.

.Dockerignore

@@ -0,0 +1,6 @@
+# Ignore Python cache files in all directories
+**/__pycache__/
+*.pyc
+
+# Ignore virtual environment directory
+venv/

.gitignore

@@ -0,0 +1,7 @@
+.env.prod
+# Ignore Python cache files in all directories
+**/__pycache__/
+*.pyc
+
+# Ignore virtual environment directory
+venv/

Dockerfile

@@ -0,0 +1,26 @@
+# Use the official Apache Airflow image as the base
+FROM apache/airflow:2.2.2-python3.9
+
+# Set the working directory
+WORKDIR /opt/airflow
+
+# Copy necessary files into the container
+COPY requirements.txt .
+COPY entrypoint.sh /entrypoint.sh
+COPY dags/ dags/
+COPY config/ config/
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Set environment variables (if not using Render's built-in environment management)
+ENV AIRFLOW_HOME=/opt/airflow
+ENV AIRFLOW__CORE__LOAD_EXAMPLES=False
+ENV AIRFLOW__CORE__DAGS_FOLDER=/opt/airflow/dags
+
+
+# Expose Airflow's webserver port
+EXPOSE 8080
+
+# Run the entrypoint script when the container starts
+ENTRYPOINT ["/entrypoint.sh"]

README.md

@@ -5,6 +5,7 @@ colorFrom: pink
 colorTo: yellow
 sdk: docker
 pinned: false
+app_port: 8080
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

config/airflow.cfg

@@ -0,0 +1,2767 @@
+[core]
+# The folder where your airflow pipelines live, most likely a
+# subfolder in a code repository. This path must be absolute.
+#
+# Variable: AIRFLOW__CORE__DAGS_FOLDER
+#
+dags_folder = /opt/airflow/dags
+
+# Hostname by providing a path to a callable, which will resolve the hostname.
+# The format is "package.function".
+# 
+# For example, default value ``airflow.utils.net.getfqdn`` means that result from patched
+# version of `socket.getfqdn() <https://docs.python.org/3/library/socket.html#socket.getfqdn>`__,
+# see related `CPython Issue <https://github.com/python/cpython/issues/49254>`__.
+# 
+# No argument should be required in the function specified.
+# If using IP address as hostname is preferred, use value ``airflow.utils.net.get_host_ip_address``
+#
+# Variable: AIRFLOW__CORE__HOSTNAME_CALLABLE
+#
+hostname_callable = airflow.utils.net.getfqdn
+
+# A callable to check if a python file has airflow dags defined or not and should
+# return ``True`` if it has dags otherwise ``False``.
+# If this is not provided, Airflow uses its own heuristic rules.
+# 
+# The function should have the following signature
+# 
+# .. code-block:: python
+# 
+#     def func_name(file_path: str, zip_file: zipfile.ZipFile | None = None) -> bool: ...
+#
+# Variable: AIRFLOW__CORE__MIGHT_CONTAIN_DAG_CALLABLE
+#
+might_contain_dag_callable = airflow.utils.file.might_contain_dag_via_default_heuristic
+
+# Default timezone in case supplied date times are naive
+# can be `UTC` (default), `system`, or any `IANA <https://www.iana.org/time-zones>`
+# timezone string (e.g. Europe/Amsterdam)
+#
+# Variable: AIRFLOW__CORE__DEFAULT_TIMEZONE
+#
+default_timezone = Asia/Ho_Chi_Minh
+
+# The executor class that airflow should use. Choices include
+# ``SequentialExecutor``, ``LocalExecutor``, ``CeleryExecutor``,
+# ``KubernetesExecutor``, ``CeleryKubernetesExecutor``, ``LocalKubernetesExecutor`` or the
+# full import path to the class when using a custom executor.
+#
+# Variable: AIRFLOW__CORE__EXECUTOR
+#
+executor = ${AIRFLOW__CORE__EXECUTOR}
+
+# The auth manager class that airflow should use. Full import path to the auth manager class.
+#
+# Variable: AIRFLOW__CORE__AUTH_MANAGER
+#
+auth_manager = airflow.providers.fab.auth_manager.fab_auth_manager.FabAuthManager
+
+# This defines the maximum number of task instances that can run concurrently per scheduler in
+# Airflow, regardless of the worker count. Generally this value, multiplied by the number of
+# schedulers in your cluster, is the maximum number of task instances with the running
+# state in the metadata database. Setting this value to zero allows unlimited parallelism.
+#
+# Variable: AIRFLOW__CORE__PARALLELISM
+#
+parallelism = 32
+
+# The maximum number of task instances allowed to run concurrently in each DAG. To calculate
+# the number of tasks that is running concurrently for a DAG, add up the number of running
+# tasks for all DAG runs of the DAG. This is configurable at the DAG level with ``max_active_tasks``,
+# which is defaulted as ``[core] max_active_tasks_per_dag``.
+# 
+# An example scenario when this would be useful is when you want to stop a new dag with an early
+# start date from stealing all the executor slots in a cluster.
+#
+# Variable: AIRFLOW__CORE__MAX_ACTIVE_TASKS_PER_DAG
+#
+max_active_tasks_per_dag = 16
+
+# Are DAGs paused by default at creation
+#
+# Variable: AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION
+#
+dags_are_paused_at_creation = True
+
+# The maximum number of active DAG runs per DAG. The scheduler will not create more DAG runs
+# if it reaches the limit. This is configurable at the DAG level with ``max_active_runs``,
+# which is defaulted as ``[core] max_active_runs_per_dag``.
+#
+# Variable: AIRFLOW__CORE__MAX_ACTIVE_RUNS_PER_DAG
+#
+max_active_runs_per_dag = 16
+
+# (experimental) The maximum number of consecutive DAG failures before DAG is automatically paused.
+# This is also configurable per DAG level with ``max_consecutive_failed_dag_runs``,
+# which is defaulted as ``[core] max_consecutive_failed_dag_runs_per_dag``.
+# If not specified, then the value is considered as 0,
+# meaning that the dags are never paused out by default.
+#
+# Variable: AIRFLOW__CORE__MAX_CONSECUTIVE_FAILED_DAG_RUNS_PER_DAG
+#
+max_consecutive_failed_dag_runs_per_dag = 0
+
+# The name of the method used in order to start Python processes via the multiprocessing module.
+# This corresponds directly with the options available in the Python docs:
+# `multiprocessing.set_start_method
+# <https://docs.python.org/3/library/multiprocessing.html#multiprocessing.set_start_method>`__
+# must be one of the values returned by `multiprocessing.get_all_start_methods()
+# <https://docs.python.org/3/library/multiprocessing.html#multiprocessing.get_all_start_methods>`__.
+#
+# Example: mp_start_method = fork
+#
+# Variable: AIRFLOW__CORE__MP_START_METHOD
+#
+# mp_start_method = 
+
+# Whether to load the DAG examples that ship with Airflow. It's good to
+# get started, but you probably want to set this to ``False`` in a production
+# environment
+#
+# Variable: AIRFLOW__CORE__LOAD_EXAMPLES
+#
+load_examples = True
+
+# Path to the folder containing Airflow plugins
+#
+# Variable: AIRFLOW__CORE__PLUGINS_FOLDER
+#
+plugins_folder = /opt/airflow/plugins
+
+# Should tasks be executed via forking of the parent process
+# 
+# * ``False``: Execute via forking of the parent process
+# * ``True``: Spawning a new python process, slower than fork, but means plugin changes picked
+#   up by tasks straight away
+#
+# Variable: AIRFLOW__CORE__EXECUTE_TASKS_NEW_PYTHON_INTERPRETER
+#
+execute_tasks_new_python_interpreter = False
+
+# Secret key to save connection passwords in the db
+#
+# Variable: AIRFLOW__CORE__FERNET_KEY
+#
+fernet_key = 
+
+# Whether to disable pickling dags
+#
+# Variable: AIRFLOW__CORE__DONOT_PICKLE
+#
+donot_pickle = True
+
+# How long before timing out a python file import
+#
+# Variable: AIRFLOW__CORE__DAGBAG_IMPORT_TIMEOUT
+#
+dagbag_import_timeout = 30.0
+
+# Should a traceback be shown in the UI for dagbag import errors,
+# instead of just the exception message
+#
+# Variable: AIRFLOW__CORE__DAGBAG_IMPORT_ERROR_TRACEBACKS
+#
+dagbag_import_error_tracebacks = True
+
+# If tracebacks are shown, how many entries from the traceback should be shown
+#
+# Variable: AIRFLOW__CORE__DAGBAG_IMPORT_ERROR_TRACEBACK_DEPTH
+#
+dagbag_import_error_traceback_depth = 2
+
+# How long before timing out a DagFileProcessor, which processes a dag file
+#
+# Variable: AIRFLOW__CORE__DAG_FILE_PROCESSOR_TIMEOUT
+#
+dag_file_processor_timeout = 50
+
+# The class to use for running task instances in a subprocess.
+# Choices include StandardTaskRunner, CgroupTaskRunner or the full import path to the class
+# when using a custom task runner.
+#
+# Variable: AIRFLOW__CORE__TASK_RUNNER
+#
+task_runner = StandardTaskRunner
+
+# If set, tasks without a ``run_as_user`` argument will be run with this user
+# Can be used to de-elevate a sudo user running Airflow when executing tasks
+#
+# Variable: AIRFLOW__CORE__DEFAULT_IMPERSONATION
+#
+default_impersonation = 
+
+# What security module to use (for example kerberos)
+#
+# Variable: AIRFLOW__CORE__SECURITY
+#
+security = 
+
+# Turn unit test mode on (overwrites many configuration options with test
+# values at runtime)
+#
+# Variable: AIRFLOW__CORE__UNIT_TEST_MODE
+#
+unit_test_mode = False
+
+# Whether to enable pickling for xcom (note that this is insecure and allows for
+# RCE exploits).
+#
+# Variable: AIRFLOW__CORE__ENABLE_XCOM_PICKLING
+#
+enable_xcom_pickling = False
+
+# What classes can be imported during deserialization. This is a multi line value.
+# The individual items will be parsed as a pattern to a glob function.
+# Python built-in classes (like dict) are always allowed.
+#
+# Variable: AIRFLOW__CORE__ALLOWED_DESERIALIZATION_CLASSES
+#
+allowed_deserialization_classes = airflow.*
+
+# What classes can be imported during deserialization. This is a multi line value.
+# The individual items will be parsed as regexp patterns.
+# This is a secondary option to ``[core] allowed_deserialization_classes``.
+#
+# Variable: AIRFLOW__CORE__ALLOWED_DESERIALIZATION_CLASSES_REGEXP
+#
+allowed_deserialization_classes_regexp = 
+
+# When a task is killed forcefully, this is the amount of time in seconds that
+# it has to cleanup after it is sent a SIGTERM, before it is SIGKILLED
+#
+# Variable: AIRFLOW__CORE__KILLED_TASK_CLEANUP_TIME
+#
+killed_task_cleanup_time = 60
+
+# Whether to override params with dag_run.conf. If you pass some key-value pairs
+# through ``airflow dags backfill -c`` or
+# ``airflow dags trigger -c``, the key-value pairs will override the existing ones in params.
+#
+# Variable: AIRFLOW__CORE__DAG_RUN_CONF_OVERRIDES_PARAMS
+#
+dag_run_conf_overrides_params = True
+
+# If enabled, Airflow will only scan files containing both ``DAG`` and ``airflow`` (case-insensitive).
+#
+# Variable: AIRFLOW__CORE__DAG_DISCOVERY_SAFE_MODE
+#
+dag_discovery_safe_mode = True
+
+# The pattern syntax used in the
+# `.airflowignore
+# <https://airflow.apache.org/docs/apache-airflow/stable/core-concepts/dags.html#airflowignore>`__
+# files in the DAG directories. Valid values are ``regexp`` or ``glob``.
+#
+# Variable: AIRFLOW__CORE__DAG_IGNORE_FILE_SYNTAX
+#
+dag_ignore_file_syntax = regexp
+
+# The number of retries each task is going to have by default. Can be overridden at dag or task level.
+#
+# Variable: AIRFLOW__CORE__DEFAULT_TASK_RETRIES
+#
+default_task_retries = 0
+
+# The number of seconds each task is going to wait by default between retries. Can be overridden at
+# dag or task level.
+#
+# Variable: AIRFLOW__CORE__DEFAULT_TASK_RETRY_DELAY
+#
+default_task_retry_delay = 300
+
+# The maximum delay (in seconds) each task is going to wait by default between retries.
+# This is a global setting and cannot be overridden at task or DAG level.
+#
+# Variable: AIRFLOW__CORE__MAX_TASK_RETRY_DELAY
+#
+max_task_retry_delay = 86400
+
+# The weighting method used for the effective total priority weight of the task
+#
+# Variable: AIRFLOW__CORE__DEFAULT_TASK_WEIGHT_RULE
+#
+default_task_weight_rule = downstream
+
+# Maximum possible time (in seconds) that task will have for execution of auxiliary processes
+# (like listeners, mini scheduler...) after task is marked as success..
+#
+# Variable: AIRFLOW__CORE__TASK_SUCCESS_OVERTIME
+#
+task_success_overtime = 20
+
+# The default task execution_timeout value for the operators. Expected an integer value to
+# be passed into timedelta as seconds. If not specified, then the value is considered as None,
+# meaning that the operators are never timed out by default.
+#
+# Variable: AIRFLOW__CORE__DEFAULT_TASK_EXECUTION_TIMEOUT
+#
+default_task_execution_timeout = 
+
+# Updating serialized DAG can not be faster than a minimum interval to reduce database write rate.
+#
+# Variable: AIRFLOW__CORE__MIN_SERIALIZED_DAG_UPDATE_INTERVAL
+#
+min_serialized_dag_update_interval = 30
+
+# If ``True``, serialized DAGs are compressed before writing to DB.
+# 
+# .. note::
+# 
+#     This will disable the DAG dependencies view
+#
+# Variable: AIRFLOW__CORE__COMPRESS_SERIALIZED_DAGS
+#
+compress_serialized_dags = False
+
+# Fetching serialized DAG can not be faster than a minimum interval to reduce database
+# read rate. This config controls when your DAGs are updated in the Webserver
+#
+# Variable: AIRFLOW__CORE__MIN_SERIALIZED_DAG_FETCH_INTERVAL
+#
+min_serialized_dag_fetch_interval = 10
+
+# Maximum number of Rendered Task Instance Fields (Template Fields) per task to store
+# in the Database.
+# All the template_fields for each of Task Instance are stored in the Database.
+# Keeping this number small may cause an error when you try to view ``Rendered`` tab in
+# TaskInstance view for older tasks.
+#
+# Variable: AIRFLOW__CORE__MAX_NUM_RENDERED_TI_FIELDS_PER_TASK
+#
+max_num_rendered_ti_fields_per_task = 30
+
+# On each dagrun check against defined SLAs
+#
+# Variable: AIRFLOW__CORE__CHECK_SLAS
+#
+check_slas = True
+
+# Path to custom XCom class that will be used to store and resolve operators results
+#
+# Example: xcom_backend = path.to.CustomXCom
+#
+# Variable: AIRFLOW__CORE__XCOM_BACKEND
+#
+xcom_backend = airflow.models.xcom.BaseXCom
+
+# By default Airflow plugins are lazily-loaded (only loaded when required). Set it to ``False``,
+# if you want to load plugins whenever 'airflow' is invoked via cli or loaded from module.
+#
+# Variable: AIRFLOW__CORE__LAZY_LOAD_PLUGINS
+#
+lazy_load_plugins = True
+
+# By default Airflow providers are lazily-discovered (discovery and imports happen only when required).
+# Set it to ``False``, if you want to discover providers whenever 'airflow' is invoked via cli or
+# loaded from module.
+#
+# Variable: AIRFLOW__CORE__LAZY_DISCOVER_PROVIDERS
+#
+lazy_discover_providers = True
+
+# Hide sensitive **Variables** or **Connection extra json keys** from UI
+# and task logs when set to ``True``
+# 
+# .. note::
+# 
+#     Connection passwords are always hidden in logs
+#
+# Variable: AIRFLOW__CORE__HIDE_SENSITIVE_VAR_CONN_FIELDS
+#
+hide_sensitive_var_conn_fields = True
+
+# A comma-separated list of extra sensitive keywords to look for in variables names or connection's
+# extra JSON.
+#
+# Variable: AIRFLOW__CORE__SENSITIVE_VAR_CONN_NAMES
+#
+sensitive_var_conn_names = 
+
+# Task Slot counts for ``default_pool``. This setting would not have any effect in an existing
+# deployment where the ``default_pool`` is already created. For existing deployments, users can
+# change the number of slots using Webserver, API or the CLI
+#
+# Variable: AIRFLOW__CORE__DEFAULT_POOL_TASK_SLOT_COUNT
+#
+default_pool_task_slot_count = 128
+
+# The maximum list/dict length an XCom can push to trigger task mapping. If the pushed list/dict has a
+# length exceeding this value, the task pushing the XCom will be failed automatically to prevent the
+# mapped tasks from clogging the scheduler.
+#
+# Variable: AIRFLOW__CORE__MAX_MAP_LENGTH
+#
+max_map_length = 1024
+
+# The default umask to use for process when run in daemon mode (scheduler, worker,  etc.)
+# 
+# This controls the file-creation mode mask which determines the initial value of file permission bits
+# for newly created files.
+# 
+# This value is treated as an octal-integer.
+#
+# Variable: AIRFLOW__CORE__DAEMON_UMASK
+#
+daemon_umask = 0o077
+
+# Class to use as dataset manager.
+#
+# Example: dataset_manager_class = airflow.datasets.manager.DatasetManager
+#
+# Variable: AIRFLOW__CORE__DATASET_MANAGER_CLASS
+#
+# dataset_manager_class = 
+
+# Kwargs to supply to dataset manager.
+#
+# Example: dataset_manager_kwargs = {"some_param": "some_value"}
+#
+# Variable: AIRFLOW__CORE__DATASET_MANAGER_KWARGS
+#
+# dataset_manager_kwargs = 
+
+# Dataset URI validation should raise an exception if it is not compliant with AIP-60.
+# By default this configuration is false, meaning that Airflow 2.x only warns the user.
+# In Airflow 3, this configuration will be enabled by default.
+#
+# Variable: AIRFLOW__CORE__STRICT_DATASET_URI_VALIDATION
+#
+strict_dataset_uri_validation = False
+
+# (experimental) Whether components should use Airflow Internal API for DB connectivity.
+#
+# Variable: AIRFLOW__CORE__DATABASE_ACCESS_ISOLATION
+#
+database_access_isolation = False
+
+# (experimental) Airflow Internal API url.
+# Only used if ``[core] database_access_isolation`` is ``True``.
+#
+# Example: internal_api_url = http://localhost:8080
+#
+# Variable: AIRFLOW__CORE__INTERNAL_API_URL
+#
+# internal_api_url = 
+
+# Secret key used to authenticate internal API clients to core. It should be as random as possible.
+# However, when running more than 1 instances of webserver / internal API services, make sure all
+# of them use the same ``secret_key`` otherwise calls will fail on authentication.
+# The authentication token generated using the secret key has a short expiry time though - make
+# sure that time on ALL the machines that you run airflow components on is synchronized
+# (for example using ntpd) otherwise you might get "forbidden" errors when the logs are accessed.
+#
+# Variable: AIRFLOW__CORE__INTERNAL_API_SECRET_KEY
+#
+internal_api_secret_key = pDBrar+Nyodn8Sf5ZeJfVw==
+
+# The ability to allow testing connections across Airflow UI, API and CLI.
+# Supported options: ``Disabled``, ``Enabled``, ``Hidden``. Default: Disabled
+# Disabled - Disables the test connection functionality and disables the Test Connection button in UI.
+# Enabled - Enables the test connection functionality and shows the Test Connection button in UI.
+# Hidden - Disables the test connection functionality and hides the Test Connection button in UI.
+# Before setting this to Enabled, make sure that you review the users who are able to add/edit
+# connections and ensure they are trusted. Connection testing can be done maliciously leading to
+# undesired and insecure outcomes.
+# See `Airflow Security Model: Capabilities of authenticated UI users
+# <https://airflow.apache.org/docs/apache-airflow/stable/security/security_model.html#capabilities-of-authenticated-ui-users>`__
+# for more details.
+#
+# Variable: AIRFLOW__CORE__TEST_CONNECTION
+#
+test_connection = Disabled
+
+# The maximum length of the rendered template field. If the value to be stored in the
+# rendered template field exceeds this size, it's redacted.
+#
+# Variable: AIRFLOW__CORE__MAX_TEMPLATED_FIELD_LENGTH
+#
+max_templated_field_length = 4096
+
+[database]
+# Path to the ``alembic.ini`` file. You can either provide the file path relative
+# to the Airflow home directory or the absolute path if it is located elsewhere.
+#
+# Variable: AIRFLOW__DATABASE__ALEMBIC_INI_FILE_PATH
+#
+alembic_ini_file_path = alembic.ini
+
+# The SQLAlchemy connection string to the metadata database.
+# SQLAlchemy supports many different database engines.
+# See: `Set up a Database Backend: Database URI
+# <https://airflow.apache.org/docs/apache-airflow/stable/howto/set-up-database.html#database-uri>`__
+# for more details.
+#
+# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_CONN
+#
+sql_alchemy_conn = ${AIRFLOW__DATABASE__SQL_ALCHEMY_CONN}
+
+# Extra engine specific keyword args passed to SQLAlchemy's create_engine, as a JSON-encoded value
+#
+# Example: sql_alchemy_engine_args = {"arg1": true}
+#
+# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_ENGINE_ARGS
+#
+# sql_alchemy_engine_args = 
+
+# The encoding for the databases
+#
+# Variable: AIRFLOW__DATABASE__SQL_ENGINE_ENCODING
+#
+sql_engine_encoding = utf-8
+
+# Collation for ``dag_id``, ``task_id``, ``key``, ``external_executor_id`` columns
+# in case they have different encoding.
+# By default this collation is the same as the database collation, however for ``mysql`` and ``mariadb``
+# the default is ``utf8mb3_bin`` so that the index sizes of our index keys will not exceed
+# the maximum size of allowed index when collation is set to ``utf8mb4`` variant, see
+# `GitHub Issue Comment <https://github.com/apache/airflow/pull/17603#issuecomment-901121618>`__
+# for more details.
+#
+# Variable: AIRFLOW__DATABASE__SQL_ENGINE_COLLATION_FOR_IDS
+#
+# sql_engine_collation_for_ids = 
+
+# If SQLAlchemy should pool database connections.
+#
+# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_POOL_ENABLED
+#
+sql_alchemy_pool_enabled = True
+
+# The SQLAlchemy pool size is the maximum number of database connections
+# in the pool. 0 indicates no limit.
+#
+# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_POOL_SIZE
+#
+sql_alchemy_pool_size = 5
+
+# The maximum overflow size of the pool.
+# When the number of checked-out connections reaches the size set in pool_size,
+# additional connections will be returned up to this limit.
+# When those additional connections are returned to the pool, they are disconnected and discarded.
+# It follows then that the total number of simultaneous connections the pool will allow
+# is **pool_size** + **max_overflow**,
+# and the total number of "sleeping" connections the pool will allow is pool_size.
+# max_overflow can be set to ``-1`` to indicate no overflow limit;
+# no limit will be placed on the total number of concurrent connections. Defaults to ``10``.
+#
+# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_MAX_OVERFLOW
+#
+sql_alchemy_max_overflow = 10
+
+# The SQLAlchemy pool recycle is the number of seconds a connection
+# can be idle in the pool before it is invalidated. This config does
+# not apply to sqlite. If the number of DB connections is ever exceeded,
+# a lower config value will allow the system to recover faster.
+#
+# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_POOL_RECYCLE
+#
+sql_alchemy_pool_recycle = 1800
+
+# Check connection at the start of each connection pool checkout.
+# Typically, this is a simple statement like "SELECT 1".
+# See `SQLAlchemy Pooling: Disconnect Handling - Pessimistic
+# <https://docs.sqlalchemy.org/en/14/core/pooling.html#disconnect-handling-pessimistic>`__
+# for more details.
+#
+# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_POOL_PRE_PING
+#
+sql_alchemy_pool_pre_ping = True
+
+# The schema to use for the metadata database.
+# SQLAlchemy supports databases with the concept of multiple schemas.
+#
+# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_SCHEMA
+#
+sql_alchemy_schema = 
+
+# Import path for connect args in SQLAlchemy. Defaults to an empty dict.
+# This is useful when you want to configure db engine args that SQLAlchemy won't parse
+# in connection string. This can be set by passing a dictionary containing the create engine parameters.
+# For more details about passing create engine parameters (keepalives variables, timeout etc)
+# in Postgres DB Backend see `Setting up a PostgreSQL Database
+# <https://airflow.apache.org/docs/apache-airflow/stable/howto/set-up-database.html#setting-up-a-postgresql-database>`__
+# e.g ``connect_args={"timeout":30}`` can be defined in ``airflow_local_settings.py`` and
+# can be imported as shown below
+#
+# Example: sql_alchemy_connect_args = airflow_local_settings.connect_args
+#
+# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_CONNECT_ARGS
+#
+# sql_alchemy_connect_args = 
+
+# Important Warning: Use of sql_alchemy_session_maker Highly Discouraged
+# Import path for function which returns 'sqlalchemy.orm.sessionmaker'.
+# Improper configuration of sql_alchemy_session_maker can lead to serious issues,
+# including data corruption, unrecoverable application crashes. Please review the SQLAlchemy
+# documentation for detailed guidance on proper configuration and best practices.
+#
+# Example: sql_alchemy_session_maker = airflow_local_settings._sessionmaker
+#
+# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_SESSION_MAKER
+#
+# sql_alchemy_session_maker = 
+
+# Whether to load the default connections that ship with Airflow when ``airflow db init`` is called.
+# It's good to get started, but you probably want to set this to ``False`` in a production environment.
+#
+# Variable: AIRFLOW__DATABASE__LOAD_DEFAULT_CONNECTIONS
+#
+load_default_connections = True
+
+# Number of times the code should be retried in case of DB Operational Errors.
+# Not all transactions will be retried as it can cause undesired state.
+# Currently it is only used in ``DagFileProcessor.process_file`` to retry ``dagbag.sync_to_db``.
+#
+# Variable: AIRFLOW__DATABASE__MAX_DB_RETRIES
+#
+max_db_retries = 3
+
+# Whether to run alembic migrations during Airflow start up. Sometimes this operation can be expensive,
+# and the users can assert the correct version through other means (e.g. through a Helm chart).
+# Accepts ``True`` or ``False``.
+#
+# Variable: AIRFLOW__DATABASE__CHECK_MIGRATIONS
+#
+check_migrations = True
+
+[logging]
+# The folder where airflow should store its log files.
+# This path must be absolute.
+# There are a few existing configurations that assume this is set to the default.
+# If you choose to override this you may need to update the
+# ``[logging] dag_processor_manager_log_location`` and
+# ``[logging] child_process_log_directory settings`` as well.
+#
+# Variable: AIRFLOW__LOGGING__BASE_LOG_FOLDER
+#
+base_log_folder = /opt/airflow/logs
+
+# Airflow can store logs remotely in AWS S3, Google Cloud Storage or Elastic Search.
+# Set this to ``True`` if you want to enable remote logging.
+#
+# Variable: AIRFLOW__LOGGING__REMOTE_LOGGING
+#
+remote_logging = False
+
+# Users must supply an Airflow connection id that provides access to the storage
+# location. Depending on your remote logging service, this may only be used for
+# reading logs, not writing them.
+#
+# Variable: AIRFLOW__LOGGING__REMOTE_LOG_CONN_ID
+#
+remote_log_conn_id = 
+
+# Whether the local log files for GCS, S3, WASB and OSS remote logging should be deleted after
+# they are uploaded to the remote location.
+#
+# Variable: AIRFLOW__LOGGING__DELETE_LOCAL_LOGS
+#
+delete_local_logs = False
+
+# Path to Google Credential JSON file. If omitted, authorization based on `the Application Default
+# Credentials
+# <https://cloud.google.com/docs/authentication/application-default-credentials>`__ will
+# be used.
+#
+# Variable: AIRFLOW__LOGGING__GOOGLE_KEY_PATH
+#
+google_key_path = 
+
+# Storage bucket URL for remote logging
+# S3 buckets should start with **s3://**
+# Cloudwatch log groups should start with **cloudwatch://**
+# GCS buckets should start with **gs://**
+# WASB buckets should start with **wasb** just to help Airflow select correct handler
+# Stackdriver logs should start with **stackdriver://**
+#
+# Variable: AIRFLOW__LOGGING__REMOTE_BASE_LOG_FOLDER
+#
+remote_base_log_folder = 
+
+# The remote_task_handler_kwargs param is loaded into a dictionary and passed to the ``__init__``
+# of remote task handler and it overrides the values provided by Airflow config. For example if you set
+# ``delete_local_logs=False`` and you provide ``{"delete_local_copy": true}``, then the local
+# log files will be deleted after they are uploaded to remote location.
+#
+# Example: remote_task_handler_kwargs = {"delete_local_copy": true}
+#
+# Variable: AIRFLOW__LOGGING__REMOTE_TASK_HANDLER_KWARGS
+#
+remote_task_handler_kwargs = 
+
+# Use server-side encryption for logs stored in S3
+#
+# Variable: AIRFLOW__LOGGING__ENCRYPT_S3_LOGS
+#
+encrypt_s3_logs = False
+
+# Logging level.
+# 
+# Supported values: ``CRITICAL``, ``ERROR``, ``WARNING``, ``INFO``, ``DEBUG``.
+#
+# Variable: AIRFLOW__LOGGING__LOGGING_LEVEL
+#
+logging_level = INFO
+
+# Logging level for celery. If not set, it uses the value of logging_level
+# 
+# Supported values: ``CRITICAL``, ``ERROR``, ``WARNING``, ``INFO``, ``DEBUG``.
+#
+# Variable: AIRFLOW__LOGGING__CELERY_LOGGING_LEVEL
+#
+celery_logging_level = 
+
+# Logging level for Flask-appbuilder UI.
+# 
+# Supported values: ``CRITICAL``, ``ERROR``, ``WARNING``, ``INFO``, ``DEBUG``.
+#
+# Variable: AIRFLOW__LOGGING__FAB_LOGGING_LEVEL
+#
+fab_logging_level = WARNING
+
+# Logging class
+# Specify the class that will specify the logging configuration
+# This class has to be on the python classpath
+#
+# Example: logging_config_class = my.path.default_local_settings.LOGGING_CONFIG
+#
+# Variable: AIRFLOW__LOGGING__LOGGING_CONFIG_CLASS
+#
+logging_config_class = 
+
+# Flag to enable/disable Colored logs in Console
+# Colour the logs when the controlling terminal is a TTY.
+#
+# Variable: AIRFLOW__LOGGING__COLORED_CONSOLE_LOG
+#
+colored_console_log = True
+
+# Log format for when Colored logs is enabled
+#
+# Variable: AIRFLOW__LOGGING__COLORED_LOG_FORMAT
+#
+colored_log_format = [%%(blue)s%%(asctime)s%%(reset)s] {%%(blue)s%%(filename)s:%%(reset)s%%(lineno)d} %%(log_color)s%%(levelname)s%%(reset)s - %%(log_color)s%%(message)s%%(reset)s
+
+# Specifies the class utilized by Airflow to implement colored logging
+#
+# Variable: AIRFLOW__LOGGING__COLORED_FORMATTER_CLASS
+#
+colored_formatter_class = airflow.utils.log.colored_log.CustomTTYColoredFormatter
+
+# Format of Log line
+#
+# Variable: AIRFLOW__LOGGING__LOG_FORMAT
+#
+log_format = [%%(asctime)s] {%%(filename)s:%%(lineno)d} %%(levelname)s - %%(message)s
+
+# Defines the format of log messages for simple logging configuration
+#
+# Variable: AIRFLOW__LOGGING__SIMPLE_LOG_FORMAT
+#
+simple_log_format = %%(asctime)s %%(levelname)s - %%(message)s
+
+# Where to send dag parser logs. If "file", logs are sent to log files defined by child_process_log_directory.
+#
+# Variable: AIRFLOW__LOGGING__DAG_PROCESSOR_LOG_TARGET
+#
+dag_processor_log_target = file
+
+# Format of Dag Processor Log line
+#
+# Variable: AIRFLOW__LOGGING__DAG_PROCESSOR_LOG_FORMAT
+#
+dag_processor_log_format = [%%(asctime)s] [SOURCE:DAG_PROCESSOR] {%%(filename)s:%%(lineno)d} %%(levelname)s - %%(message)s
+
+# Determines the formatter class used by Airflow for structuring its log messages
+# The default formatter class is timezone-aware, which means that timestamps attached to log entries
+# will be adjusted to reflect the local timezone of the Airflow instance
+#
+# Variable: AIRFLOW__LOGGING__LOG_FORMATTER_CLASS
+#
+log_formatter_class = airflow.utils.log.timezone_aware.TimezoneAware
+
+# An import path to a function to add adaptations of each secret added with
+# ``airflow.utils.log.secrets_masker.mask_secret`` to be masked in log messages. The given function
+# is expected to require a single parameter: the secret to be adapted. It may return a
+# single adaptation of the secret or an iterable of adaptations to each be masked as secrets.
+# The original secret will be masked as well as any adaptations returned.
+#
+# Example: secret_mask_adapter = urllib.parse.quote
+#
+# Variable: AIRFLOW__LOGGING__SECRET_MASK_ADAPTER
+#
+secret_mask_adapter = 
+
+# Specify prefix pattern like mentioned below with stream handler ``TaskHandlerWithCustomFormatter``
+#
+# Example: task_log_prefix_template = {{ti.dag_id}}-{{ti.task_id}}-{{execution_date}}-{{ti.try_number}}
+#
+# Variable: AIRFLOW__LOGGING__TASK_LOG_PREFIX_TEMPLATE
+#
+task_log_prefix_template = 
+
+# Formatting for how airflow generates file names/paths for each task run.
+#
+# Variable: AIRFLOW__LOGGING__LOG_FILENAME_TEMPLATE
+#
+log_filename_template = dag_id={{ ti.dag_id }}/run_id={{ ti.run_id }}/task_id={{ ti.task_id }}/{%% if ti.map_index >= 0 %%}map_index={{ ti.map_index }}/{%% endif %%}attempt={{ try_number }}.log
+
+# Formatting for how airflow generates file names for log
+#
+# Variable: AIRFLOW__LOGGING__LOG_PROCESSOR_FILENAME_TEMPLATE
+#
+log_processor_filename_template = {{ filename }}.log
+
+# Full path of dag_processor_manager logfile.
+#
+# Variable: AIRFLOW__LOGGING__DAG_PROCESSOR_MANAGER_LOG_LOCATION
+#
+dag_processor_manager_log_location = /opt/airflow/logs/dag_processor_manager/dag_processor_manager.log
+
+# Whether DAG processor manager will write logs to stdout
+#
+# Variable: AIRFLOW__LOGGING__DAG_PROCESSOR_MANAGER_LOG_STDOUT
+#
+dag_processor_manager_log_stdout = False
+
+# Name of handler to read task instance logs.
+# Defaults to use ``task`` handler.
+#
+# Variable: AIRFLOW__LOGGING__TASK_LOG_READER
+#
+task_log_reader = task
+
+# A comma\-separated list of third-party logger names that will be configured to print messages to
+# consoles\.
+#
+# Example: extra_logger_names = connexion,sqlalchemy
+#
+# Variable: AIRFLOW__LOGGING__EXTRA_LOGGER_NAMES
+#
+extra_logger_names = 
+
+# When you start an Airflow worker, Airflow starts a tiny web server
+# subprocess to serve the workers local log files to the airflow main
+# web server, who then builds pages and sends them to users. This defines
+# the port on which the logs are served. It needs to be unused, and open
+# visible from the main web server to connect into the workers.
+#
+# Variable: AIRFLOW__LOGGING__WORKER_LOG_SERVER_PORT
+#
+worker_log_server_port = 8793
+
+# Port to serve logs from for triggerer.
+# See ``[logging] worker_log_server_port`` description for more info.
+#
+# Variable: AIRFLOW__LOGGING__TRIGGER_LOG_SERVER_PORT
+#
+trigger_log_server_port = 8794
+
+# We must parse timestamps to interleave logs between trigger and task.  To do so,
+# we need to parse timestamps in log files. In case your log format is non-standard,
+# you may provide import path to callable which takes a string log line and returns
+# the timestamp (datetime.datetime compatible).
+#
+# Example: interleave_timestamp_parser = path.to.my_func
+#
+# Variable: AIRFLOW__LOGGING__INTERLEAVE_TIMESTAMP_PARSER
+#
+# interleave_timestamp_parser = 
+
+# Permissions in the form or of octal string as understood by chmod. The permissions are important
+# when you use impersonation, when logs are written by a different user than airflow. The most secure
+# way of configuring it in this case is to add both users to the same group and make it the default
+# group of both users. Group-writeable logs are default in airflow, but you might decide that you are
+# OK with having the logs other-writeable, in which case you should set it to ``0o777``. You might
+# decide to add more security if you do not use impersonation and change it to ``0o755`` to make it
+# only owner-writeable. You can also make it just readable only for owner by changing it to ``0o700``
+# if all the access (read/write) for your logs happens from the same user.
+#
+# Example: file_task_handler_new_folder_permissions = 0o775
+#
+# Variable: AIRFLOW__LOGGING__FILE_TASK_HANDLER_NEW_FOLDER_PERMISSIONS
+#
+file_task_handler_new_folder_permissions = 0o775
+
+# Permissions in the form or of octal string as understood by chmod. The permissions are important
+# when you use impersonation, when logs are written by a different user than airflow. The most secure
+# way of configuring it in this case is to add both users to the same group and make it the default
+# group of both users. Group-writeable logs are default in airflow, but you might decide that you are
+# OK with having the logs other-writeable, in which case you should set it to ``0o666``. You might
+# decide to add more security if you do not use impersonation and change it to ``0o644`` to make it
+# only owner-writeable. You can also make it just readable only for owner by changing it to ``0o600``
+# if all the access (read/write) for your logs happens from the same user.
+#
+# Example: file_task_handler_new_file_permissions = 0o664
+#
+# Variable: AIRFLOW__LOGGING__FILE_TASK_HANDLER_NEW_FILE_PERMISSIONS
+#
+file_task_handler_new_file_permissions = 0o664
+
+# By default Celery sends all logs into stderr.
+# If enabled any previous logging handlers will get *removed*.
+# With this option AirFlow will create new handlers
+# and send low level logs like INFO and WARNING to stdout,
+# while sending higher severity logs to stderr.
+#
+# Variable: AIRFLOW__LOGGING__CELERY_STDOUT_STDERR_SEPARATION
+#
+celery_stdout_stderr_separation = False
+
+# If enabled, Airflow may ship messages to task logs from outside the task run context, e.g. from
+# the scheduler, executor, or callback execution context. This can help in circumstances such as
+# when there's something blocking the execution of the task and ordinarily there may be no task
+# logs at all.
+# This is set to ``True`` by default. If you encounter issues with this feature
+# (e.g. scheduler performance issues) it can be disabled.
+#
+# Variable: AIRFLOW__LOGGING__ENABLE_TASK_CONTEXT_LOGGER
+#
+enable_task_context_logger = True
+
+# A comma separated list of keywords related to errors whose presence should display the line in red
+# color in UI
+#
+# Variable: AIRFLOW__LOGGING__COLOR_LOG_ERROR_KEYWORDS
+#
+color_log_error_keywords = error,exception
+
+# A comma separated list of keywords related to warning whose presence should display the line in yellow
+# color in UI
+#
+# Variable: AIRFLOW__LOGGING__COLOR_LOG_WARNING_KEYWORDS
+#
+color_log_warning_keywords = warn
+
+[metrics]
+# `StatsD <https://github.com/statsd/statsd>`__ integration settings.
+
+# If true, ``[metrics] metrics_allow_list`` and ``[metrics] metrics_block_list`` will use
+# regex pattern matching anywhere within the metric name instead of only prefix matching
+# at the start of the name.
+#
+# Variable: AIRFLOW__METRICS__METRICS_USE_PATTERN_MATCH
+#
+metrics_use_pattern_match = False
+
+# Configure an allow list (comma separated string) to send only certain metrics.
+# If ``[metrics] metrics_use_pattern_match`` is ``false``, match only the exact metric name prefix.
+# If ``[metrics] metrics_use_pattern_match`` is ``true``, provide regex patterns to match.
+#
+# Example: metrics_allow_list = "scheduler,executor,dagrun,pool,triggerer,celery" or "^scheduler,^executor,heartbeat|timeout"
+#
+# Variable: AIRFLOW__METRICS__METRICS_ALLOW_LIST
+#
+metrics_allow_list = 
+
+# Configure a block list (comma separated string) to block certain metrics from being emitted.
+# If ``[metrics] metrics_allow_list`` and ``[metrics] metrics_block_list`` are both configured,
+# ``[metrics] metrics_block_list`` is ignored.
+# 
+# If ``[metrics] metrics_use_pattern_match`` is ``false``, match only the exact metric name prefix.
+# 
+# If ``[metrics] metrics_use_pattern_match`` is ``true``, provide regex patterns to match.
+#
+# Example: metrics_block_list = "scheduler,executor,dagrun,pool,triggerer,celery" or "^scheduler,^executor,heartbeat|timeout"
+#
+# Variable: AIRFLOW__METRICS__METRICS_BLOCK_LIST
+#
+metrics_block_list = 
+
+# Enables sending metrics to StatsD.
+#
+# Variable: AIRFLOW__METRICS__STATSD_ON
+#
+statsd_on = False
+
+# Specifies the host address where the StatsD daemon (or server) is running
+#
+# Variable: AIRFLOW__METRICS__STATSD_HOST
+#
+statsd_host = localhost
+
+# Specifies the port on which the StatsD daemon (or server) is listening to
+#
+# Variable: AIRFLOW__METRICS__STATSD_PORT
+#
+statsd_port = 8125
+
+# Defines the namespace for all metrics sent from Airflow to StatsD
+#
+# Variable: AIRFLOW__METRICS__STATSD_PREFIX
+#
+statsd_prefix = airflow
+
+# A function that validate the StatsD stat name, apply changes to the stat name if necessary and return
+# the transformed stat name.
+# 
+# The function should have the following signature
+# 
+# .. code-block:: python
+# 
+#     def func_name(stat_name: str) -> str: ...
+#
+# Variable: AIRFLOW__METRICS__STAT_NAME_HANDLER
+#
+stat_name_handler = 
+
+# To enable datadog integration to send airflow metrics.
+#
+# Variable: AIRFLOW__METRICS__STATSD_DATADOG_ENABLED
+#
+statsd_datadog_enabled = False
+
+# List of datadog tags attached to all metrics(e.g: ``key1:value1,key2:value2``)
+#
+# Variable: AIRFLOW__METRICS__STATSD_DATADOG_TAGS
+#
+statsd_datadog_tags = 
+
+# Set to ``False`` to disable metadata tags for some of the emitted metrics
+#
+# Variable: AIRFLOW__METRICS__STATSD_DATADOG_METRICS_TAGS
+#
+statsd_datadog_metrics_tags = True
+
+# If you want to utilise your own custom StatsD client set the relevant
+# module path below.
+# Note: The module path must exist on your
+# `PYTHONPATH <https://docs.python.org/3/using/cmdline.html#envvar-PYTHONPATH>`
+# for Airflow to pick it up
+#
+# Variable: AIRFLOW__METRICS__STATSD_CUSTOM_CLIENT_PATH
+#
+# statsd_custom_client_path = 
+
+# If you want to avoid sending all the available metrics tags to StatsD,
+# you can configure a block list of prefixes (comma separated) to filter out metric tags
+# that start with the elements of the list (e.g: ``job_id,run_id``)
+#
+# Example: statsd_disabled_tags = job_id,run_id,dag_id,task_id
+#
+# Variable: AIRFLOW__METRICS__STATSD_DISABLED_TAGS
+#
+statsd_disabled_tags = job_id,run_id
+
+# To enable sending Airflow metrics with StatsD-Influxdb tagging convention.
+#
+# Variable: AIRFLOW__METRICS__STATSD_INFLUXDB_ENABLED
+#
+statsd_influxdb_enabled = False
+
+# Enables sending metrics to OpenTelemetry.
+#
+# Variable: AIRFLOW__METRICS__OTEL_ON
+#
+otel_on = False
+
+# Specifies the hostname or IP address of the OpenTelemetry Collector to which Airflow sends
+# metrics and traces.
+#
+# Variable: AIRFLOW__METRICS__OTEL_HOST
+#
+otel_host = localhost
+
+# Specifies the port of the OpenTelemetry Collector that is listening to.
+#
+# Variable: AIRFLOW__METRICS__OTEL_PORT
+#
+otel_port = 8889
+
+# The prefix for the Airflow metrics.
+#
+# Variable: AIRFLOW__METRICS__OTEL_PREFIX
+#
+otel_prefix = airflow
+
+# Defines the interval, in milliseconds, at which Airflow sends batches of metrics and traces
+# to the configured OpenTelemetry Collector.
+#
+# Variable: AIRFLOW__METRICS__OTEL_INTERVAL_MILLISECONDS
+#
+otel_interval_milliseconds = 60000
+
+# If ``True``, all metrics are also emitted to the console. Defaults to ``False``.
+#
+# Variable: AIRFLOW__METRICS__OTEL_DEBUGGING_ON
+#
+otel_debugging_on = False
+
+# If ``True``, SSL will be enabled. Defaults to ``False``.
+# To establish an HTTPS connection to the OpenTelemetry collector,
+# you need to configure the SSL certificate and key within the OpenTelemetry collector's
+# ``config.yml`` file.
+#
+# Variable: AIRFLOW__METRICS__OTEL_SSL_ACTIVE
+#
+otel_ssl_active = False
+
+[traces]
+# Distributed traces integration settings.
+
+# Enables sending traces to OpenTelemetry.
+#
+# Variable: AIRFLOW__TRACES__OTEL_ON
+#
+otel_on = False
+
+# Specifies the hostname or IP address of the OpenTelemetry Collector to which Airflow sends
+# traces.
+#
+# Variable: AIRFLOW__TRACES__OTEL_HOST
+#
+otel_host = localhost
+
+# Specifies the port of the OpenTelemetry Collector that is listening to.
+#
+# Variable: AIRFLOW__TRACES__OTEL_PORT
+#
+otel_port = 8889
+
+# The default service name of traces.
+#
+# Variable: AIRFLOW__TRACES__OTEL_SERVICE
+#
+otel_service = Airflow
+
+# If True, all traces are also emitted to the console. Defaults to False.
+#
+# Variable: AIRFLOW__TRACES__OTEL_DEBUGGING_ON
+#
+otel_debugging_on = False
+
+# If True, SSL will be enabled.  Defaults to False.
+# To establish an HTTPS connection to the OpenTelemetry collector,
+# you need to configure the SSL certificate and key within the OpenTelemetry collector's
+# config.yml file.
+#
+# Variable: AIRFLOW__TRACES__OTEL_SSL_ACTIVE
+#
+otel_ssl_active = False
+
+# If True, after the task is complete, the full task log messages will be added as the
+# span events, chunked by 64k size. defaults to False.
+#
+# Variable: AIRFLOW__TRACES__OTEL_TASK_LOG_EVENT
+#
+otel_task_log_event = False
+
+[secrets]
+# Full class name of secrets backend to enable (will precede env vars and metastore in search path)
+#
+# Example: backend = airflow.providers.amazon.aws.secrets.systems_manager.SystemsManagerParameterStoreBackend
+#
+# Variable: AIRFLOW__SECRETS__BACKEND
+#
+backend = 
+
+# The backend_kwargs param is loaded into a dictionary and passed to ``__init__``
+# of secrets backend class. See documentation for the secrets backend you are using.
+# JSON is expected.
+# 
+# Example for AWS Systems Manager ParameterStore:
+# ``{"connections_prefix": "/airflow/connections", "profile_name": "default"}``
+#
+# Variable: AIRFLOW__SECRETS__BACKEND_KWARGS
+#
+backend_kwargs = 
+
+# .. note:: |experimental|
+# 
+# Enables local caching of Variables, when parsing DAGs only.
+# Using this option can make dag parsing faster if Variables are used in top level code, at the expense
+# of longer propagation time for changes.
+# Please note that this cache concerns only the DAG parsing step. There is no caching in place when DAG
+# tasks are run.
+#
+# Variable: AIRFLOW__SECRETS__USE_CACHE
+#
+use_cache = False
+
+# .. note:: |experimental|
+# 
+# When the cache is enabled, this is the duration for which we consider an entry in the cache to be
+# valid. Entries are refreshed if they are older than this many seconds.
+# It means that when the cache is enabled, this is the maximum amount of time you need to wait to see a
+# Variable change take effect.
+#
+# Variable: AIRFLOW__SECRETS__CACHE_TTL_SECONDS
+#
+cache_ttl_seconds = 900
+
+[cli]
+# In what way should the cli access the API. The LocalClient will use the
+# database directly, while the json_client will use the api running on the
+# webserver
+#
+# Variable: AIRFLOW__CLI__API_CLIENT
+#
+api_client = airflow.api.client.local_client
+
+# If you set web_server_url_prefix, do NOT forget to append it here, ex:
+# ``endpoint_url = http://localhost:8080/myroot``
+# So api will look like: ``http://localhost:8080/myroot/api/experimental/...``
+#
+# Variable: AIRFLOW__CLI__ENDPOINT_URL
+#
+endpoint_url = http://localhost:8080
+
+[debug]
+# Used only with ``DebugExecutor``. If set to ``True`` DAG will fail with first
+# failed task. Helpful for debugging purposes.
+#
+# Variable: AIRFLOW__DEBUG__FAIL_FAST
+#
+fail_fast = False
+
+[api]
+# Enables the deprecated experimental API. Please note that these API endpoints do not have
+# access control. An authenticated user has full access.
+# 
+# .. warning::
+# 
+#   This `Experimental REST API
+#   <https://airflow.apache.org/docs/apache-airflow/stable/deprecated-rest-api-ref.html>`__ is
+#   deprecated since version 2.0. Please consider using
+#   `the Stable REST API
+#   <https://airflow.apache.org/docs/apache-airflow/stable/stable-rest-api-ref.html>`__.
+#   For more information on migration, see
+#   `RELEASE_NOTES.rst <https://github.com/apache/airflow/blob/main/RELEASE_NOTES.rst>`_
+#
+# Variable: AIRFLOW__API__ENABLE_EXPERIMENTAL_API
+#
+enable_experimental_api = False
+
+# Comma separated list of auth backends to authenticate users of the API. See
+# `Security: API
+# <https://airflow.apache.org/docs/apache-airflow/stable/security/api.html>`__ for possible values.
+# ("airflow.api.auth.backend.default" allows all requests for historic reasons)
+#
+# Variable: AIRFLOW__API__AUTH_BACKENDS
+#
+auth_backends = airflow.api.auth.backend.session
+
+# Used to set the maximum page limit for API requests. If limit passed as param
+# is greater than maximum page limit, it will be ignored and maximum page limit value
+# will be set as the limit
+#
+# Variable: AIRFLOW__API__MAXIMUM_PAGE_LIMIT
+#
+maximum_page_limit = 100
+
+# Used to set the default page limit when limit param is zero or not provided in API
+# requests. Otherwise if positive integer is passed in the API requests as limit, the
+# smallest number of user given limit or maximum page limit is taken as limit.
+#
+# Variable: AIRFLOW__API__FALLBACK_PAGE_LIMIT
+#
+fallback_page_limit = 100
+
+# The intended audience for JWT token credentials used for authorization. This value must match on the client and server sides. If empty, audience will not be tested.
+#
+# Example: google_oauth2_audience = project-id-random-value.apps.googleusercontent.com
+#
+# Variable: AIRFLOW__API__GOOGLE_OAUTH2_AUDIENCE
+#
+google_oauth2_audience = 
+
+# Path to Google Cloud Service Account key file (JSON). If omitted, authorization based on
+# `the Application Default Credentials
+# <https://cloud.google.com/docs/authentication/production#finding_credentials_automatically>`__ will
+# be used.
+#
+# Example: google_key_path = /files/service-account-json
+#
+# Variable: AIRFLOW__API__GOOGLE_KEY_PATH
+#
+google_key_path = 
+
+# Used in response to a preflight request to indicate which HTTP
+# headers can be used when making the actual request. This header is
+# the server side response to the browser's
+# Access-Control-Request-Headers header.
+#
+# Variable: AIRFLOW__API__ACCESS_CONTROL_ALLOW_HEADERS
+#
+access_control_allow_headers = 
+
+# Specifies the method or methods allowed when accessing the resource.
+#
+# Variable: AIRFLOW__API__ACCESS_CONTROL_ALLOW_METHODS
+#
+access_control_allow_methods = 
+
+# Indicates whether the response can be shared with requesting code from the given origins.
+# Separate URLs with space.
+#
+# Variable: AIRFLOW__API__ACCESS_CONTROL_ALLOW_ORIGINS
+#
+access_control_allow_origins = 
+
+# Indicates whether the **xcomEntries** endpoint supports the **deserialize**
+# flag. If set to ``False``, setting this flag in a request would result in a
+# 400 Bad Request error.
+#
+# Variable: AIRFLOW__API__ENABLE_XCOM_DESERIALIZE_SUPPORT
+#
+enable_xcom_deserialize_support = False
+
+[lineage]
+# what lineage backend to use
+#
+# Variable: AIRFLOW__LINEAGE__BACKEND
+#
+backend = 
+
+[operators]
+# The default owner assigned to each new operator, unless
+# provided explicitly or passed via ``default_args``
+#
+# Variable: AIRFLOW__OPERATORS__DEFAULT_OWNER
+#
+default_owner = airflow
+
+# The default value of attribute "deferrable" in operators and sensors.
+#
+# Variable: AIRFLOW__OPERATORS__DEFAULT_DEFERRABLE
+#
+default_deferrable = false
+
+# Indicates the default number of CPU units allocated to each operator when no specific CPU request
+# is specified in the operator's configuration
+#
+# Variable: AIRFLOW__OPERATORS__DEFAULT_CPUS
+#
+default_cpus = 1
+
+# Indicates the default number of RAM allocated to each operator when no specific RAM request
+# is specified in the operator's configuration
+#
+# Variable: AIRFLOW__OPERATORS__DEFAULT_RAM
+#
+default_ram = 512
+
+# Indicates the default number of disk storage allocated to each operator when no specific disk request
+# is specified in the operator's configuration
+#
+# Variable: AIRFLOW__OPERATORS__DEFAULT_DISK
+#
+default_disk = 512
+
+# Indicates the default number of GPUs allocated to each operator when no specific GPUs request
+# is specified in the operator's configuration
+#
+# Variable: AIRFLOW__OPERATORS__DEFAULT_GPUS
+#
+default_gpus = 0
+
+# Default queue that tasks get assigned to and that worker listen on.
+#
+# Variable: AIRFLOW__OPERATORS__DEFAULT_QUEUE
+#
+default_queue = default
+
+# Is allowed to pass additional/unused arguments (args, kwargs) to the BaseOperator operator.
+# If set to ``False``, an exception will be thrown,
+# otherwise only the console message will be displayed.
+#
+# Variable: AIRFLOW__OPERATORS__ALLOW_ILLEGAL_ARGUMENTS
+#
+allow_illegal_arguments = False
+
+[webserver]
+# The message displayed when a user attempts to execute actions beyond their authorised privileges.
+#
+# Variable: AIRFLOW__WEBSERVER__ACCESS_DENIED_MESSAGE
+#
+access_denied_message = Access is Denied
+
+# Path of webserver config file used for configuring the webserver parameters
+#
+# Variable: AIRFLOW__WEBSERVER__CONFIG_FILE
+#
+config_file = /opt/airflow/webserver_config.py
+
+# The base url of your website: Airflow cannot guess what domain or CNAME you are using.
+# This is used to create links in the Log Url column in the Browse - Task Instances menu,
+# as well as in any automated emails sent by Airflow that contain links to your webserver.
+#
+# Variable: AIRFLOW__WEBSERVER__BASE_URL
+#
+base_url = http://localhost:8080
+
+# Default timezone to display all dates in the UI, can be UTC, system, or
+# any IANA timezone string (e.g. **Europe/Amsterdam**). If left empty the
+# default value of core/default_timezone will be used
+#
+# Example: default_ui_timezone = America/New_York
+#
+# Variable: AIRFLOW__WEBSERVER__DEFAULT_UI_TIMEZONE
+#
+default_ui_timezone = UTC
+
+# The ip specified when starting the web server
+#
+# Variable: AIRFLOW__WEBSERVER__WEB_SERVER_HOST
+#
+web_server_host = 0.0.0.0
+
+# The port on which to run the web server
+#
+# Variable: AIRFLOW__WEBSERVER__WEB_SERVER_PORT
+#
+web_server_port = 8080
+
+# Paths to the SSL certificate and key for the web server. When both are
+# provided SSL will be enabled. This does not change the web server port.
+#
+# Variable: AIRFLOW__WEBSERVER__WEB_SERVER_SSL_CERT
+#
+web_server_ssl_cert = 
+
+# Paths to the SSL certificate and key for the web server. When both are
+# provided SSL will be enabled. This does not change the web server port.
+#
+# Variable: AIRFLOW__WEBSERVER__WEB_SERVER_SSL_KEY
+#
+web_server_ssl_key = 
+
+# The type of backend used to store web session data, can be ``database`` or ``securecookie``. For the
+# ``database`` backend, sessions are store in the database and they can be
+# managed there (for example when you reset password of the user, all sessions for that user are
+# deleted). For the ``securecookie`` backend, sessions are stored in encrypted cookies on the client
+# side. The ``securecookie`` mechanism is 'lighter' than database backend, but sessions are not deleted
+# when you reset password of the user, which means that other than waiting for expiry time, the only
+# way to invalidate all sessions for a user is to change secret_key and restart webserver (which
+# also invalidates and logs out all other user's sessions).
+# 
+# When you are using ``database`` backend, make sure to keep your database session table small
+# by periodically running ``airflow db clean --table session`` command, especially if you have
+# automated API calls that will create a new session for each call rather than reuse the sessions
+# stored in browser cookies.
+#
+# Example: session_backend = securecookie
+#
+# Variable: AIRFLOW__WEBSERVER__SESSION_BACKEND
+#
+session_backend = database
+
+# Number of seconds the webserver waits before killing gunicorn master that doesn't respond
+#
+# Variable: AIRFLOW__WEBSERVER__WEB_SERVER_MASTER_TIMEOUT
+#
+web_server_master_timeout = 120
+
+# Number of seconds the gunicorn webserver waits before timing out on a worker
+#
+# Variable: AIRFLOW__WEBSERVER__WEB_SERVER_WORKER_TIMEOUT
+#
+web_server_worker_timeout = 120
+
+# Number of workers to refresh at a time. When set to 0, worker refresh is
+# disabled. When nonzero, airflow periodically refreshes webserver workers by
+# bringing up new ones and killing old ones.
+#
+# Variable: AIRFLOW__WEBSERVER__WORKER_REFRESH_BATCH_SIZE
+#
+worker_refresh_batch_size = 1
+
+# Number of seconds to wait before refreshing a batch of workers.
+#
+# Variable: AIRFLOW__WEBSERVER__WORKER_REFRESH_INTERVAL
+#
+worker_refresh_interval = 6000
+
+# If set to ``True``, Airflow will track files in plugins_folder directory. When it detects changes,
+# then reload the gunicorn. If set to ``True``, gunicorn starts without preloading, which is slower,
+# uses more memory, and may cause race conditions. Avoid setting this to ``True`` in production.
+#
+# Variable: AIRFLOW__WEBSERVER__RELOAD_ON_PLUGIN_CHANGE
+#
+reload_on_plugin_change = False
+
+# Secret key used to run your flask app. It should be as random as possible. However, when running
+# more than 1 instances of webserver, make sure all of them use the same ``secret_key`` otherwise
+# one of them will error with "CSRF session token is missing".
+# The webserver key is also used to authorize requests to Celery workers when logs are retrieved.
+# The token generated using the secret key has a short expiry time though - make sure that time on
+# ALL the machines that you run airflow components on is synchronized (for example using ntpd)
+# otherwise you might get "forbidden" errors when the logs are accessed.
+#
+# Variable: AIRFLOW__WEBSERVER__SECRET_KEY
+#
+secret_key = pDBrar+Nyodn8Sf5ZeJfVw==
+
+# Number of workers to run the Gunicorn web server
+#
+# Variable: AIRFLOW__WEBSERVER__WORKERS
+#
+workers = 4
+
+# The worker class gunicorn should use. Choices include
+# ``sync`` (default), ``eventlet``, ``gevent``.
+# 
+# .. warning::
+# 
+#     When using ``gevent`` you might also want to set the ``_AIRFLOW_PATCH_GEVENT``
+#     environment variable to ``"1"`` to make sure gevent patching is done as early as possible.
+# 
+#     Be careful to set ``_AIRFLOW_PATCH_GEVENT`` only on the web server as gevent patching may
+#     affect the scheduler behavior via the ``multiprocessing`` sockets module and cause crash.
+# 
+#     See related Issues / PRs for more details:
+# 
+#     * https://github.com/benoitc/gunicorn/issues/2796
+#     * https://github.com/apache/airflow/issues/8212
+#     * https://github.com/apache/airflow/pull/28283
+#
+# Variable: AIRFLOW__WEBSERVER__WORKER_CLASS
+#
+worker_class = sync
+
+# Log files for the gunicorn webserver. '-' means log to stderr.
+#
+# Variable: AIRFLOW__WEBSERVER__ACCESS_LOGFILE
+#
+access_logfile = -
+
+# Log files for the gunicorn webserver. '-' means log to stderr.
+#
+# Variable: AIRFLOW__WEBSERVER__ERROR_LOGFILE
+#
+error_logfile = -
+
+# Access log format for gunicorn webserver.
+# default format is ``%%(h)s %%(l)s %%(u)s %%(t)s "%%(r)s" %%(s)s %%(b)s "%%(f)s" "%%(a)s"``
+# See `Gunicorn Settings: 'access_log_format' Reference
+# <https://docs.gunicorn.org/en/stable/settings.html#access-log-format>`__ for more details
+#
+# Variable: AIRFLOW__WEBSERVER__ACCESS_LOGFORMAT
+#
+access_logformat = 
+
+# Expose the configuration file in the web server. Set to ``non-sensitive-only`` to show all values
+# except those that have security implications. ``True`` shows all values. ``False`` hides the
+# configuration completely.
+#
+# Variable: AIRFLOW__WEBSERVER__EXPOSE_CONFIG
+#
+expose_config = False
+
+# Expose hostname in the web server
+#
+# Variable: AIRFLOW__WEBSERVER__EXPOSE_HOSTNAME
+#
+expose_hostname = False
+
+# Expose stacktrace in the web server
+#
+# Variable: AIRFLOW__WEBSERVER__EXPOSE_STACKTRACE
+#
+expose_stacktrace = False
+
+# Default DAG view. Valid values are: ``grid``, ``graph``, ``duration``, ``gantt``, ``landing_times``
+#
+# Variable: AIRFLOW__WEBSERVER__DAG_DEFAULT_VIEW
+#
+dag_default_view = grid
+
+# Default DAG orientation. Valid values are:
+# ``LR`` (Left->Right), ``TB`` (Top->Bottom), ``RL`` (Right->Left), ``BT`` (Bottom->Top)
+#
+# Variable: AIRFLOW__WEBSERVER__DAG_ORIENTATION
+#
+dag_orientation = LR
+
+# Sorting order in grid view. Valid values are: ``topological``, ``hierarchical_alphabetical``
+#
+# Variable: AIRFLOW__WEBSERVER__GRID_VIEW_SORTING_ORDER
+#
+grid_view_sorting_order = topological
+
+# The amount of time (in secs) webserver will wait for initial handshake
+# while fetching logs from other worker machine
+#
+# Variable: AIRFLOW__WEBSERVER__LOG_FETCH_TIMEOUT_SEC
+#
+log_fetch_timeout_sec = 5
+
+# Time interval (in secs) to wait before next log fetching.
+#
+# Variable: AIRFLOW__WEBSERVER__LOG_FETCH_DELAY_SEC
+#
+log_fetch_delay_sec = 2
+
+# Distance away from page bottom to enable auto tailing.
+#
+# Variable: AIRFLOW__WEBSERVER__LOG_AUTO_TAILING_OFFSET
+#
+log_auto_tailing_offset = 30
+
+# Animation speed for auto tailing log display.
+#
+# Variable: AIRFLOW__WEBSERVER__LOG_ANIMATION_SPEED
+#
+log_animation_speed = 1000
+
+# By default, the webserver shows paused DAGs. Flip this to hide paused
+# DAGs by default
+#
+# Variable: AIRFLOW__WEBSERVER__HIDE_PAUSED_DAGS_BY_DEFAULT
+#
+hide_paused_dags_by_default = False
+
+# Consistent page size across all listing views in the UI
+#
+# Variable: AIRFLOW__WEBSERVER__PAGE_SIZE
+#
+page_size = 100
+
+# Define the color of navigation bar
+#
+# Variable: AIRFLOW__WEBSERVER__NAVBAR_COLOR
+#
+navbar_color = #fff
+
+# Define the color of text in the navigation bar
+#
+# Variable: AIRFLOW__WEBSERVER__NAVBAR_TEXT_COLOR
+#
+navbar_text_color = #51504f
+
+# Define the color of navigation bar links when hovered
+#
+# Variable: AIRFLOW__WEBSERVER__NAVBAR_HOVER_COLOR
+#
+navbar_hover_color = #eee
+
+# Define the color of text in the navigation bar when hovered
+#
+# Variable: AIRFLOW__WEBSERVER__NAVBAR_TEXT_HOVER_COLOR
+#
+navbar_text_hover_color = #51504f
+
+# Define the color of the logo text
+#
+# Variable: AIRFLOW__WEBSERVER__NAVBAR_LOGO_TEXT_COLOR
+#
+navbar_logo_text_color = #51504f
+
+# Default dagrun to show in UI
+#
+# Variable: AIRFLOW__WEBSERVER__DEFAULT_DAG_RUN_DISPLAY_NUMBER
+#
+default_dag_run_display_number = 25
+
+# Enable werkzeug ``ProxyFix`` middleware for reverse proxy
+#
+# Variable: AIRFLOW__WEBSERVER__ENABLE_PROXY_FIX
+#
+enable_proxy_fix = False
+
+# Number of values to trust for ``X-Forwarded-For``.
+# See `Werkzeug: X-Forwarded-For Proxy Fix
+# <https://werkzeug.palletsprojects.com/en/2.3.x/middleware/proxy_fix/>`__ for more details.
+#
+# Variable: AIRFLOW__WEBSERVER__PROXY_FIX_X_FOR
+#
+proxy_fix_x_for = 1
+
+# Number of values to trust for ``X-Forwarded-Proto``.
+# See `Werkzeug: X-Forwarded-For Proxy Fix
+# <https://werkzeug.palletsprojects.com/en/2.3.x/middleware/proxy_fix/>`__ for more details.
+#
+# Variable: AIRFLOW__WEBSERVER__PROXY_FIX_X_PROTO
+#
+proxy_fix_x_proto = 1
+
+# Number of values to trust for ``X-Forwarded-Host``.
+# See `Werkzeug: X-Forwarded-For Proxy Fix
+# <https://werkzeug.palletsprojects.com/en/2.3.x/middleware/proxy_fix/>`__ for more details.
+#
+# Variable: AIRFLOW__WEBSERVER__PROXY_FIX_X_HOST
+#
+proxy_fix_x_host = 1
+
+# Number of values to trust for ``X-Forwarded-Port``.
+# See `Werkzeug: X-Forwarded-For Proxy Fix
+# <https://werkzeug.palletsprojects.com/en/2.3.x/middleware/proxy_fix/>`__ for more details.
+#
+# Variable: AIRFLOW__WEBSERVER__PROXY_FIX_X_PORT
+#
+proxy_fix_x_port = 1
+
+# Number of values to trust for ``X-Forwarded-Prefix``.
+# See `Werkzeug: X-Forwarded-For Proxy Fix
+# <https://werkzeug.palletsprojects.com/en/2.3.x/middleware/proxy_fix/>`__ for more details.
+#
+# Variable: AIRFLOW__WEBSERVER__PROXY_FIX_X_PREFIX
+#
+proxy_fix_x_prefix = 1
+
+# Set secure flag on session cookie
+#
+# Variable: AIRFLOW__WEBSERVER__COOKIE_SECURE
+#
+cookie_secure = False
+
+# Set samesite policy on session cookie
+#
+# Variable: AIRFLOW__WEBSERVER__COOKIE_SAMESITE
+#
+cookie_samesite = Lax
+
+# Default setting for wrap toggle on DAG code and TI log views.
+#
+# Variable: AIRFLOW__WEBSERVER__DEFAULT_WRAP
+#
+default_wrap = False
+
+# Allow the UI to be rendered in a frame
+#
+# Variable: AIRFLOW__WEBSERVER__X_FRAME_ENABLED
+#
+x_frame_enabled = True
+
+# Send anonymous user activity to your analytics tool
+# choose from ``google_analytics``, ``segment``, ``metarouter``, or ``matomo``
+#
+# Variable: AIRFLOW__WEBSERVER__ANALYTICS_TOOL
+#
+# analytics_tool = 
+
+# Unique ID of your account in the analytics tool
+#
+# Variable: AIRFLOW__WEBSERVER__ANALYTICS_ID
+#
+# analytics_id = 
+
+# Your instances url, only applicable to Matomo.
+#
+# Example: analytics_url = https://your.matomo.instance.com/
+#
+# Variable: AIRFLOW__WEBSERVER__ANALYTICS_URL
+#
+# analytics_url = 
+
+# 'Recent Tasks' stats will show for old DagRuns if set
+#
+# Variable: AIRFLOW__WEBSERVER__SHOW_RECENT_STATS_FOR_COMPLETED_RUNS
+#
+show_recent_stats_for_completed_runs = True
+
+# The UI cookie lifetime in minutes. User will be logged out from UI after
+# ``[webserver] session_lifetime_minutes`` of non-activity
+#
+# Variable: AIRFLOW__WEBSERVER__SESSION_LIFETIME_MINUTES
+#
+session_lifetime_minutes = 43200
+
+# Sets a custom page title for the DAGs overview page and site title for all pages
+#
+# Variable: AIRFLOW__WEBSERVER__INSTANCE_NAME
+#
+# instance_name = 
+
+# Whether the custom page title for the DAGs overview page contains any Markup language
+#
+# Variable: AIRFLOW__WEBSERVER__INSTANCE_NAME_HAS_MARKUP
+#
+instance_name_has_markup = False
+
+# How frequently, in seconds, the DAG data will auto-refresh in graph or grid view
+# when auto-refresh is turned on
+#
+# Variable: AIRFLOW__WEBSERVER__AUTO_REFRESH_INTERVAL
+#
+auto_refresh_interval = 3
+
+# Boolean for displaying warning for publicly viewable deployment
+#
+# Variable: AIRFLOW__WEBSERVER__WARN_DEPLOYMENT_EXPOSURE
+#
+warn_deployment_exposure = True
+
+# Comma separated string of view events to exclude from dag audit view.
+# All other events will be added minus the ones passed here.
+# The audit logs in the db will not be affected by this parameter.
+#
+# Example: audit_view_excluded_events = cli_task_run,running,success
+#
+# Variable: AIRFLOW__WEBSERVER__AUDIT_VIEW_EXCLUDED_EVENTS
+#
+# audit_view_excluded_events = 
+
+# Comma separated string of view events to include in dag audit view.
+# If passed, only these events will populate the dag audit view.
+# The audit logs in the db will not be affected by this parameter.
+#
+# Example: audit_view_included_events = dagrun_cleared,failed
+#
+# Variable: AIRFLOW__WEBSERVER__AUDIT_VIEW_INCLUDED_EVENTS
+#
+# audit_view_included_events = 
+
+# Boolean for running SwaggerUI in the webserver.
+#
+# Variable: AIRFLOW__WEBSERVER__ENABLE_SWAGGER_UI
+#
+enable_swagger_ui = True
+
+# Boolean for running Internal API in the webserver.
+#
+# Variable: AIRFLOW__WEBSERVER__RUN_INTERNAL_API
+#
+run_internal_api = False
+
+# The caching algorithm used by the webserver. Must be a valid hashlib function name.
+#
+# Example: caching_hash_method = sha256
+#
+# Variable: AIRFLOW__WEBSERVER__CACHING_HASH_METHOD
+#
+caching_hash_method = md5
+
+# Behavior of the trigger DAG run button for DAGs without params. ``False`` to skip and trigger
+# without displaying a form to add a **dag_run.conf**, ``True`` to always display the form.
+# The form is displayed always if parameters are defined.
+#
+# Variable: AIRFLOW__WEBSERVER__SHOW_TRIGGER_FORM_IF_NO_PARAMS
+#
+show_trigger_form_if_no_params = False
+
+# Number of recent DAG run configurations in the selector on the trigger web form.
+#
+# Example: num_recent_configurations_for_trigger = 10
+#
+# Variable: AIRFLOW__WEBSERVER__NUM_RECENT_CONFIGURATIONS_FOR_TRIGGER
+#
+num_recent_configurations_for_trigger = 5
+
+# A DAG author is able to provide any raw HTML into ``doc_md`` or params description in
+# ``description_md`` for text formatting. This is including potentially unsafe javascript.
+# Displaying the DAG or trigger form in web UI provides the DAG author the potential to
+# inject malicious code into clients browsers. To ensure the web UI is safe by default,
+# raw HTML is disabled by default. If you trust your DAG authors, you can enable HTML
+# support in markdown by setting this option to ``True``.
+# 
+# This parameter also enables the deprecated fields ``description_html`` and
+# ``custom_html_form`` in DAG params until the feature is removed in a future version.
+#
+# Example: allow_raw_html_descriptions = False
+#
+# Variable: AIRFLOW__WEBSERVER__ALLOW_RAW_HTML_DESCRIPTIONS
+#
+allow_raw_html_descriptions = False
+
+# The maximum size of the request payload (in MB) that can be sent.
+#
+# Variable: AIRFLOW__WEBSERVER__ALLOWED_PAYLOAD_SIZE
+#
+allowed_payload_size = 1.0
+
+# Require confirmation when changing a DAG in the web UI. This is to prevent accidental changes
+# to a DAG that may be running on sensitive environments like production.
+# When set to ``True``, confirmation dialog will be shown when a user tries to Pause/Unpause,
+# Trigger a DAG
+#
+# Variable: AIRFLOW__WEBSERVER__REQUIRE_CONFIRMATION_DAG_CHANGE
+#
+require_confirmation_dag_change = False
+
+[email]
+# Configuration email backend and whether to
+# send email alerts on retry or failure
+
+# Email backend to use
+#
+# Variable: AIRFLOW__EMAIL__EMAIL_BACKEND
+#
+email_backend = airflow.utils.email.send_email_smtp
+
+# Email connection to use
+#
+# Variable: AIRFLOW__EMAIL__EMAIL_CONN_ID
+#
+email_conn_id = smtp_default
+
+# Whether email alerts should be sent when a task is retried
+#
+# Variable: AIRFLOW__EMAIL__DEFAULT_EMAIL_ON_RETRY
+#
+default_email_on_retry = True
+
+# Whether email alerts should be sent when a task failed
+#
+# Variable: AIRFLOW__EMAIL__DEFAULT_EMAIL_ON_FAILURE
+#
+default_email_on_failure = True
+
+# File that will be used as the template for Email subject (which will be rendered using Jinja2).
+# If not set, Airflow uses a base template.
+#
+# Example: subject_template = /path/to/my_subject_template_file
+#
+# Variable: AIRFLOW__EMAIL__SUBJECT_TEMPLATE
+#
+# subject_template = 
+
+# File that will be used as the template for Email content (which will be rendered using Jinja2).
+# If not set, Airflow uses a base template.
+#
+# Example: html_content_template = /path/to/my_html_content_template_file
+#
+# Variable: AIRFLOW__EMAIL__HTML_CONTENT_TEMPLATE
+#
+# html_content_template = 
+
+# Email address that will be used as sender address.
+# It can either be raw email or the complete address in a format ``Sender Name <[email protected]>``
+#
+# Example: from_email = Airflow <[email protected]>
+#
+# Variable: AIRFLOW__EMAIL__FROM_EMAIL
+#
+# from_email = 
+
+# ssl context to use when using SMTP and IMAP SSL connections. By default, the context is "default"
+# which sets it to ``ssl.create_default_context()`` which provides the right balance between
+# compatibility and security, it however requires that certificates in your operating system are
+# updated and that SMTP/IMAP servers of yours have valid certificates that have corresponding public
+# keys installed on your machines. You can switch it to "none" if you want to disable checking
+# of the certificates, but it is not recommended as it allows MITM (man-in-the-middle) attacks
+# if your infrastructure is not sufficiently secured. It should only be set temporarily while you
+# are fixing your certificate configuration. This can be typically done by upgrading to newer
+# version of the operating system you run Airflow components on,by upgrading/refreshing proper
+# certificates in the OS or by updating certificates for your mail servers.
+#
+# Example: ssl_context = default
+#
+# Variable: AIRFLOW__EMAIL__SSL_CONTEXT
+#
+ssl_context = default
+
+[smtp]
+# If you want airflow to send emails on retries, failure, and you want to use
+# the airflow.utils.email.send_email_smtp function, you have to configure an
+# smtp server here
+
+# Specifies the host server address used by Airflow when sending out email notifications via SMTP.
+#
+# Variable: AIRFLOW__SMTP__SMTP_HOST
+#
+smtp_host = localhost
+
+# Determines whether to use the STARTTLS command when connecting to the SMTP server.
+#
+# Variable: AIRFLOW__SMTP__SMTP_STARTTLS
+#
+smtp_starttls = True
+
+# Determines whether to use an SSL connection when talking to the SMTP server.
+#
+# Variable: AIRFLOW__SMTP__SMTP_SSL
+#
+smtp_ssl = False
+
+# Username to authenticate when connecting to smtp server.
+#
+# Example: smtp_user = airflow
+#
+# Variable: AIRFLOW__SMTP__SMTP_USER
+#
+# smtp_user = 
+
+# Password to authenticate when connecting to smtp server.
+#
+# Example: smtp_password = airflow
+#
+# Variable: AIRFLOW__SMTP__SMTP_PASSWORD
+#
+# smtp_password = 
+
+# Defines the port number on which Airflow connects to the SMTP server to send email notifications.
+#
+# Variable: AIRFLOW__SMTP__SMTP_PORT
+#
+smtp_port = 25
+
+# Specifies the default **from** email address used when Airflow sends email notifications.
+#
+# Variable: AIRFLOW__SMTP__SMTP_MAIL_FROM
+#
+smtp_mail_from = [email protected]
+
+# Determines the maximum time (in seconds) the Apache Airflow system will wait for a
+# connection to the SMTP server to be established.
+#
+# Variable: AIRFLOW__SMTP__SMTP_TIMEOUT
+#
+smtp_timeout = 30
+
+# Defines the maximum number of times Airflow will attempt to connect to the SMTP server.
+#
+# Variable: AIRFLOW__SMTP__SMTP_RETRY_LIMIT
+#
+smtp_retry_limit = 5
+
+[sentry]
+# `Sentry <https://docs.sentry.io>`__ integration. Here you can supply
+# additional configuration options based on the Python platform.
+# See `Python / Configuration / Basic Options
+# <https://docs.sentry.io/platforms/python/configuration/options/>`__ for more details.
+# Unsupported options: ``integrations``, ``in_app_include``, ``in_app_exclude``,
+# ``ignore_errors``, ``before_breadcrumb``, ``transport``.
+
+# Enable error reporting to Sentry
+#
+# Variable: AIRFLOW__SENTRY__SENTRY_ON
+#
+sentry_on = false
+
+#
+# Variable: AIRFLOW__SENTRY__SENTRY_DSN
+#
+sentry_dsn = 
+
+# Dotted path to a before_send function that the sentry SDK should be configured to use.
+#
+# Variable: AIRFLOW__SENTRY__BEFORE_SEND
+#
+# before_send = 
+
+[scheduler]
+# Task instances listen for external kill signal (when you clear tasks
+# from the CLI or the UI), this defines the frequency at which they should
+# listen (in seconds).
+#
+# Variable: AIRFLOW__SCHEDULER__JOB_HEARTBEAT_SEC
+#
+job_heartbeat_sec = 5
+
+# The scheduler constantly tries to trigger new tasks (look at the
+# scheduler section in the docs for more information). This defines
+# how often the scheduler should run (in seconds).
+#
+# Variable: AIRFLOW__SCHEDULER__SCHEDULER_HEARTBEAT_SEC
+#
+scheduler_heartbeat_sec = 5
+
+# The frequency (in seconds) at which the LocalTaskJob should send heartbeat signals to the
+# scheduler to notify it's still alive. If this value is set to 0, the heartbeat interval will default
+# to the value of ``[scheduler] scheduler_zombie_task_threshold``.
+#
+# Variable: AIRFLOW__SCHEDULER__LOCAL_TASK_JOB_HEARTBEAT_SEC
+#
+local_task_job_heartbeat_sec = 0
+
+# The number of times to try to schedule each DAG file
+# -1 indicates unlimited number
+#
+# Variable: AIRFLOW__SCHEDULER__NUM_RUNS
+#
+num_runs = -1
+
+# Controls how long the scheduler will sleep between loops, but if there was nothing to do
+# in the loop. i.e. if it scheduled something then it will start the next loop
+# iteration straight away.
+#
+# Variable: AIRFLOW__SCHEDULER__SCHEDULER_IDLE_SLEEP_TIME
+#
+scheduler_idle_sleep_time = 1
+
+# Number of seconds after which a DAG file is parsed. The DAG file is parsed every
+# ``[scheduler] min_file_process_interval`` number of seconds. Updates to DAGs are reflected after
+# this interval. Keeping this number low will increase CPU usage.
+#
+# Variable: AIRFLOW__SCHEDULER__MIN_FILE_PROCESS_INTERVAL
+#
+min_file_process_interval = 30
+
+# How often (in seconds) to check for stale DAGs (DAGs which are no longer present in
+# the expected files) which should be deactivated, as well as datasets that are no longer
+# referenced and should be marked as orphaned.
+#
+# Variable: AIRFLOW__SCHEDULER__PARSING_CLEANUP_INTERVAL
+#
+parsing_cleanup_interval = 60
+
+# How long (in seconds) to wait after we have re-parsed a DAG file before deactivating stale
+# DAGs (DAGs which are no longer present in the expected files). The reason why we need
+# this threshold is to account for the time between when the file is parsed and when the
+# DAG is loaded. The absolute maximum that this could take is ``[core] dag_file_processor_timeout``,
+# but when you have a long timeout configured, it results in a significant delay in the
+# deactivation of stale dags.
+#
+# Variable: AIRFLOW__SCHEDULER__STALE_DAG_THRESHOLD
+#
+stale_dag_threshold = 50
+
+# How often (in seconds) to scan the DAGs directory for new files. Default to 5 minutes.
+#
+# Variable: AIRFLOW__SCHEDULER__DAG_DIR_LIST_INTERVAL
+#
+dag_dir_list_interval = 300
+
+# How often should stats be printed to the logs. Setting to 0 will disable printing stats
+#
+# Variable: AIRFLOW__SCHEDULER__PRINT_STATS_INTERVAL
+#
+print_stats_interval = 30
+
+# How often (in seconds) should pool usage stats be sent to StatsD (if statsd_on is enabled)
+#
+# Variable: AIRFLOW__SCHEDULER__POOL_METRICS_INTERVAL
+#
+pool_metrics_interval = 5.0
+
+# If the last scheduler heartbeat happened more than ``[scheduler] scheduler_health_check_threshold``
+# ago (in seconds), scheduler is considered unhealthy.
+# This is used by the health check in the **/health** endpoint and in ``airflow jobs check`` CLI
+# for SchedulerJob.
+#
+# Variable: AIRFLOW__SCHEDULER__SCHEDULER_HEALTH_CHECK_THRESHOLD
+#
+scheduler_health_check_threshold = 30
+
+# When you start a scheduler, airflow starts a tiny web server
+# subprocess to serve a health check if this is set to ``True``
+#
+# Variable: AIRFLOW__SCHEDULER__ENABLE_HEALTH_CHECK
+#
+enable_health_check = False
+
+# When you start a scheduler, airflow starts a tiny web server
+# subprocess to serve a health check on this host
+#
+# Variable: AIRFLOW__SCHEDULER__SCHEDULER_HEALTH_CHECK_SERVER_HOST
+#
+scheduler_health_check_server_host = 0.0.0.0
+
+# When you start a scheduler, airflow starts a tiny web server
+# subprocess to serve a health check on this port
+#
+# Variable: AIRFLOW__SCHEDULER__SCHEDULER_HEALTH_CHECK_SERVER_PORT
+#
+scheduler_health_check_server_port = 8974
+
+# How often (in seconds) should the scheduler check for orphaned tasks and SchedulerJobs
+#
+# Variable: AIRFLOW__SCHEDULER__ORPHANED_TASKS_CHECK_INTERVAL
+#
+orphaned_tasks_check_interval = 300.0
+
+# Determines the directory where logs for the child processes of the scheduler will be stored
+#
+# Variable: AIRFLOW__SCHEDULER__CHILD_PROCESS_LOG_DIRECTORY
+#
+child_process_log_directory = /opt/airflow/logs/scheduler
+
+# Local task jobs periodically heartbeat to the DB. If the job has
+# not heartbeat in this many seconds, the scheduler will mark the
+# associated task instance as failed and will re-schedule the task.
+#
+# Variable: AIRFLOW__SCHEDULER__SCHEDULER_ZOMBIE_TASK_THRESHOLD
+#
+scheduler_zombie_task_threshold = 300
+
+# How often (in seconds) should the scheduler check for zombie tasks.
+#
+# Variable: AIRFLOW__SCHEDULER__ZOMBIE_DETECTION_INTERVAL
+#
+zombie_detection_interval = 10.0
+
+# Turn off scheduler catchup by setting this to ``False``.
+# Default behavior is unchanged and
+# Command Line Backfills still work, but the scheduler
+# will not do scheduler catchup if this is ``False``,
+# however it can be set on a per DAG basis in the
+# DAG definition (catchup)
+#
+# Variable: AIRFLOW__SCHEDULER__CATCHUP_BY_DEFAULT
+#
+catchup_by_default = True
+
+# Setting this to ``True`` will make first task instance of a task
+# ignore depends_on_past setting. A task instance will be considered
+# as the first task instance of a task when there is no task instance
+# in the DB with an execution_date earlier than it., i.e. no manual marking
+# success will be needed for a newly added task to be scheduled.
+#
+# Variable: AIRFLOW__SCHEDULER__IGNORE_FIRST_DEPENDS_ON_PAST_BY_DEFAULT
+#
+ignore_first_depends_on_past_by_default = True
+
+# This changes the batch size of queries in the scheduling main loop.
+# This should not be greater than ``[core] parallelism``.
+# If this is too high, SQL query performance may be impacted by
+# complexity of query predicate, and/or excessive locking.
+# Additionally, you may hit the maximum allowable query length for your db.
+# Set this to 0 to use the value of ``[core] parallelism``
+#
+# Variable: AIRFLOW__SCHEDULER__MAX_TIS_PER_QUERY
+#
+max_tis_per_query = 16
+
+# Should the scheduler issue ``SELECT ... FOR UPDATE`` in relevant queries.
+# If this is set to ``False`` then you should not run more than a single
+# scheduler at once
+#
+# Variable: AIRFLOW__SCHEDULER__USE_ROW_LEVEL_LOCKING
+#
+use_row_level_locking = True
+
+# Max number of DAGs to create DagRuns for per scheduler loop.
+#
+# Variable: AIRFLOW__SCHEDULER__MAX_DAGRUNS_TO_CREATE_PER_LOOP
+#
+max_dagruns_to_create_per_loop = 10
+
+# How many DagRuns should a scheduler examine (and lock) when scheduling
+# and queuing tasks.
+#
+# Variable: AIRFLOW__SCHEDULER__MAX_DAGRUNS_PER_LOOP_TO_SCHEDULE
+#
+max_dagruns_per_loop_to_schedule = 20
+
+# Should the Task supervisor process perform a "mini scheduler" to attempt to schedule more tasks of the
+# same DAG. Leaving this on will mean tasks in the same DAG execute quicker, but might starve out other
+# dags in some circumstances
+#
+# Variable: AIRFLOW__SCHEDULER__SCHEDULE_AFTER_TASK_EXECUTION
+#
+schedule_after_task_execution = True
+
+# The scheduler reads dag files to extract the airflow modules that are going to be used,
+# and imports them ahead of time to avoid having to re-do it for each parsing process.
+# This flag can be set to ``False`` to disable this behavior in case an airflow module needs
+# to be freshly imported each time (at the cost of increased DAG parsing time).
+#
+# Variable: AIRFLOW__SCHEDULER__PARSING_PRE_IMPORT_MODULES
+#
+parsing_pre_import_modules = True
+
+# The scheduler can run multiple processes in parallel to parse dags.
+# This defines how many processes will run.
+#
+# Variable: AIRFLOW__SCHEDULER__PARSING_PROCESSES
+#
+parsing_processes = 2
+
+# One of ``modified_time``, ``random_seeded_by_host`` and ``alphabetical``.
+# The scheduler will list and sort the dag files to decide the parsing order.
+# 
+# * ``modified_time``: Sort by modified time of the files. This is useful on large scale to parse the
+#   recently modified DAGs first.
+# * ``random_seeded_by_host``: Sort randomly across multiple Schedulers but with same order on the
+#   same host. This is useful when running with Scheduler in HA mode where each scheduler can
+#   parse different DAG files.
+# * ``alphabetical``: Sort by filename
+#
+# Variable: AIRFLOW__SCHEDULER__FILE_PARSING_SORT_MODE
+#
+file_parsing_sort_mode = modified_time
+
+# Whether the dag processor is running as a standalone process or it is a subprocess of a scheduler
+# job.
+#
+# Variable: AIRFLOW__SCHEDULER__STANDALONE_DAG_PROCESSOR
+#
+standalone_dag_processor = False
+
+# Only applicable if ``[scheduler] standalone_dag_processor`` is true and  callbacks are stored
+# in database. Contains maximum number of callbacks that are fetched during a single loop.
+#
+# Variable: AIRFLOW__SCHEDULER__MAX_CALLBACKS_PER_LOOP
+#
+max_callbacks_per_loop = 20
+
+# Only applicable if ``[scheduler] standalone_dag_processor`` is true.
+# Time in seconds after which dags, which were not updated by Dag Processor are deactivated.
+#
+# Variable: AIRFLOW__SCHEDULER__DAG_STALE_NOT_SEEN_DURATION
+#
+dag_stale_not_seen_duration = 600
+
+# Turn off scheduler use of cron intervals by setting this to ``False``.
+# DAGs submitted manually in the web UI or with trigger_dag will still run.
+#
+# Variable: AIRFLOW__SCHEDULER__USE_JOB_SCHEDULE
+#
+use_job_schedule = True
+
+# Allow externally triggered DagRuns for Execution Dates in the future
+# Only has effect if schedule_interval is set to None in DAG
+#
+# Variable: AIRFLOW__SCHEDULER__ALLOW_TRIGGER_IN_FUTURE
+#
+allow_trigger_in_future = False
+
+# How often to check for expired trigger requests that have not run yet.
+#
+# Variable: AIRFLOW__SCHEDULER__TRIGGER_TIMEOUT_CHECK_INTERVAL
+#
+trigger_timeout_check_interval = 15
+
+# Amount of time a task can be in the queued state before being retried or set to failed.
+#
+# Variable: AIRFLOW__SCHEDULER__TASK_QUEUED_TIMEOUT
+#
+task_queued_timeout = 600.0
+
+# How often to check for tasks that have been in the queued state for
+# longer than ``[scheduler] task_queued_timeout``.
+#
+# Variable: AIRFLOW__SCHEDULER__TASK_QUEUED_TIMEOUT_CHECK_INTERVAL
+#
+task_queued_timeout_check_interval = 120.0
+
+# The run_id pattern used to verify the validity of user input to the run_id parameter when
+# triggering a DAG. This pattern cannot change the pattern used by scheduler to generate run_id
+# for scheduled DAG runs or DAG runs triggered without changing the run_id parameter.
+#
+# Variable: AIRFLOW__SCHEDULER__ALLOWED_RUN_ID_PATTERN
+#
+allowed_run_id_pattern = ^[A-Za-z0-9_.~:+-]+$
+
+# Whether to create DAG runs that span an interval or one single point in time for cron schedules, when
+# a cron string is provided to ``schedule`` argument of a DAG.
+# 
+# * ``True``: **CronDataIntervalTimetable** is used, which is suitable
+#   for DAGs with well-defined data interval. You get contiguous intervals from the end of the previous
+#   interval up to the scheduled datetime.
+# * ``False``: **CronTriggerTimetable** is used, which is closer to the behavior of cron itself.
+# 
+# Notably, for **CronTriggerTimetable**, the logical date is the same as the time the DAG Run will
+# try to schedule, while for **CronDataIntervalTimetable**, the logical date is the beginning of
+# the data interval, but the DAG Run will try to schedule at the end of the data interval.
+#
+# Variable: AIRFLOW__SCHEDULER__CREATE_CRON_DATA_INTERVALS
+#
+create_cron_data_intervals = True
+
+[triggerer]
+# How many triggers a single Triggerer will run at once, by default.
+#
+# Variable: AIRFLOW__TRIGGERER__DEFAULT_CAPACITY
+#
+default_capacity = 1000
+
+# How often to heartbeat the Triggerer job to ensure it hasn't been killed.
+#
+# Variable: AIRFLOW__TRIGGERER__JOB_HEARTBEAT_SEC
+#
+job_heartbeat_sec = 5
+
+# If the last triggerer heartbeat happened more than ``[triggerer] triggerer_health_check_threshold``
+# ago (in seconds), triggerer is considered unhealthy.
+# This is used by the health check in the **/health** endpoint and in ``airflow jobs check`` CLI
+# for TriggererJob.
+#
+# Variable: AIRFLOW__TRIGGERER__TRIGGERER_HEALTH_CHECK_THRESHOLD
+#
+triggerer_health_check_threshold = 30
+
+[kerberos]
+# Location of your ccache file once kinit has been performed.
+#
+# Variable: AIRFLOW__KERBEROS__CCACHE
+#
+ccache = /tmp/airflow_krb5_ccache
+
+# gets augmented with fqdn
+#
+# Variable: AIRFLOW__KERBEROS__PRINCIPAL
+#
+principal = airflow
+
+# Determines the frequency at which initialization or re-initialization processes occur.
+#
+# Variable: AIRFLOW__KERBEROS__REINIT_FREQUENCY
+#
+reinit_frequency = 3600
+
+# Path to the kinit executable
+#
+# Variable: AIRFLOW__KERBEROS__KINIT_PATH
+#
+kinit_path = kinit
+
+# Designates the path to the Kerberos keytab file for the Airflow user
+#
+# Variable: AIRFLOW__KERBEROS__KEYTAB
+#
+keytab = airflow.keytab
+
+# Allow to disable ticket forwardability.
+#
+# Variable: AIRFLOW__KERBEROS__FORWARDABLE
+#
+forwardable = True
+
+# Allow to remove source IP from token, useful when using token behind NATted Docker host.
+#
+# Variable: AIRFLOW__KERBEROS__INCLUDE_IP
+#
+include_ip = True
+
+[sensors]
+# Sensor default timeout, 7 days by default (7 * 24 * 60 * 60).
+#
+# Variable: AIRFLOW__SENSORS__DEFAULT_TIMEOUT
+#
+default_timeout = 604800
+
+[usage_data_collection]
+# Airflow integrates `Scarf <https://about.scarf.sh/>`__ to collect basic platform and usage data
+# during operation. This data assists Airflow maintainers in better understanding how Airflow is used.
+# Insights gained from this telemetry are critical for prioritizing patches, minor releases, and
+# security fixes. Additionally, this information supports key decisions related to the development road map.
+# Check the FAQ doc for more information on what data is collected.
+# 
+# Deployments can opt-out of analytics by setting the ``enabled`` option
+# to ``False``, or the ``SCARF_ANALYTICS=false`` environment variable.
+# Individual users can easily opt-out of analytics in various ways documented in the
+# `Scarf Do Not Track docs <https://docs.scarf.sh/gateway/#do-not-track>`__.
+
+# Enable or disable usage data collection and sending.
+#
+# Variable: AIRFLOW__USAGE_DATA_COLLECTION__ENABLED
+#
+enabled = True
+
+[celery_kubernetes_executor]
+# This section only applies if you are using the ``CeleryKubernetesExecutor`` in
+# ``[core]`` section above
+
+# Define when to send a task to ``KubernetesExecutor`` when using ``CeleryKubernetesExecutor``.
+# When the queue of a task is the value of ``kubernetes_queue`` (default ``kubernetes``),
+# the task is executed via ``KubernetesExecutor``,
+# otherwise via ``CeleryExecutor``
+#
+# Variable: AIRFLOW__CELERY_KUBERNETES_EXECUTOR__KUBERNETES_QUEUE
+#
+kubernetes_queue = kubernetes
+
+[celery]
+# This section only applies if you are using the CeleryExecutor in
+# ``[core]`` section above
+
+# The app name that will be used by celery
+#
+# Variable: AIRFLOW__CELERY__CELERY_APP_NAME
+#
+celery_app_name = airflow.providers.celery.executors.celery_executor
+
+# The concurrency that will be used when starting workers with the
+# ``airflow celery worker`` command. This defines the number of task instances that
+# a worker will take, so size up your workers based on the resources on
+# your worker box and the nature of your tasks
+#
+# Variable: AIRFLOW__CELERY__WORKER_CONCURRENCY
+#
+worker_concurrency = 16
+
+# The maximum and minimum number of pool processes that will be used to dynamically resize
+# the pool based on load.Enable autoscaling by providing max_concurrency,min_concurrency
+# with the ``airflow celery worker`` command (always keep minimum processes,
+# but grow to maximum if necessary).
+# Pick these numbers based on resources on worker box and the nature of the task.
+# If autoscale option is available, worker_concurrency will be ignored.
+# https://docs.celeryq.dev/en/latest/reference/celery.bin.worker.html#cmdoption-celery-worker-autoscale
+#
+# Example: worker_autoscale = 16,12
+#
+# Variable: AIRFLOW__CELERY__WORKER_AUTOSCALE
+#
+# worker_autoscale = 
+
+# Used to increase the number of tasks that a worker prefetches which can improve performance.
+# The number of processes multiplied by worker_prefetch_multiplier is the number of tasks
+# that are prefetched by a worker. A value greater than 1 can result in tasks being unnecessarily
+# blocked if there are multiple workers and one worker prefetches tasks that sit behind long
+# running tasks while another worker has unutilized processes that are unable to process the already
+# claimed blocked tasks.
+# https://docs.celeryq.dev/en/stable/userguide/optimizing.html#prefetch-limits
+#
+# Variable: AIRFLOW__CELERY__WORKER_PREFETCH_MULTIPLIER
+#
+worker_prefetch_multiplier = 1
+
+# Specify if remote control of the workers is enabled.
+# In some cases when the broker does not support remote control, Celery creates lots of
+# ``.*reply-celery-pidbox`` queues. You can prevent this by setting this to false.
+# However, with this disabled Flower won't work.
+# https://docs.celeryq.dev/en/stable/getting-started/backends-and-brokers/index.html#broker-overview
+#
+# Variable: AIRFLOW__CELERY__WORKER_ENABLE_REMOTE_CONTROL
+#
+worker_enable_remote_control = true
+
+# The Celery broker URL. Celery supports RabbitMQ, Redis and experimentally
+# a sqlalchemy database. Refer to the Celery documentation for more information.
+#
+# Variable: AIRFLOW__CELERY__BROKER_URL
+#
+broker_url = ${AIRFLOW__CELERY__BROKER_URL}
+
+# The Celery result_backend. When a job finishes, it needs to update the
+# metadata of the job. Therefore it will post a message on a message bus,
+# or insert it into a database (depending of the backend)
+# This status is used by the scheduler to update the state of the task
+# The use of a database is highly recommended
+# When not specified, sql_alchemy_conn with a db+ scheme prefix will be used
+# https://docs.celeryq.dev/en/latest/userguide/configuration.html#task-result-backend-settings
+#
+# Example: result_backend = db+postgresql://postgres:airflow@postgres/airflow
+#
+# Variable: AIRFLOW__CELERY__RESULT_BACKEND
+#
+result_backend = ${AIRFLOW__DATABASE__SQL_ALCHEMY_CONN}
+
+# Optional configuration dictionary to pass to the Celery result backend SQLAlchemy engine.
+#
+# Example: result_backend_sqlalchemy_engine_options = {"pool_recycle": 1800}
+#
+# Variable: AIRFLOW__CELERY__RESULT_BACKEND_SQLALCHEMY_ENGINE_OPTIONS
+#
+result_backend_sqlalchemy_engine_options = 
+
+# Celery Flower is a sweet UI for Celery. Airflow has a shortcut to start
+# it ``airflow celery flower``. This defines the IP that Celery Flower runs on
+#
+# Variable: AIRFLOW__CELERY__FLOWER_HOST
+#
+flower_host = 0.0.0.0
+
+# The root URL for Flower
+#
+# Example: flower_url_prefix = /flower
+#
+# Variable: AIRFLOW__CELERY__FLOWER_URL_PREFIX
+#
+flower_url_prefix = 
+
+# This defines the port that Celery Flower runs on
+#
+# Variable: AIRFLOW__CELERY__FLOWER_PORT
+#
+flower_port = 5555
+
+# Securing Flower with Basic Authentication
+# Accepts user:password pairs separated by a comma
+#
+# Example: flower_basic_auth = user1:password1,user2:password2
+#
+# Variable: AIRFLOW__CELERY__FLOWER_BASIC_AUTH
+#
+flower_basic_auth = 
+
+# How many processes CeleryExecutor uses to sync task state.
+# 0 means to use max(1, number of cores - 1) processes.
+#
+# Variable: AIRFLOW__CELERY__SYNC_PARALLELISM
+#
+sync_parallelism = 0
+
+# Import path for celery configuration options
+#
+# Variable: AIRFLOW__CELERY__CELERY_CONFIG_OPTIONS
+#
+celery_config_options = airflow.providers.celery.executors.default_celery.DEFAULT_CELERY_CONFIG
+
+#
+# Variable: AIRFLOW__CELERY__SSL_ACTIVE
+#
+ssl_active = False
+
+# Path to the client key.
+#
+# Variable: AIRFLOW__CELERY__SSL_KEY
+#
+ssl_key = 
+
+# Path to the client certificate.
+#
+# Variable: AIRFLOW__CELERY__SSL_CERT
+#
+ssl_cert = 
+
+# Path to the CA certificate.
+#
+# Variable: AIRFLOW__CELERY__SSL_CACERT
+#
+ssl_cacert = 
+
+# Celery Pool implementation.
+# Choices include: ``prefork`` (default), ``eventlet``, ``gevent`` or ``solo``.
+# See:
+# https://docs.celeryq.dev/en/latest/userguide/workers.html#concurrency
+# https://docs.celeryq.dev/en/latest/userguide/concurrency/eventlet.html
+#
+# Variable: AIRFLOW__CELERY__POOL
+#
+pool = prefork
+
+# The number of seconds to wait before timing out ``send_task_to_executor`` or
+# ``fetch_celery_task_state`` operations.
+#
+# Variable: AIRFLOW__CELERY__OPERATION_TIMEOUT
+#
+operation_timeout = 1.0
+
+task_acks_late = True
+# Celery task will report its status as 'started' when the task is executed by a worker.
+# This is used in Airflow to keep track of the running tasks and if a Scheduler is restarted
+# or run in HA mode, it can adopt the orphan tasks launched by previous SchedulerJob.
+#
+# Variable: AIRFLOW__CELERY__TASK_TRACK_STARTED
+#
+task_track_started = True
+
+# The Maximum number of retries for publishing task messages to the broker when failing
+# due to ``AirflowTaskTimeout`` error before giving up and marking Task as failed.
+#
+# Variable: AIRFLOW__CELERY__TASK_PUBLISH_MAX_RETRIES
+#
+task_publish_max_retries = 3
+
+# Worker initialisation check to validate Metadata Database connection
+#
+# Variable: AIRFLOW__CELERY__WORKER_PRECHECK
+#
+worker_precheck = False
+
+[celery_broker_transport_options]
+# This section is for specifying options which can be passed to the
+# underlying celery broker transport. See:
+# https://docs.celeryq.dev/en/latest/userguide/configuration.html#std:setting-broker_transport_options
+
+# The visibility timeout defines the number of seconds to wait for the worker
+# to acknowledge the task before the message is redelivered to another worker.
+# Make sure to increase the visibility timeout to match the time of the longest
+# ETA you're planning to use.
+# visibility_timeout is only supported for Redis and SQS celery brokers.
+# See:
+# https://docs.celeryq.dev/en/stable/getting-started/backends-and-brokers/redis.html#visibility-timeout
+#
+# Example: visibility_timeout = 21600
+#
+# Variable: AIRFLOW__CELERY_BROKER_TRANSPORT_OPTIONS__VISIBILITY_TIMEOUT
+#
+# visibility_timeout = 
+
+# The sentinel_kwargs parameter allows passing additional options to the Sentinel client.
+# In a typical scenario where Redis Sentinel is used as the broker and Redis servers are
+# password-protected, the password needs to be passed through this parameter. Although its
+# type is string, it is required to pass a string that conforms to the dictionary format.
+# See:
+# https://docs.celeryq.dev/en/stable/getting-started/backends-and-brokers/redis.html#configuration
+#
+# Example: sentinel_kwargs = {"password": "password_for_redis_server"}
+#
+# Variable: AIRFLOW__CELERY_BROKER_TRANSPORT_OPTIONS__SENTINEL_KWARGS
+#
+# sentinel_kwargs = 
+
+[common.io]
+# Common IO configuration section
+
+# Path to a location on object storage where XComs can be stored in url format.
+#
+# Example: xcom_objectstorage_path = s3://conn_id@bucket/path
+#
+# Variable: AIRFLOW__COMMON.IO__XCOM_OBJECTSTORAGE_PATH
+#
+xcom_objectstorage_path = 
+
+# Threshold in bytes for storing XComs in object storage. -1 means always store in the
+# database. 0 means always store in object storage. Any positive number means
+# it will be stored in object storage if the size of the value is greater than the threshold.
+#
+# Example: xcom_objectstorage_threshold = 1000000
+#
+# Variable: AIRFLOW__COMMON.IO__XCOM_OBJECTSTORAGE_THRESHOLD
+#
+xcom_objectstorage_threshold = -1
+
+# Compression algorithm to use when storing XComs in object storage. Supported algorithms
+# are a.o.: snappy, zip, gzip, bz2, and lzma. If not specified, no compression will be used.
+# Note that the compression algorithm must be available in the Python installation (e.g.
+# python-snappy for snappy). Zip, gz, bz2 are available by default.
+#
+# Example: xcom_objectstorage_compression = gz
+#
+# Variable: AIRFLOW__COMMON.IO__XCOM_OBJECTSTORAGE_COMPRESSION
+#
+xcom_objectstorage_compression = 
+
+[fab]
+# This section contains configs specific to FAB provider.
+
+# Boolean for enabling rate limiting on authentication endpoints.
+#
+# Variable: AIRFLOW__FAB__AUTH_RATE_LIMITED
+#
+auth_rate_limited = True
+
+# Rate limit for authentication endpoints.
+#
+# Variable: AIRFLOW__FAB__AUTH_RATE_LIMIT
+#
+auth_rate_limit = 5 per 40 second
+
+# Update FAB permissions and sync security manager roles
+# on webserver startup
+#
+# Variable: AIRFLOW__FAB__UPDATE_FAB_PERMS
+#
+update_fab_perms = True
+
+[imap]
+# Options for IMAP provider.
+
+# ssl_context = 
+
+[smtp_provider]
+# Options for SMTP provider.
+
+# ssl context to use when using SMTP and IMAP SSL connections. By default, the context is "default"
+# which sets it to ``ssl.create_default_context()`` which provides the right balance between
+# compatibility and security, it however requires that certificates in your operating system are
+# updated and that SMTP/IMAP servers of yours have valid certificates that have corresponding public
+# keys installed on your machines. You can switch it to "none" if you want to disable checking
+# of the certificates, but it is not recommended as it allows MITM (man-in-the-middle) attacks
+# if your infrastructure is not sufficiently secured. It should only be set temporarily while you
+# are fixing your certificate configuration. This can be typically done by upgrading to newer
+# version of the operating system you run Airflow components on,by upgrading/refreshing proper
+# certificates in the OS or by updating certificates for your mail servers.
+# 
+# If you do not set this option explicitly, it will use Airflow "email.ssl_context" configuration,
+# but if this configuration is not present, it will use "default" value.
+#
+# Example: ssl_context = default
+#
+# Variable: AIRFLOW__SMTP_PROVIDER__SSL_CONTEXT
+#
+# ssl_context = 
+
+# Allows overriding of the standard templated email subject line when the SmtpNotifier is used.
+# Must provide a path to the template.
+#
+# Example: templated_email_subject_path = path/to/override/email_subject.html
+#
+# Variable: AIRFLOW__SMTP_PROVIDER__TEMPLATED_EMAIL_SUBJECT_PATH
+#
+# templated_email_subject_path = 
+
+# Allows overriding of the standard templated email path when the SmtpNotifier is used. Must provide
+# a path to the template.
+#
+# Example: templated_html_content_path = path/to/override/email.html
+#
+# Variable: AIRFLOW__SMTP_PROVIDER__TEMPLATED_HTML_CONTENT_PATH
+#
+# templated_html_content_path = 
+

dags/CrawDag.py

@@ -0,0 +1,49 @@
+import requests
+from datetime import datetime
+from airflow import DAG
+from airflow.operators.python import PythonOperator
+from CrawDag.models import News
+from CrawDag.crawling import CrawlingTask
+from CrawDag.scraping import ScrapingTask
+from CrawDag.saving import SavingTask
+from CrawDag.sending import SendingTask
+import pytz
+
+
+with DAG(
+    dag_id = 'CrawDag',
+    description = 'Crawling news from multiple sources',
+    # start_date = datetime(2025,1,1, 0, 0 ,0, 0, tzinfo=pytz.timezone('Asia/Ho_Chi_Minh')),
+    schedule_interval='@monthly',
+    start_date = datetime.now(tz=pytz.timezone('Asia/Ho_Chi_Minh')),
+    # schedule_interval = '*/30 * * * *'
+
+) as dag:
+    crawl_task = PythonOperator(
+        task_id = 'crawl_task',
+        python_callable = CrawlingTask('crawl_task').execute,
+        provide_context = True
+    )
+
+    scrape_task = PythonOperator(
+        task_id = 'scrape_task',
+        python_callable = ScrapingTask('scrape_task').execute,
+        provide_context = True
+    )
+
+    save_task = PythonOperator(
+        task_id = 'save_task',
+        python_callable = SavingTask('save_task').execute,
+        provide_context = True
+    )
+
+    sent_task = PythonOperator(
+        task_id = 'sent_task',
+        python_callable = SendingTask('sent_task').execute,
+        provide_context = True
+    )
+
+    # crawl_task
+    # crawl_task >> scrape_task
+    # crawl_task >> scrape_task >> save_task
+    crawl_task >> scrape_task >> save_task >> sent_task

dags/CrawDag/crawling/Crawler.py

@@ -0,0 +1,9 @@
+from abc import ABC, abstractmethod
+from CrawDag.models import News
+class Crawler(ABC):
+    def __init__(self, topics: dict[str: str]) -> None:
+        self.topics = topics
+        
+    @abstractmethod
+    def crawl(self) -> list[News]:
+        pass

dags/CrawDag/crawling/CrawlingTask.py

@@ -0,0 +1,46 @@
+from CrawDag.models import TaskHandle, DataExchange, News
+from .RssCrawler import ThanhNienCrawler, VnexpressCrawler
+from .Crawler import Crawler
+class CrawlingTask(TaskHandle):
+    task_ids = None
+    key = 'crawl_news'    
+
+    def __init__(self, task_ids: str) -> None:
+        super().__init__()
+        CrawlingTask.task_ids = task_ids
+        self.sources = [
+            {
+                'source': 'vnexpress',
+                'type': 'rss',
+                'topic': {
+                    'economic': 'https://vnexpress.net/rss/kinh-doanh.rss',
+                    'health': 'https://vnexpress.net/rss/suc-khoe.rss',
+                    'sport': 'https://vnexpress.net/rss/the-thao.rss',
+                    'politic': 'https://vnexpress.net/rss/the-gioi.rss'
+                },
+            },
+            {
+                'source': 'thanhnien',
+                'type': 'rss',
+                'topic': {
+                    'economic': 'https://thanhnien.vn/rss/kinh-te.rss',
+                    'health': 'https://thanhnien.vn/rss/suc-khoe.rss',
+                    'sport': 'https://thanhnien.vn/rss/the-thao.rss',
+                    'politic': 'https://thanhnien.vn/rss/chinh-tri.rss'
+                },
+            }
+        ]
+
+    def execute(self, **context: any):
+        news: list[News] = []
+        for source in self.sources:
+            if source['source'] == 'vnexpress':
+                crawler:Crawler = VnexpressCrawler(source['topic'])
+            elif source['source'] == 'thanhnien':
+                crawler:Crawler = ThanhNienCrawler(source['topic'])
+            news.extend(crawler.crawl())
+        news = news[:40]
+        dataExchange = DataExchange(context['ti'])
+        dataExchange.push(CrawlingTask.key, [new.to_json() for new in news])
+    
+        

dags/CrawDag/crawling/RssCrawler/ThanhNienCrawler.py

@@ -0,0 +1,35 @@
+from CrawDag.crawling.Crawler import Crawler
+from CrawDag.models import News
+from datetime import datetime, timedelta
+from bs4 import BeautifulSoup
+import requests
+import pytz
+import html
+
+class ThanhNienCrawler(Crawler):
+    def __init__(self, topics: dict[str: str]) -> None:
+        super().__init__(topics)
+
+    def crawl(self) -> list[News]:
+        news = []
+        for topic in self.topics:
+            response = requests.get(self.topics[topic], verify=False)
+            soup = BeautifulSoup(response.content, 'xml')
+            time = datetime.now(pytz.timezone('Asia/Ho_Chi_Minh')) - timedelta(hours=24)
+            for item in soup.find_all('item'):
+                link = item.find('link').text
+                pub_date_text = item.find('pubDate').text
+                date = datetime.strptime(pub_date_text, '%a, %d %b %y %H:%M:%S %z')                
+                title = item.find('title').text.strip()
+                title = html.unescape(title)
+                description = item.find('description').text
+                description = description[9:-3]
+                description_soup = BeautifulSoup(description, 'html.parser')
+                img_tag = description_soup.find('img')
+                image = img_tag['src'] if img_tag else None
+                if date >= time:
+                    news.append(News(topic=topic, title=title, link=link, date=date, image=image))
+        return news
+
+
+    

dags/CrawDag/crawling/RssCrawler/VnexpressCrawler.py

@@ -0,0 +1,35 @@
+from CrawDag.crawling.Crawler import Crawler
+from CrawDag.models import News
+from datetime import datetime, timedelta
+from bs4 import BeautifulSoup
+import requests
+import pytz
+import html
+
+class VnexpressCrawler(Crawler):
+    def __init__(self, topics: dict[str: str]) -> None:
+        super().__init__(topics)
+
+
+    def crawl(self) -> list[News]:
+        news = []
+        for topic in self.topics:
+            response = requests.get(self.topics[topic], verify=False)
+            soup = BeautifulSoup(response.content, 'xml')
+            time = datetime.now(pytz.timezone('Asia/Ho_Chi_Minh')) - timedelta(hours=24)
+            for item in soup.find_all('item'):
+                link = item.find('link').text
+                pub_date_text = item.find('pubDate').text
+                date = datetime.strptime(pub_date_text, '%a, %d %b %Y %H:%M:%S %z')
+                title = item.find('title').text.strip()
+                title = html.unescape(title)
+                description = item.find('description').text
+                description_soup = BeautifulSoup(description, 'html.parser')
+                img_tag = description_soup.find('img')
+                image = img_tag['src'] if img_tag else None
+                if date >= time:
+                    news.append(News(topic=topic, title=title, link=link, date=date, image=image))
+        return news
+
+
+    

dags/CrawDag/crawling/RssCrawler/__init__.py

@@ -0,0 +1,2 @@
+from .ThanhNienCrawler import ThanhNienCrawler
+from .VnexpressCrawler import VnexpressCrawler

dags/CrawDag/crawling/__init__.py

@@ -0,0 +1 @@
+from .CrawlingTask import CrawlingTask

dags/CrawDag/models/DataExchange.py

@@ -0,0 +1,11 @@
+from airflow.models import TaskInstance
+
+class DataExchange:
+    def __init__(self, task_instance: TaskInstance):
+        self.task_instance = task_instance
+
+    def push(self, key: str, value: any):
+        self.task_instance.xcom_push(key=key, value=value)
+
+    def pull(self, task_ids: str, key: str) -> any:
+        return self.task_instance.xcom_pull(task_ids=task_ids, key=key)

dags/CrawDag/models/TaskHandle.py

@@ -0,0 +1,5 @@
+from abc import ABC, abstractmethod
+class TaskHandle(ABC):
+    @abstractmethod
+    def execute(self, **context: any):
+        pass

dags/CrawDag/models/__init__.py

@@ -0,0 +1,3 @@
+from .News import News
+from .DataExchange import DataExchange
+from .TaskHandle import TaskHandle

dags/CrawDag/models/news.py

@@ -0,0 +1,42 @@
+from datetime import datetime
+class News:
+    def __init__(self, 
+                 topic: str = '', 
+                 title: str = '', 
+                 content: str = '', 
+                 link: str = '', 
+                 date: datetime = None, 
+                 image: str = '',
+                 html: str = ''):
+        self.topic = topic
+        self.title = title
+        self.content = content
+        self.link = link
+        self.date = date
+        self.image = image
+        self.html = html
+
+    def __str__(self):
+        return f"Title: {self.title}, Content: {self.content}, URL: {self.url}, Date: {self.date}, Source: {self.source}"
+
+    def to_json(self):
+        return {
+            'topic': self.topic,
+            'title': self.title,
+            'content': self.content,
+            'link': self.link,
+            'date': self.date.isoformat(),
+            'image': self.image,
+            'html': self.html,
+        }
+    
+    def __eq__(self, value: object) -> bool:
+        if not isinstance(value, News):
+            return False
+        return self.topic == value.topic and self.title == value.title and self.content == value.content
+
+    @classmethod
+    def from_json(cls, data):
+        """Convert JSON data back to News object."""
+        data['date'] = datetime.fromisoformat(data['date'])  # Convert string back to datetime
+        return cls(**data)

dags/CrawDag/saving/DataLake.py

@@ -0,0 +1,10 @@
+from abc import ABC, abstractmethod
+from CrawDag.models import News
+class DataLake(ABC):
+    @abstractmethod
+    def save(self, listNews: list[News]) -> list[str]:
+        pass
+
+    @abstractmethod
+    def delete(self, listNewsId: list[str]) -> None:
+        pass

dags/CrawDag/saving/SavingMethod/MongoDataLake.py

@@ -0,0 +1,45 @@
+from CrawDag.saving.DataLake import DataLake
+from CrawDag.models import News
+from pymongo import MongoClient
+from bson.objectid import ObjectId
+import os
+from pymongo.server_api import ServerApi
+from dotenv import load_dotenv
+import logging
+class MongoDataLake(DataLake):
+    def __init__(self) -> None:
+        self.database = self.__connect()
+        pass
+
+    def __connect(self):      
+        uri = f"mongodb+srv://admin:[email protected]/?retryWrites=true&w=majority&appName=Cluster0"
+        uri = (
+        "mongodb+srv://{}:{}@{}/?retryWrites=true&w=majority&appName=Cluster0".format(
+            os.getenv("MONGO_INITDB_ROOT_USERNAME"), os.getenv("MONGO_INITDB_ROOT_PASSWORD"),
+            os.getenv("MONGO_HOST"),
+            )
+        )
+    
+        client = MongoClient(uri, server_api=ServerApi('1'))
+        database = client.get_database(os.getenv("MONGO_DATABASE"))
+        return database
+
+    def save(self, listNews: list[News]) -> list[str]:
+        newsCollection = self.database.get_collection('news')
+        newsListIds = []
+        for new in listNews:
+            existing = newsCollection.find_one({'topic': new.topic, 'title': new.title})
+            if existing:
+                if new.content != existing['content']:
+                    newsCollection.update_one({'_id': existing['_id']}, {'$set': new.to_json()})
+                    newsListIds.append(str(existing['_id']))
+            else:
+                result = newsCollection.insert_one(new.to_json())
+                newsListIds.append(str(result.inserted_id))
+
+        return newsListIds
+    
+    def delete(self, listNewsId: list[str]) -> None:
+        newsCollection = self.database.get_collection('news')
+        for newsId in listNewsId:
+            newsCollection.delete_one({'_id': ObjectId(newsId)})

dags/CrawDag/saving/SavingMethod/__init__.py

@@ -0,0 +1 @@
+from .MongoDataLake import MongoDataLake

dags/CrawDag/saving/SavingTask.py

@@ -0,0 +1,20 @@
+from CrawDag.models import TaskHandle, DataExchange, News
+from CrawDag.scraping import ScrapingTask
+from CrawDag.saving.SavingMethod import MongoDataLake
+from .DataLake import DataLake
+class SavingTask(TaskHandle):
+    task_ids = None
+    key = 'scrape_news'
+
+    def __init__(self, task_ids: str) -> None:
+        super().__init__()
+        SavingTask.task_ids = task_ids
+        self.dataLake: DataLake = MongoDataLake()
+
+    def execute(self, **context: any):
+        dataExchange = DataExchange(context['ti'])
+        listNewsJson = dataExchange.pull(ScrapingTask.task_ids, ScrapingTask.key)
+        listNews = [News.from_json(newsJson) for newsJson in listNewsJson]
+
+        listNewsId = self.dataLake.save(listNews)
+        dataExchange.push(SavingTask.key, listNewsId)

dags/CrawDag/saving/__init__.py

@@ -0,0 +1 @@
+from .SavingTask import SavingTask

dags/CrawDag/scraping/ScrapeMethod/ScrapeArticle.py

@@ -0,0 +1,21 @@
+from CrawDag.scraping.Scraper import Scraper
+from CrawDag.models import News
+from newspaper import Article
+
+class ScrapeArticle(Scraper):
+    def __init__(self, listNews: list[News]) -> None:
+        super().__init__(listNews)
+
+    def scrape(self) -> list[News]:
+        newsList: list[News] = []
+        for news in self.listNews:
+            article = Article(news.link)
+            article.download()
+            article.parse()
+            paragraphs = article.text.split('\n')
+            news.content = '\n'.join([para for para in paragraphs[0:-1]]).strip()
+            news.html = article.html
+            if news.content != '' and len(news.content) > 10: # check if the content is not empty
+                newsList.append(news)
+            
+        return newsList

dags/CrawDag/scraping/ScrapeMethod/ScrapeBasic.py

@@ -0,0 +1,23 @@
+from CrawDag.scraping.Scraper import Scraper
+from CrawDag.models import News
+from bs4 import BeautifulSoup
+import requests
+
+class ScrapeBasic(Scraper):
+    def __init__(self, listNews: list[News]) -> None:
+        self.listNews = listNews
+
+    def scrape(self) -> list[News]:
+        newsList: list[News] = []
+        for news in self.listNews:
+            response = requests.get(news.link, verify=False)
+            soup = BeautifulSoup(response.content, 'html.parser')
+            paragraphs = soup.find_all('p')
+            content = ' '.join([para.get_text() for para in paragraphs[0:-1]])
+            html = soup.find('article')
+            news.content = content.strip()
+            news.html = html
+            newsList.append(news)
+
+        return newsList
+        

dags/CrawDag/scraping/ScrapeMethod/__init__.py

@@ -0,0 +1,2 @@
+from .ScrapeArticle import ScrapeArticle
+from .ScrapeBasic import ScrapeBasic

dags/CrawDag/scraping/Scraper.py

@@ -0,0 +1,10 @@
+from abc import ABC, abstractmethod
+from CrawDag.models import News
+class Scraper(ABC):
+    @abstractmethod
+    def __init__(self, listNews: list[News]) -> None:
+        self.listNews = listNews
+
+    @abstractmethod
+    def scrape(self) -> list[News]:
+        pass

dags/CrawDag/scraping/ScrapingTask.py

@@ -0,0 +1,20 @@
+from CrawDag.models import TaskHandle, DataExchange, News
+from CrawDag.crawling import CrawlingTask
+from .ScrapeMethod import ScrapeArticle
+from .Scraper import Scraper
+class ScrapingTask(TaskHandle):
+    task_ids = None
+    key = 'scrape_news'
+
+    def __init__(self, task_ids: str) -> None:
+        super().__init__()
+        ScrapingTask.task_ids = task_ids
+
+    def execute(self, **context: any):
+        dataExchange = DataExchange(context['ti'])
+        listNewsJson = dataExchange.pull(CrawlingTask.task_ids, CrawlingTask.key)
+        listNews = [News.from_json(newsJson) for newsJson in listNewsJson]
+
+        newsList:list[News] = ScrapeArticle(listNews).scrape()
+        dataExchange.push(ScrapingTask.key, [news.to_json() for news in newsList])
+        

dags/CrawDag/scraping/__init__.py

@@ -0,0 +1,2 @@
+from .basic_scraper import scrape_basic_article, scrape_news_v2
+from .ScrapingTask import ScrapingTask

dags/CrawDag/scraping/basic_scraper.py

@@ -0,0 +1,25 @@
+from bs4 import BeautifulSoup
+import requests
+from CrawDag.models import News
+from newspaper import Article
+
+def clean_content(text: str) -> str:
+    """Helper function to clean article content."""
+    return text.strip().replace("\n", " ").replace("\t", " ")
+
+def scrape_basic_article(news: News):
+    response = requests.get(news.link, verify=False)
+    soup = BeautifulSoup(response.content, 'html.parser')
+    paragraphs = soup.find_all('p')
+    content = ' '.join([para.get_text() for para in paragraphs[0:-1]])
+    html = soup.find('article')
+    news.content = clean_content(content)
+    news.html = html
+
+def scrape_news_v2(news: News):
+    article = Article(news.link)
+    article.download()
+    article.parse()
+    paragraphs = article.text.split('\n')
+    news.content = '\n'.join([para for para in paragraphs[0:-1]]).strip()
+    news.html = article.html

dags/CrawDag/sending/SendingTask.py

@@ -0,0 +1,44 @@
+from CrawDag.models import TaskHandle, DataExchange, News
+from CrawDag.saving import SavingTask
+from CrawDag.saving.SavingMethod import MongoDataLake
+import time
+import requests
+from dotenv import load_dotenv
+import os
+
+load_dotenv()
+
+class SendingTask(TaskHandle):
+    task_ids = None
+    key = 'send_news'
+
+    def __init__(self, task_ids: str) -> None:
+        super().__init__()
+        SendingTask.task_ids = task_ids
+        self.__maxRetry = 4
+        self.__delay = 15
+
+    def execute(self, **context: any):
+        dataExchange = DataExchange(context['ti'])
+        listNewsId = dataExchange.pull(SavingTask.task_ids, SavingTask.key)
+
+        for attempt in range(self.__maxRetry):
+            try:
+                response = requests.post(
+                    url=os.getenv("SERVER_URL") + '/api/news/summarize',
+                    json=listNewsId
+                )
+                if response.status_code == 202:
+                    return
+                else:
+                    print(f"Attempt {attempt + 1} failed: {response.status_code}")
+                    time.sleep(self.__delay)
+
+            except requests.RequestException as e: 
+                print(f"Attempt {attempt + 1} failed: {e}")
+            time.sleep(self.__delay)
+        
+        dataLake = SavingTask(SavingTask.task_ids).dataLake
+        dataLake.delete(listNewsId)
+        print('Failed to send data to API')
+        raise Exception('Failed to send data to API')

dags/CrawDag/sending/__init__.py

@@ -0,0 +1 @@
+from .SendingTask import SendingTask

entrypoint.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+set -e
+
+
+# Initialize Airflow database migrations
+echo "Running database migrations..."
+airflow db migrate
+
+# Check if the Airflow user already exists before creating it
+echo "Checking if the admin user exists..."
+USER_EXISTS=$(airflow users list | grep -w "${AIRFLOW_USERNAME}" || true)
+
+if [ -z "$USER_EXISTS" ]; then
+    echo "Creating Airflow admin user..."
+    airflow users create --username "${AIRFLOW_USERNAME}" --password "${AIRFLOW_PASSWORD}" --firstname Admin --lastname Admin --role Admin --email "${AIRFLOW_EMAIL}"
+else
+    echo "Admin user already exists, skipping user creation."
+fi
+
+# Start Airflow services
+echo "Starting Airflow webserver, scheduler, and workers..."
+exec airflow webserver --port 8080 &  # Start webserver in the background
+exec airflow scheduler &               # Start scheduler in the background
+exec airflow celery worker              # Start Celery worker as the main process