Develop

.gitignore

 .*
+image
 !.gitignore
+!.env.example
+alembic.ini
 *.pyc
-*.json
\ No newline at end of file
+__pycache__
+*.json
+src/spiders/test_spider.py
+*.log
\ No newline at end of file

README.md

+1. Rename .env.example to .env and set your settings
+2. Rename alembic.ini.example to alembic.ini and set sqlalchemy.url field
+3. Install dependencies from requirments.txt file
+4. Create tables for database using sql\create-dump.sql or apply migration using the command "alembic upgrade head" in src directory
+5. In src directory use "scrapy crawl books" command for start parsing.
\ No newline at end of file

requirments.txt

+alembic==1.0.10
+asn1crypto==0.24.0
+attrs==19.1.0
+Automat==0.7.0
+cffi==1.12.3
+constantly==15.1.0
+cryptography==2.7
+cssselect==1.0.3
+hyperlink==19.0.0
+idna==2.8
+incremental==17.5.0
+lxml==4.3.4
+Mako==1.0.12
+MarkupSafe==1.1.1
+parsel==1.5.1
+Pillow==6.0.0
+pyasn1==0.4.5
+pyasn1-modules==0.2.5
+pycparser==2.19
+PyDispatcher==2.0.5
+PyHamcrest==1.9.0
+PyMySQL==0.9.3
+pyOpenSSL==19.0.0
+pypiwin32==223
+python-dateutil==2.8.0
+python-dotenv==0.10.3
+python-editor==1.0.4
+pywin32==224
+queuelib==1.5.0
+Scrapy==1.6.0
+service-identity==18.1.0
+six==1.12.0
+SQLAlchemy==1.3.4
+Twisted==19.2.1
+w3lib==1.20.0
+zope.interface==4.6.0

sql/create-dump.sql

+-- --------------------------------------------------------
+-- Хост:                         127.0.0.1
+-- Версия сервера:               8.0.15 - MySQL Community Server - GPL
+-- Операционная система:         Win64
+-- HeidiSQL Версия:              10.1.0.5464
+-- --------------------------------------------------------
+
+/*!40101 SET @OLD_CHARACTER_SET_CLIENT=@@CHARACTER_SET_CLIENT */;
+/*!40101 SET NAMES utf8 */;
+/*!50503 SET NAMES utf8mb4 */;
+/*!40014 SET @OLD_FOREIGN_KEY_CHECKS=@@FOREIGN_KEY_CHECKS, FOREIGN_KEY_CHECKS=0 */;
+/*!40101 SET @OLD_SQL_MODE=@@SQL_MODE, SQL_MODE='NO_AUTO_VALUE_ON_ZERO' */;
+
+-- Дамп структуры для таблица db-scrapy-tutorial.alembic_version
+CREATE TABLE IF NOT EXISTS `alembic_version` (
+  `version_num` varchar(32) NOT NULL,
+  PRIMARY KEY (`version_num`)
+) ENGINE=InnoDB DEFAULT CHARSET=utf8;
+
+-- Экспортируемые данные не выделены.
+-- Дамп структуры для таблица db-scrapy-tutorial.books
+CREATE TABLE IF NOT EXISTS `books` (
+  `id` int(11) NOT NULL AUTO_INCREMENT,
+  `url` varchar(255) DEFAULT NULL,
+  `title` varchar(255) NOT NULL,
+  `description` text,
+  `image_path` varchar(255) DEFAULT NULL,
+  `rating` smallint(6) DEFAULT NULL,
+  `upc` varchar(32) DEFAULT NULL,
+  `product_type` varchar(32) DEFAULT NULL,
+  `price_excl_tax` decimal(6,2) DEFAULT NULL,
+  `price_incl_tax` decimal(6,2) DEFAULT NULL,
+  `tax` decimal(6,2) DEFAULT NULL,
+  `in_stock` int(11) DEFAULT NULL,
+  `count_reviews` int(11) DEFAULT NULL,
+  `category` varchar(32) DEFAULT NULL,
+  `currency_type` varchar(4) DEFAULT NULL,
+  PRIMARY KEY (`id`),
+  UNIQUE KEY `upc` (`upc`),
+  KEY `ix_books_category` (`category`),
+  KEY `ix_books_count_reviews` (`count_reviews`),
+  KEY `ix_books_currency_type` (`currency_type`),
+  KEY `ix_books_in_stock` (`in_stock`),
+  KEY `ix_books_price_excl_tax` (`price_excl_tax`),
+  KEY `ix_books_price_incl_tax` (`price_incl_tax`),
+  KEY `ix_books_product_type` (`product_type`),
+  KEY `ix_books_rating` (`rating`),
+  KEY `ix_books_tax` (`tax`),
+  KEY `ix_books_title` (`title`)
+) ENGINE=InnoDB AUTO_INCREMENT=2001 DEFAULT CHARSET=utf8;
+
+-- Экспортируемые данные не выделены.
+/*!40101 SET SQL_MODE=IFNULL(@OLD_SQL_MODE, '') */;
+/*!40014 SET FOREIGN_KEY_CHECKS=IF(@OLD_FOREIGN_KEY_CHECKS IS NULL, 1, @OLD_FOREIGN_KEY_CHECKS) */;
+/*!40101 SET CHARACTER_SET_CLIENT=@OLD_CHARACTER_SET_CLIENT */;

src/.env.example

+### DATABASE CONFIG
+### and need set settings alembic.ini
+DB_CONNECTION=mysql+pymysql
+DB_HOST=127.0.0.1
+DB_PORT=3306
+DB_DATABASE=database
+DB_USERNAME=username
+DB_PASSWORD=secret
+
+### MAIL CONFIG
+MAIL_FROM = 'example@example.com'
+MAIL_USER = 'example@example.com'
+MAIL_PASS = 'secret'
+MAIL_HOST = 'smtp.gmail.com'
+MAIL_PORT = 465
+MAIL_TLS = False
+MAIL_SSL = True
+
+### LOGGER CONFIG
+### levels: DEBUG, INFO, WARNING, ERROR
+LOG_LEVEL = DEBUG
+LOG_FILE = ../log.log
+LOG_ENABLED = False
+LOG_FORMAT = '%(asctime)s - %(levelname)s - %(name)s  : %(message)s'
+LOG_STDOUT = False
+
+
+

src/alembic.ini.example

+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = database
+
+# template used to generate migration files
+# file_template = %%(rev)s_%%(slug)s
+
+# timezone to use when rendering the date
+# within the migration file as well as the filename.
+# string value is passed to dateutil.tz.gettz()file_template
+# 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 database/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path
+# version_locations = %(here)s/bar %(here)s/bat database/versions
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+# sqlalchemy.url = driver://user:pass@host:port/dbname
+sqlalchemy.url = mysql+pymysql://user:password@localhost/databasename
+
+
+# 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

src/database/Connector.py

+from sqlalchemy import create_engine
+from sqlalchemy.orm import sessionmaker
+from scrapy.conf import settings
+from utils.Singleton import Singleton
+
+
+class Connector(metaclass=Singleton):
+    __connection = None
+    __engine = create_engine(settings['CONNECTION_STRING'])
+    __Session = sessionmaker(bind=__engine)
+
+    @staticmethod
+    def get_session():
+        return Connector.__Session()
+
+    @staticmethod
+    def get_connection():
+        if not Connector.__connection:
+            Connector.__connection = Connector.__engine.connect()
+        return Connector.__connection

src/database/README

+Generic single-database configuration.
\ No newline at end of file

src/database/connectors/BookConnector.py

+from ..Connector import Connector
+from ..models.Book import Book
+
+
+class BookConnector(Connector):
+    def save_book(self, item):
+        session = self.get_session()
+
+        book = Book()
+        book.update(item)
+        book.image_path = item['images'][0]['path']
+
+        session.add(book)
+        session.commit()
\ No newline at end of file

src/database/env.py

+
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+import os
+import sys
+
+
+# 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.
+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 = None
+
+# added
+sys.path.insert(0, '\\'.join(os.path.dirname(os.path.abspath(__file__)).split('\\')[:-1]))
+from database.models.Book import Book
+target_metadata = [Book.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():
+    """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
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online():
+    """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()

src/database/models/Book.py

+from sqlalchemy import Column, Integer, String, Text, SmallInteger, Numeric
+from sqlalchemy.ext.declarative import declarative_base
+from .Model import Model
+
+Base = declarative_base()
+
+
+class Book(Base, Model):
+    __tablename__ = 'books'
+    id = Column(Integer, primary_key=True)
+    url = Column(String(255))
+
+    title = Column(String(255), nullable=False, index=True)
+    description = Column(Text)
+    image_path = Column(String(255))
+    rating = Column(SmallInteger, index=True)
+
+    upc = Column(String(32), unique=True)
+    product_type = Column(String(32), index=True)
+    price_excl_tax = Column(Numeric(6, 2), index=True)
+    price_incl_tax = Column(Numeric(6, 2), index=True)
+    tax = Column(Numeric(6, 2), index=True)
+    in_stock = Column(Integer, index=True)
+    count_reviews = Column(Integer, index=True)
+
+    category = Column(String(32), index=True)
+
+    currency_type = Column(String(4), index=True)

src/database/models/Model.py

+
+
+class Model:
+    def update(self, dct):
+        for key, value in dct.items():
+            if hasattr(self, key):
+                setattr(self, key, value)
\ No newline at end of file

src/database/script.py.mako

+# -*- coding: UTF-8 -*-
+"""${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():
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade():
+    ${downgrades if downgrades else "pass"}

src/database/versions/3217c19ef3a6_create_books_table.py

+"""create books table
+
+Revision ID: 3217c19ef3a6
+Revises: 
+Create Date: 2019-06-13 18:27:06.732796
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = '3217c19ef3a6'
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('books',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('url', sa.String(length=255), nullable=True),
+    sa.Column('title', sa.String(length=255), nullable=False),
+    sa.Column('description', sa.Text(), nullable=True),
+    sa.Column('image_path', sa.String(length=255), nullable=True),
+    sa.Column('rating', sa.SmallInteger(), nullable=True),
+    sa.Column('upc', sa.String(length=32), nullable=True),
+    sa.Column('product_type', sa.String(length=32), nullable=True),
+    sa.Column('price_excl_tax', sa.Numeric(precision=6, scale=2), nullable=True),
+    sa.Column('price_incl_tax', sa.Numeric(precision=6, scale=2), nullable=True),
+    sa.Column('tax', sa.Numeric(precision=6, scale=2), nullable=True),
+    sa.Column('in_stock', sa.Integer(), nullable=True),
+    sa.Column('count_reviews', sa.Integer(), nullable=True),
+    sa.Column('category', sa.String(length=32), nullable=True),
+    sa.Column('currency_type', sa.String(length=4), nullable=True),
+    sa.PrimaryKeyConstraint('id'),
+    sa.UniqueConstraint('upc')
+    )
+    op.create_index(op.f('ix_books_category'), 'books', ['category'], unique=False)
+    op.create_index(op.f('ix_books_count_reviews'), 'books', ['count_reviews'], unique=False)
+    op.create_index(op.f('ix_books_currency_type'), 'books', ['currency_type'], unique=False)
+    op.create_index(op.f('ix_books_in_stock'), 'books', ['in_stock'], unique=False)
+    op.create_index(op.f('ix_books_price_excl_tax'), 'books', ['price_excl_tax'], unique=False)
+    op.create_index(op.f('ix_books_price_incl_tax'), 'books', ['price_incl_tax'], unique=False)
+    op.create_index(op.f('ix_books_product_type'), 'books', ['product_type'], unique=False)
+    op.create_index(op.f('ix_books_rating'), 'books', ['rating'], unique=False)
+    op.create_index(op.f('ix_books_tax'), 'books', ['tax'], unique=False)
+    op.create_index(op.f('ix_books_title'), 'books', ['title'], unique=False)
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index(op.f('ix_books_title'), table_name='books')
+    op.drop_index(op.f('ix_books_tax'), table_name='books')
+    op.drop_index(op.f('ix_books_rating'), table_name='books')
+    op.drop_index(op.f('ix_books_product_type'), table_name='books')
+    op.drop_index(op.f('ix_books_price_incl_tax'), table_name='books')
+    op.drop_index(op.f('ix_books_price_excl_tax'), table_name='books')
+    op.drop_index(op.f('ix_books_in_stock'), table_name='books')
+    op.drop_index(op.f('ix_books_currency_type'), table_name='books')
+    op.drop_index(op.f('ix_books_count_reviews'), table_name='books')
+    op.drop_index(op.f('ix_books_category'), table_name='books')
+    op.drop_table('books')
+    # ### end Alembic commands ###

src/items/BookItem.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class BookItem(scrapy.Item):
+    url = scrapy.Field()
+
+    title = scrapy.Field()
+    description = scrapy.Field()
+    image_urls = scrapy.Field()
+    images = scrapy.Field()
+    rating = scrapy.Field()
+
+    upc = scrapy.Field()
+    product_type = scrapy.Field()
+    price_excl_tax = scrapy.Field()
+    price_incl_tax = scrapy.Field()
+    tax = scrapy.Field()
+    in_stock = scrapy.Field()
+    count_reviews = scrapy.Field()
+
+    category = scrapy.Field()
+
+    currency_type = scrapy.Field()