip(clip_slug)
+    assert clip["slug"] == clip_slug

tests/test_patterns.py

@@ -1,10 +1,6 @@
 import pytest
 
-from unittest.mock import patch
-from twitchdl.commands import download
-from collections import namedtuple
-
-Args = namedtuple("args", ["video"])
+from twitchdl.utils import parse_video_identifier, parse_clip_identifier
 
 
 TEST_VIDEO_PATTERNS = [
@@ -22,24 +18,18 @@ TEST_CLIP_PATTERNS = {
     ("HungryProudRadicchioDoggo", "https://clips.twitch.tv/HungryProudRadicchioDoggo"),
     ("HungryProudRadicchioDoggo", "https://www.twitch.tv/bananasaurus_rex/clip/HungryProudRadicchioDoggo?filter=clips&range=7d&sort=time"),
     ("HungryProudRadicchioDoggo", "https://twitch.tv/bananasaurus_rex/clip/HungryProudRadicchioDoggo?filter=clips&range=7d&sort=time"),
+    ("GloriousColdbloodedTortoiseRuleFive-E017utJ4DZmHVpfQ", "GloriousColdbloodedTortoiseRuleFive-E017utJ4DZmHVpfQ"),
+    ("GloriousColdbloodedTortoiseRuleFive-E017utJ4DZmHVpfQ", "https://twitch.tv/dracul1nx/clip/GloriousColdbloodedTortoiseRuleFive-E017utJ4DZmHVpfQ"),
+    ("GloriousColdbloodedTortoiseRuleFive-E017utJ4DZmHVpfQ", "https://twitch.tv/dracul1nx/clip/GloriousColdbloodedTortoiseRuleFive-E017utJ4DZmHVpfQ?filter=clips&range=7d&sort=time"),
+    ("GloriousColdbloodedTortoiseRuleFive-E017utJ4DZmHVpfQ", "https://www.twitch.tv/dracul1nx/clip/GloriousColdbloodedTortoiseRuleFive-E017utJ4DZmHVpfQ?filter=clips&range=7d&sort=time"),
 }
 
 
-@patch("twitchdl.commands._download_clip")
-@patch("twitchdl.commands._download_video")
 @pytest.mark.parametrize("expected,input", TEST_VIDEO_PATTERNS)
-def test_video_patterns(video_dl, clip_dl, expected, input):
-    args = Args(video=input)
-    download(args)
-    video_dl.assert_called_once_with(expected, args)
-    clip_dl.assert_not_called()
+def test_video_patterns(expected, input):
+    assert parse_video_identifier(input) == expected
 
 
-@patch("twitchdl.commands._download_clip")
-@patch("twitchdl.commands._download_video")
 @pytest.mark.parametrize("expected,input", TEST_CLIP_PATTERNS)
-def test_clip_patterns(video_dl, clip_dl, expected, input):
-    args = Args(video=input)
-    download(args)
-    clip_dl.assert_called_once_with(expected, args)
-    video_dl.assert_not_called()
+def test_clip_patterns(expected, input):
+    assert parse_clip_identifier(input) == expected

twitchdl/__init__.py

@@ -1,3 +1,3 @@
-__version__ = "1.14.1"
+__version__ = "1.17.0"
 
 CLIENT_ID = "kimne78kx3ncx6brgo4mv6wki5h1ko"

twitchdl/commands/clips.py

@@ -3,11 +3,22 @@ import re
 from os import path
 
 from twitchdl import twitch, utils
+from twitchdl.commands.download import get_clip_authenticated_url
 from twitchdl.download import download_file
 from twitchdl.exceptions import ConsoleError
 from twitchdl.output import print_out, print_clip, print_json
 
 
+def clips(args):
+    if args.json:
+        return _clips_json(args)
+
+    if args.download:
+        return _clips_download(args)
+
+    return _clips_list(args)
+
+
 def _continue():
     print_out(
         "\nThere are more clips. "
@@ -63,26 +74,27 @@ def _clip_target_filename(clip):
 
 
 def _clips_download(args):
+    downloaded_count = 0
     generator = twitch.channel_clips_generator(args.channel_name, args.period, 100)
+
     for clips, _ in generator:
         for clip in clips["edges"]:
             clip = clip["node"]
-            url = clip["videoQualities"][0]["sourceURL"]
+            url = get_clip_authenticated_url(clip["slug"], "source")
             target = _clip_target_filename(clip)
+
             if path.exists(target):
                 print_out("Already downloaded: <green>{}</green>".format(target))
             else:
                 print_out("Downloading: <yellow>{}</yellow>".format(target))
                 download_file(url, target)
 
+            downloaded_count += 1
+            if args.limit and downloaded_count >= args.limit:
+                return
 
-def clips(args):
-    if args.json:
-        return _clips_json(args)
-
-    if args.download:
-        return _clips_download(args)
 
+def _clips_list(args):
     print_out("<dim>Loading clips...</dim>")
     generator = twitch.channel_clips_generator(args.channel_name, args.period, args.limit)
 

twitchdl/commands/download.py

@@ -7,7 +7,7 @@ import tempfile
 
 from os import path
 from pathlib import Path
-from urllib.parse import urlparse
+from urllib.parse import urlparse, urlencode
 
 from twitchdl import twitch, utils
 from twitchdl.download import download_file, download_files
@@ -48,14 +48,17 @@ def _select_playlist_interactive(playlists):
     return uri
 
 
-def _join_vods(playlist_path, target, overwrite):
+def _join_vods(playlist_path, target, overwrite, video):
     command = [
         "ffmpeg",
         "-i", playlist_path,
         "-c", "copy",
-        target,
+        "-metadata", "artist={}".format(video["creator"]["displayName"]),
+        "-metadata", "title={}".format(video["title"]),
+        "-metadata", "encoded_by=twitch-dl",
         "-stats",
         "-loglevel", "warning",
+        target,
     ]
 
     if overwrite:
@@ -73,7 +76,7 @@ def _video_target_filename(video, format):
 
     name = "_".join([
         date,
-        video['id'][1:],
+        video['id'],
         video['creator']['login'],
         utils.slugify(video['title']),
     ])
@@ -124,7 +127,7 @@ def _crete_temp_dir(base_uri):
     path = urlparse(base_uri).path.lstrip("/")
     temp_dir = Path(tempfile.gettempdir(), "twitch-dl", path)
     temp_dir.mkdir(parents=True, exist_ok=True)
-    return temp_dir
+    return str(temp_dir)
 
 
 def download(args):
@@ -139,21 +142,21 @@ def download(args):
     raise ConsoleError("Invalid input: {}".format(args.video))
 
 
-def _get_clip_url(clip, args):
+def _get_clip_url(clip, quality):
     qualities = clip["videoQualities"]
 
     # Quality given as an argument
-    if args.quality:
-        if args.quality == "source":
+    if quality:
+        if quality == "source":
             return qualities[0]["sourceURL"]
 
-        selected_quality = args.quality.rstrip("p")  # allow 720p as well as 720
+        selected_quality = 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)
+        msg = "Quality '{}' not found. Available qualities are: {}".format(quality, available)
         raise ConsoleError(msg)
 
     # Ask user to select quality
@@ -167,6 +170,23 @@ def _get_clip_url(clip, args):
     return selected_quality["sourceURL"]
 
 
+def get_clip_authenticated_url(slug, quality):
+    print_out("<dim>Fetching access token...</dim>")
+    access_token = twitch.get_clip_access_token(slug)
+
+    if not access_token:
+        raise ConsoleError("Access token not found for slug '{}'".format(slug))
+
+    url = _get_clip_url(access_token, quality)
+
+    query = urlencode({
+        "sig": access_token["playbackAccessToken"]["signature"],
+        "token": access_token["playbackAccessToken"]["value"],
+    })
+
+    return "{}?{}".format(url, query)
+
+
 def _download_clip(slug, args):
     print_out("<dim>Looking up clip...</dim>")
     clip = twitch.get_clip(slug)
@@ -174,6 +194,12 @@ def _download_clip(slug, args):
     if not clip:
         raise ConsoleError("Clip '{}' not found".format(slug))
 
+    print_out("<dim>Fetching access token...</dim>")
+    access_token = twitch.get_clip_access_token(slug)
+
+    if not access_token:
+        raise ConsoleError("Access token not found for slug '{}'".format(slug))
+
     print_out("Found: <green>{}</green> by <yellow>{}</yellow>, playing <blue>{}</blue> ({})".format(
         clip["title"],
         clip["broadcaster"]["displayName"],
@@ -181,7 +207,7 @@ def _download_clip(slug, args):
         utils.format_duration(clip["durationSeconds"])
     ))
 
-    url = _get_clip_url(clip, args)
+    url = get_clip_authenticated_url(slug, args.quality)
     print_out("<dim>Selected URL: {}</dim>".format(url))
 
     target = _clip_target_filename(clip)
@@ -199,6 +225,9 @@ def _download_video(video_id, args):
     print_out("<dim>Looking up video...</dim>")
     video = twitch.get_video(video_id)
 
+    if not video:
+        raise ConsoleError("Video {} not found".format(video_id))
+
     print_out("Found: <blue>{}</blue> by <yellow>{}</yellow>".format(
         video['title'], video['creator']['displayName']))
 
@@ -249,7 +278,7 @@ def _download_video(video_id, args):
 
     print_out("\n\nJoining files...")
     target = _video_target_filename(video, args.format)
-    _join_vods(playlist_path, target, args.overwrite)
+    _join_vods(playlist_path, target, args.overwrite, video)
 
     if args.keep:
         print_out("\n<dim>Temporary files not deleted: {}</dim>".format(target_dir))

twitchdl/commands/info.py

@@ -40,7 +40,7 @@ def info(args):
             clip_info(clip)
         return
 
-    raise ConsoleError("Invalid input: {}".format(args.video))
+    raise ConsoleError("Invalid input: {}".format(args.identifier))
 
 
 def video_info(video, playlists):

twitchdl/console.py

@@ -239,6 +239,9 @@ def main():
     except ConsoleError as e:
         print_err(e)
         sys.exit(1)
+    except KeyboardInterrupt:
+        print_err("Operation canceled")
+        sys.exit(1)
     except GQLError as e:
         print_err(e)
         for err in e.errors:

twitchdl/download.py

@@ -34,11 +34,13 @@ def _download(url, path):
 
 def download_file(url, path, retries=RETRY_COUNT):
     if os.path.exists(path):
-        return os.path.getsize(path)
+        from_disk = True
+        return (os.path.getsize(path), from_disk)
 
+    from_disk = False
     for _ in range(retries):
         try:
-            return _download(url, path)
+            return (_download(url, path), from_disk)
         except RequestException:
             pass
 
@@ -51,17 +53,26 @@ def _print_progress(futures):
     max_msg_size = 0
     start_time = datetime.now()
     total_count = len(futures)
+    current_download_size = 0
+    current_downloaded_count = 0
 
     for future in as_completed(futures):
-        size = future.result()
+        size, from_disk = future.result()
         downloaded_count += 1
         downloaded_size += size
 
+        # If we find something on disk, we don't want to take it in account in
+        # the speed calculation
+        if not from_disk:
+            current_download_size += size
+            current_downloaded_count += 1
+
         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
+        speed = current_download_size // duration if duration else 0
+        remaining = (total_count - downloaded_count) * duration / current_downloaded_count \
+            if current_downloaded_count else 0
 
         msg = " ".join([
             "Downloaded VOD {}/{}".format(downloaded_count, total_count),
@@ -69,7 +80,7 @@ def _print_progress(futures):
             "<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 "",
+            "remaining <cyan>~{}</cyan>".format(format_duration(remaining)) if remaining > 0 else "",
         ])
 
         max_msg_size = max(len(msg), max_msg_size)

twitchdl/twitch.py

@@ -42,13 +42,14 @@ def authenticated_post(url, data=None, json=None, headers={}):
     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_post(query):
+    url = "https://gql.twitch.tv/gql"
+    response = authenticated_post(url, data=query).json()
+
+    if "errors" in response:
+        raise GQLError(response["errors"])
+
+    return response
 
 
 def gql_query(query):
@@ -61,15 +62,6 @@ def gql_query(query):
     return response
 
 
-def get_video_legacy(video_id):
-    """
-    https://dev.twitch.tv/docs/v5/reference/videos#get-video
-    """
-    url = "https://api.twitch.tv/kraken/videos/{}".format(video_id)
-
-    return kraken_get(url).json()
-
-
 VIDEO_FIELDS = """
     id
     title
@@ -86,6 +78,30 @@ VIDEO_FIELDS = """
 """
 
 
+CLIP_FIELDS = """
+    id
+    slug
+    title
+    createdAt
+    viewCount
+    durationSeconds
+    url
+    videoQualities {
+        frameRate
+        quality
+        sourceURL
+    }
+    game {
+        id
+        name
+    }
+    broadcaster {
+        displayName
+        login
+    }
+"""
+
+
 def get_video(video_id):
     query = """
     {{
@@ -105,31 +121,32 @@ def get_clip(slug):
     query = """
     {{
         clip(slug: "{}") {{
-            id
-            slug
-            title
-            createdAt
-            viewCount
-            durationSeconds
-            url
-            videoQualities {{
-                frameRate
-                quality
-                sourceURL
-            }}
-            game {{
-                id
-                name
-            }}
-            broadcaster {{
-                displayName
-                login
+            {fields}
+        }}
+    }}
+    """
+
+    response = gql_query(query.format(slug, fields=CLIP_FIELDS))
+    return response["data"]["clip"]
+
+
+def get_clip_access_token(slug):
+    query = """
+    {{
+        "operationName": "VideoAccessToken_Clip",
+        "variables": {{
+            "slug": "{slug}"
+        }},
+        "extensions": {{
+            "persistedQuery": {{
+                "version": 1,
+                "sha256Hash": "36b89d2507fce29e5ca551df756d27c1cfe079e2609642b4390aa4c35796eb11"
             }}
         }}
     }}
     """
 
-    response = gql_query(query.format(slug))
+    response = gql_post(query.format(slug=slug).strip())
     return response["data"]["clip"]
 
 
@@ -154,26 +171,7 @@ def get_channel_clips(channel_id, period, limit, after=None):
           edges {{
             cursor
             node {{
-              id
-              slug
-              title
-              createdAt
-              viewCount
-              durationSeconds
-              url
-              videoQualities {{
-                frameRate
-                quality
-                sourceURL
-              }}
-              game {{
-                id
-                name
-              }}
-              broadcaster {{
-                displayName
-                login
-              }}
+              {fields}
             }}
           }}
         }}
@@ -181,12 +179,13 @@ def get_channel_clips(channel_id, period, limit, after=None):
     }}
     """
 
-    query = query.format(**{
-        "channel_id": channel_id,
-        "after": after if after else "",
-        "limit": limit,
-        "period": period.upper(),
-    })
+    query = query.format(
+        channel_id=channel_id,
+        after=after if after else "",
+        limit=limit,
+        period=period.upper(),
+        fields=CLIP_FIELDS
+    )
 
     response = gql_query(query)
     user = response["data"]["user"]
@@ -234,18 +233,7 @@ def get_channel_videos(channel_id, limit, sort, type="archive", game_ids=[], aft
                 edges {{
                     cursor
                     node {{
-                        id
-                        title
-                        publishedAt
-                        broadcastType
-                        lengthSeconds
-                        game {{
-                            name
-                        }}
-                        creator {{
-                            login
-                            displayName
-                        }}
+                        {fields}
                     }}
                 }}
             }}
@@ -253,16 +241,21 @@ def get_channel_videos(channel_id, limit, sort, type="archive", game_ids=[], aft
     }}
     """
 
-    query = query.format(**{
-        "channel_id": channel_id,
-        "game_ids": game_ids,
-        "after": after if after else "",
-        "limit": limit,
-        "sort": sort.upper(),
-        "type": type.upper(),
-    })
+    query = query.format(
+        channel_id=channel_id,
+        game_ids=game_ids,
+        after=after if after else "",
+        limit=limit,
+        sort=sort.upper(),
+        type=type.upper(),
+        fields=VIDEO_FIELDS
+    )
 
     response = gql_query(query)
+
+    if not response["data"]["user"]:
+        raise ConsoleError("Channel {} not found".format(channel_id))
+
     return response["data"]["user"]["videos"]
 
 

twitchdl/utils.py

@@ -69,9 +69,9 @@ VIDEO_PATTERNS = [
 ]
 
 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]+)(\?.+)?$",
+    r"^(?P<slug>[A-Za-z0-9]+(?:-[A-Za-z0-9_-]{16})?)$",
+    r"^https://(www.)?twitch.tv/\w+/clip/(?P<slug>[A-Za-z0-9]+(?:-[A-Za-z0-9_-]{16})?)(\?.+)?$",
+    r"^https://clips.twitch.tv/(?P<slug>[A-Za-z0-9]+(?:-[A-Za-z0-9_-]{16})?)(\?.+)?$",
 ]