first commit

.github/workflows/update_jlcpcb.yml.example

@@ -0,0 +1,41 @@
+name: Run main.py
+
+on:
+  schedule:
+    - cron: '0 10 * * *'
+  push:
+    branches:
+      - main
+
+jobs:
+  build:
+    runs-on: pi5 #ubuntu-latest
+
+    env:
+      SQLALCHEMY_DATABASE_URI: ${{ secrets.SQLALCHEMY_DATABASE_URI }}
+      JLCPCB_KEY: ${{ secrets.JLCPCB_KEY }}
+      JLCPCB_SECRET: ${{ secrets.JLCPCB_SECRET }}
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Python
+      run: |
+        apt-get update
+        apt-get install python3 python3-pip -y
+
+    # - name: Set up Python
+    #   uses: actions/setup-python@v5
+    #   with:
+    #     python-version: '3.12'
+
+    - name: Install dependencies
+      run: |
+        pip3 install --break-system-packages -r requirements.txt
+
+    - name: Run main.py
+      with: # Set the secret as an input
+        SQLALCHEMY_DATABASE_URI: ${{ secrets.SQLALCHEMY_DATABASE_URI }}
+        JLCPCB_KEY: ${{ secrets.JLCPCB_KEY }}
+        JLCPCB_SECRET: ${{ secrets.JLCPCB_SECRET }}
+      run: python3 jlcpcb_scraper/main.py

.gitignore

@@ -0,0 +1,25 @@
+.env
+*.env
+
+# Ignore system files
+.DS_Store
+Thumbs.db
+
+# Ignore node modules
+node_modules/
+
+# Ignore logs
+*.log
+
+# Ignore the build folder
+/dist
+
+# Ignore IDE specific files
+.idea/
+*.iml
+.vscode/
+
+# Ignore Python compiled files
+*.pyc
+
+*.egg-info/

README.md

@@ -0,0 +1,46 @@
+# JLCPCB Scraper
+
+This is a Python module to scrape parts information from jlcpcb.com/parts.
+
+## Installation
+
+To install the dependencies, run:
+
+```bash
+pip install -r requirements.txt
+```
+
+## Usage
+
+
+Create a Postgres DB and make sure it is reachable by the pc that will execute this script.
+Set environment variable SQLALCHEMY_DATABASE_URI, JLCPCB_KEY and JLCPCB_SECRET
+```
+export SQLALCHEMY_DATABASE_URI=postgres://YourUserName:YourPassword@YourHostname:5432/YourDatabaseName
+export JLCPCB_KEY=<KEY>
+export JLCPCB_SECRET=<SECRET>
+```
+
+Execute main.py
+```
+python3 jlcpcb_scraper/main.py
+``` 
+
+
+## Testing TODO, INCOMPLETE
+
+To run the tests, use the following command:
+
+```bash
+pytest tests
+```
+
+## Contributing
+
+Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
+
+Please make sure to update tests as appropriate.
+
+## License
+
+[MIT](https://choosealicense.com/licenses/mit/)

alembic.ini

@@ -0,0 +1,116 @@
+# 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>=3.9 or backports.zoneinfo library.
+# Any required deps can installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to ZoneInfo()
+# 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 = driver://user:pass@localhost/dbname
+
+
+[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
+
+# lint with attempts to fix using "ruff" - use the exec runner, execute a binary
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = %(here)s/.venv/bin/ruff
+# ruff.options = --fix 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 +1,84 @@
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+
+from jlcpcb_scraper.config import config as app_config
+from jlcpcb_scraper.base import *
+
+# 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 myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+target_metadata = Base.metadata
+
+# 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 = app_config.SQLALCHEMY_DATABASE_URI
+    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.
+
+    """
+    global config
+    config = config.get_section(config.config_ini_section, {})
+    config["sqlalchemy.url"] = app_config.SQLALCHEMY_DATABASE_URI
+    connectable = engine_from_config(
+        config,
+        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 +1,26 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}