persist data in database

.gitignore

@@ -1,10 +1,9 @@
 .ipynb_checkpoints/
 __pycache__/
+archive/
 
 .env
 test.py
-src/test.csv
+test.csv
 
 *.ipynb
-*.log
-*.zip

alembic.ini

@@ -0,0 +1,110 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = alembic
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python-dateutil library that can be
+# installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to dateutil.tz.gettz()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the
+# "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to alembic/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "version_path_separator" below.
+# version_locations = %(here)s/bar:%(here)s/bat:alembic/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
+# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
+# Valid values for version_path_separator are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+version_path_separator = os  # Use os.pathsep. Default configuration used for new projects.
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+sqlalchemy.url = sqlite:///database/jobs.db
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

alembic/README

@@ -0,0 +1 @@
+Generic single-database configuration.

alembic/env.py

@@ -0,0 +1,78 @@
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+from database.models import Base
+target_metadata = Base.metadata
+# target_metadata = None
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection, target_metadata=target_metadata
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

alembic/script.py.mako

@@ -0,0 +1,24 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision = ${repr(up_revision)}
+down_revision = ${repr(down_revision)}
+branch_labels = ${repr(branch_labels)}
+depends_on = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

alembic/versions/80a4b5684683_create_jobs_table.py

@@ -0,0 +1,40 @@
+"""create jobs table
+
+Revision ID: 80a4b5684683
+Revises: 
+Create Date: 2023-04-15 05:42:29.021389
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = '80a4b5684683'
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('jobs',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('role', sa.String(), nullable=False),
+    sa.Column('experience_level', sa.String(), nullable=True),
+    sa.Column('location', sa.String(), nullable=False),
+    sa.Column('url', sa.String(), nullable=False),
+    sa.Column('company', sa.String(), nullable=False),
+    sa.Column('created_at', sa.TIMESTAMP(timezone=True), server_default=sa.text("(datetime('now'))"), nullable=False),
+    sa.Column('qualify_for', sa.Boolean(), server_default=sa.text('0'), nullable=False),
+    sa.Column('sent', sa.Boolean(), server_default=sa.text('0'), nullable=False),
+    sa.PrimaryKeyConstraint('id'),
+    sa.UniqueConstraint('url')
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_table('jobs')
+    # ### end Alembic commands ###

alembic/versions/ae98339276a4_rename_sent_column.py

@@ -0,0 +1,30 @@
+"""rename sent column
+
+Revision ID: ae98339276a4
+Revises: 80a4b5684683
+Create Date: 2023-04-15 05:44:29.353001
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = 'ae98339276a4'
+down_revision = '80a4b5684683'
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column('jobs', sa.Column('is_sent', sa.Boolean(), server_default=sa.text('0'), nullable=False))
+    op.drop_column('jobs', 'sent')
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column('jobs', sa.Column('sent', sa.BOOLEAN(), server_default=sa.text('0'), nullable=False))
+    op.drop_column('jobs', 'is_sent')
+    # ### end Alembic commands ###

database/models.py

@@ -0,0 +1,31 @@
+from sqlalchemy import TIMESTAMP, Boolean, Column, String, Integer, text
+from sqlalchemy.sql import expression
+from sqlalchemy.ext.declarative import declarative_base
+
+
+Base = declarative_base()
+
+# class Company(Base):
+# 	__tablename__ = 'companies'
+
+# 	id = Column(Integer, primary_key=True)
+# 	name = Column(Text, nullable=False)
+
+class Job(Base):
+
+	__tablename__ = 'jobs'
+
+	id 					= Column(Integer, primary_key=True, nullable=False)
+	role 				= Column(String, nullable=False)
+	experience_level 	= Column(String, nullable=True)
+	location 			= Column(String, nullable=False)
+	url 				= Column(String, nullable=False, unique=True)
+	company 			= Column(String, nullable=False)
+	created_at 			= Column(TIMESTAMP(timezone=True), nullable=False, server_default=text("datetime('now')"))
+	qualify_for 		= Column(Boolean, nullable=False, server_default=expression.false())
+	is_sent 			= Column(Boolean, nullable=False, server_default=expression.false())
+
+
+
+
+

src/config.py

@@ -0,0 +1,17 @@
+COMPANIES = ('spotify',)
+
+
+
+KEYWORDS_MAP = {
+    'spotify': ('Associate', 'Engineer'), 
+    'zalando': ('Engineer',), 
+    'hellofresh': ('Junior', 'Engineer'),
+    }
+
+
+
+URLS_MAP = {
+    'spotify': "https://www.lifeatspotify.com/jobs", 
+    'zalando': "https://jobs.zalando.com/en/jobs",
+    'hellofresh': "https://careers.hellofresh.com/global/en/search-results"
+    }