Init repo

Author: Giulio Carvalho

.db.env.sample

@@ -0,0 +1,2 @@
+POSTGRES_PASSWORD=
+POSTGRES_USER=

.env.sample

@@ -0,0 +1,4 @@
+DB_DSN=
+TWOCAPTCHA_API_KEY=
+INSTACART_LOGIN=
+INSTACART_PASSWORD=

.gitignore

@@ -0,0 +1,139 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+.db.env
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/

.isort.cfg

@@ -0,0 +1,10 @@
+[settings]
+combine_star = true
+combine_as_imports = true
+order_by_type = true
+multi_line_output = 3
+include_trailing_comma = true
+use_parentheses = true
+line_length = 88
+known_third_party = "aiohttp, aiopg, parsel, twocaptcha, jmespath, sqlalchemy, decouple"
+known_first_party = "data_collection"

.pre-commit-config.yaml

@@ -0,0 +1,20 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v2.4.0
+    hooks:
+    -   id: trailing-whitespace
+    -   id: end-of-file-fixer
+-   repo: https://github.com/PyCQA/isort
+    rev: 5.6.4
+    hooks:
+    -   id: isort
+-   repo: https://github.com/psf/black
+    rev: 20.8b1
+    hooks:
+    -   id: black
+-   repo: https://gitlab.com/pycqa/flake8
+    rev: 3.7.9
+    hooks:
+        - id: flake8
+          args: ['--ignore=E, W, --show-source=True']
+          files: '.*\.py$'

Dockerfile

@@ -0,0 +1,17 @@
+FROM python:3.8-slim
+
+RUN apt-get update -y
+
+RUN apt-get -y install wait-for-it
+
+WORKDIR /mnt
+
+COPY requirements/requirements.txt .
+
+RUN pip install -r requirements.txt
+
+COPY . .
+
+RUN chmod 755 data_collection/run.sh
+
+ENTRYPOINT ["data_collection/run.sh"]

Makefile

@@ -0,0 +1,40 @@
+POSTGRES_USER ?= $(POSTGRES_USER)
+QUERY ?= SELECT * FROM stores;
+
+query-command=(docker exec -it instacart-postgres psql -U $(POSTGRES_USER) -c $1)
+
+.PHONY: build
+build:
+	docker-compose build
+
+start-database:
+	docker-compose up -d database
+
+wait-database:
+	docker-compose run --rm --no-deps --entrypoint "wait-for-it --timeout=30 database:5432" instacart
+
+.PHONY: database
+database: start-database wait-database
+
+.PHONY: run
+run: build database
+	docker-compose run --rm --no-deps instacart
+
+.PHONY: sql
+sql:
+	docker exec -it instacart-postgres psql -U $(POSTGRES_USER)
+
+sql-query:
+	$(call query-command, "$(QUERY)")
+
+sql-select-all:
+	$(call query-command, "SELECT * FROM stores")
+	$(call query-command, "SELECT * FROM shelves")
+	$(call query-command, "SELECT * FROM shelf_items")
+
+destroy:
+	docker-compose down -v --rmi all
+
+dev-setup:
+	pip install -r requirements/dev.txt
+	pre-commit install

README.md

@@ -0,0 +1,61 @@
+# Instacart Scraper
+
+Simple spider and workflow system for scraping Instacart's (US) default store
+for a given user.
+
+## Table of Contents
+  * [How to run](#how-to-run)
+  * [How to check collected data](#how-to-check-collected-data)
+  * [How to destroy the created environment](#how-to-destroy-the-created-environment)
+  * [For developers](#for-developers)
+
+## How to run
+
+First, you have to setup your environment variables. Samples
+([`.env.sample`](.env.sample) and [`.db.env.sample`](.db.env.sample)) were
+provided.
+
+Then, execute (Docker and Docker Compose are required):
+
+```shell
+$ make run
+```
+
+Done :smile:
+
+*Note: Recaptcha solving may fail. Retries are already in place, but in rare
+cases they are insufficient. In these cases, you try and run again.*
+
+## How to check collected data
+
+If you want to run a query in the database, execute:
+
+```shell
+$ POSTGRES_USER=<YOUR-POSTGRES-USER> QUERY=<YOUR-QUERY> make sql-query
+```
+
+However, to make things easier, a shortcut to make a `SELECT *` on all tables
+is available through:
+
+```shell
+$ POSTGRES_USER=<YOUR-POSTGRES-USER> make sql-select-all
+```
+
+## How to destroy the created environment
+
+This project uses Docker. To destroy created images, volumes, etc., execute:
+
+```shell
+$ make destroy
+```
+
+## For developers
+
+To setup you developer environment, create a virtualenv and execute:
+
+```shell
+$ make dev-setup
+```
+
+This project uses `pre-commit` for managing code formatting and `pip-tools` to
+manage dependencies.

data_collection/__init__.py

@@ -0,0 +1,38 @@
+from sqlalchemy import (
+    Column,
+    ForeignKey,
+    Integer,
+    MetaData,
+    String,
+    Table,
+    UniqueConstraint,
+)
+
+metadata = MetaData()
+
+stores_table = Table(
+    "stores",
+    metadata,
+    Column("id", Integer, primary_key=True),
+    Column("store_name", String, unique=True, nullable=False),
+    Column("store_logo_url", String),
+)
+
+shelves_table = Table(
+    "shelves",
+    metadata,
+    Column("id", Integer, primary_key=True),
+    Column("shelf_name", String, nullable=False),
+    Column("store_id", Integer, ForeignKey("stores.id")),
+    UniqueConstraint("shelf_name", "store_id"),
+)
+
+
+shelf_items_table = Table(
+    "shelf_items",
+    metadata,
+    Column("id", Integer, primary_key=True),
+    Column("item_name", String, nullable=False),
+    Column("shelf_id", Integer, ForeignKey("shelves.id")),
+    UniqueConstraint("item_name", "shelf_id"),
+)

data_collection/database/__init__.py

@@ -0,0 +1,2 @@
+class ExecutionFailedException(Exception):
+    pass

data_collection/database/models.py

@@ -0,0 +1,6 @@
+#!/bin/bash
+
+current_dir=$PWD
+cd /mnt/data_collection
+python workflow/execute.py
+cd $current_dir

data_collection/exceptions.py

@@ -0,0 +1,24 @@
+import json
+
+from parsel import Selector
+
+
+class Page:
+    def __init__(self, content):
+        self.content = content
+
+    @classmethod
+    def from_response(cls, response):
+        return cls(content=response)
+
+
+class HtmlPage(Page):
+    @classmethod
+    def from_html(cls, html_response):
+        return cls(content=Selector(html_response))
+
+
+class JsonPage(Page):
+    @classmethod
+    def from_json(cls, json_response):
+        return cls(content=json.loads(json_response))