Initial commit. Added downloader

.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+recorded

README.md

@@ -0,0 +1,4 @@
+## Known issues:
+- Configure logger with config file
+- Support multiple streamer
+- Post process with ffmpeg

main.py

@@ -0,0 +1,85 @@
+import argparse
+import os
+import sys
+import logging
+
+from stream.downloader import TwitchRecorder
+
+
+def parse_arguments():
+    parser = argparse.ArgumentParser(description='Twitch highlighter')
+    parser.add_argument('--client', "-c", help='Twitch client id', required=True, dest="tw_client")
+    parser.add_argument('--secret', "-s", help='Twitch secret id', required=True, dest="tw_secret")
+    parser.add_argument('--user', "-u", help='Twitch streamer username', required=True, dest="tw_streamer")
+    parser.add_argument('--quality', "-q", help='Video downloading quality', dest="tw_quality", default="360p")
+    parser.add_argument('--output_path', "-o", help='Video download folder', dest="output_path", default=os.getcwd())
+
+    return parser.parse_args()
+
+
+def on_downloaded():
+    pass
+
+
+if __name__ == "__main__":
+    # TODO configure logging
+    logging.basicConfig(stream=sys.stdout, level=logging.INFO)
+
+    args = parse_arguments()
+
+    rec = TwitchRecorder(args.tw_client, args.tw_secret, args.tw_streamer, args.output_path,
+                         args.tw_quality, on_download=on_downloaded)
+
+    rec.run()
+
+# Twitch downloader
+# def main(argv):
+#     twitch_recorder = TwitchRecorder()
+#     usage_message = "twitch-recorder.py -u <username> -q <quality>"
+#     logging.basicConfig(filename="twitch-recorder.log", level=logging.INFO)
+#     logging.getLogger().addHandler(logging.StreamHandler())
+#
+#     try:
+#         opts, args = getopt.getopt(argv, "hu:q:l:",
+#                                    ["username=", "quality=", "log=", "logging=", "disable-ffmpeg", 'uid='])
+#     except getopt.GetoptError:
+#         print(usage_message)
+#         sys.exit(2)
+#     print(opts)
+#     for opt, arg in opts:
+#         if opt == "-h":
+#             print(usage_message)
+#             sys.exit()
+#         elif opt in ("-u", "--username"):
+#             twitch_recorder.username = arg
+#         elif opt in ("-q", "--quality"):
+#             twitch_recorder.quality = arg
+#         elif opt in ("-l", "--log", "--logging"):
+#             logging_level = getattr(logging, arg.upper(), None)
+#             if not isinstance(logging_level, int):
+#                 raise ValueError("invalid log level: %s" % logging_level)
+#             logging.basicConfig(level=logging_level)
+#             logging.info("logging configured to %s", arg.upper())
+#         elif opt in "--uid":
+#             twitch_recorder.stream_uid = arg
+#         elif opt == "--disable-ffmpeg":
+#             twitch_recorder.disable_ffmpeg = True
+#             logging.info("ffmpeg disabled")
+#
+#     twitch_recorder.run()
+#
+#
+# if __name__ == "__main__":
+#     main(sys.argv[1:])
+
+# # fix videos from previous recording session
+#        try:
+#            video_list = [f for f in os.listdir(recorded_path) if os.path.isfile(os.path.join(recorded_path, f))]
+#            if len(video_list) > 0:
+#                logging.info("processing previously recorded files")
+#            for f in video_list:
+#                recorded_filename = os.path.join(recorded_path, f)
+#                processed_filename = os.path.join(processed_path, f)
+#                self.process_recorded_file(recorded_filename, processed_filename)
+#        except Exception as e:
+#            logging.error(e)

requirements.txt

@@ -0,0 +1,2 @@
+requests==2.28.1
+streamlink==4.2.0

stream/downloader.py

@@ -0,0 +1,134 @@
+import datetime
+import enum
+import logging
+import os
+import subprocess
+import time
+import requests
+
+TOKEN_URL = "https://id.twitch.tv/oauth2/token?client_id={0}&client_secret={1}&grant_type=client_credentials"
+HELIX_STREAM_URL = "https://api.twitch.tv/helix/streams?user_login={0}"
+
+logger = logging.getLogger(__name__)
+
+
+class TwitchStreamerStatus(enum.Enum):
+    ONLINE = 0
+    OFFLINE = 1
+    NOT_FOUND = 2
+    UNAUTHORIZED = 3
+    ERROR = 4
+
+
+class TwitchRecorder:
+    access_token = None
+
+    def __init__(self, client_id, client_secret, username, output_path, quality="480p", on_download=None):
+        # global configuration
+        self.disable_ffmpeg = False
+        self.refresh_timeout = 15
+        self.output_path = output_path
+        self.stream_uid = None
+        self.on_download = on_download
+
+        # twitch configuration
+        self.username = username
+        self.quality = quality
+        self.client_id = client_id
+        self.client_secret = client_secret
+        self.token_url = TOKEN_URL.format(self.client_id, self.client_secret)
+
+    def fetch_access_token(self):
+        token_response = requests.post(self.token_url, timeout=15)
+        token_response.raise_for_status()
+        token = token_response.json()
+        return token["access_token"]
+
+    def run(self):
+        # path to recorded stream
+        recording_path = os.path.join(self.output_path, "recorded", self.username)
+
+        # create directory for recordedPath and processedPath if not exist
+        if os.path.isdir(recording_path) is False:
+            os.makedirs(recording_path)
+
+        # make sure the interval to check user availability is not less than 15 seconds
+        if self.refresh_timeout < 15:
+            logger.warning("check interval should not be lower than 15 seconds")
+            self.refresh_timeout = 15
+            logger.warning("check interval set to 15 seconds")
+
+        self.access_token = self.fetch_access_token()
+        self.loop_check(recording_path)
+
+    def loop_check(self, recording_path):
+        logger.info("checking for %s every %s seconds, recording with %s quality",
+                    self.username, self.refresh_timeout, self.quality)
+        while True:
+            status, info = self.check_user()
+            if status == TwitchStreamerStatus.NOT_FOUND:
+                logger.error("username not found, invalid username or typo")
+                time.sleep(self.refresh_timeout)
+            elif status == TwitchStreamerStatus.ERROR:
+                logger.error("%s unexpected error. will try again in 5 minutes",
+                             datetime.datetime.now().strftime("%Hh%Mm%Ss"))
+                time.sleep(300)
+            elif status == TwitchStreamerStatus.OFFLINE:
+                logger.info("%s currently offline, checking again in %s seconds", self.username, self.refresh_timeout)
+                time.sleep(self.refresh_timeout)
+            elif status == TwitchStreamerStatus.UNAUTHORIZED:
+                logger.info("unauthorized, will attempt to log back in immediately")
+                self.access_token = self.fetch_access_token()
+            elif status == TwitchStreamerStatus.ONLINE:
+                logger.info("%s online, stream recording in session", self.username)
+
+                channels = info["data"]
+                channel = next(iter(channels), None)
+
+                recorded_filename = self.download_stream(channel, recording_path)
+
+                logger.info("recording stream is done")
+
+                if self.on_download is not None:
+                    self.on_download(recorded_filename)
+
+                time.sleep(self.refresh_timeout)
+
+    def check_user(self):
+        info = None
+        status = TwitchStreamerStatus.ERROR
+        try:
+            headers = {"Client-ID": self.client_id, "Authorization": "Bearer " + self.access_token}
+            r = requests.get(HELIX_STREAM_URL.format(self.username), headers=headers, timeout=15)
+            r.raise_for_status()
+            info = r.json()
+            if info is None or not info["data"]:
+                status = TwitchStreamerStatus.OFFLINE
+            else:
+                status = TwitchStreamerStatus.ONLINE
+        except requests.exceptions.RequestException as e:
+            if e.response:
+                if e.response.status_code == 401:
+                    status = TwitchStreamerStatus.UNAUTHORIZED
+                if e.response.status_code == 404:
+                    status = TwitchStreamerStatus.NOT_FOUND
+        return status, info
+
+    def download_stream(self, channel, recording_path):
+        filename = self.username + " - " + datetime.datetime.now() \
+            .strftime("%Y-%m-%d %Hh%Mm%Ss") + " - " + channel.get("title") + ".mp4"
+
+        filename = "".join(x for x in filename if x.isalnum() or x in [" ", "-", "_", "."])
+        recorded_filename = os.path.join(recording_path, filename)
+
+        # start streamlink process
+        subprocess.call([
+            "streamlink",
+            "--twitch-disable-ads",
+            "twitch.tv/" + self.username,
+            self.quality,
+            "-o",
+            recorded_filename
+        ])
+
+        return recorded_filename