From a92af197308a7a4264218b6c823b09dcef81a22a Mon Sep 17 00:00:00 2001
From: Gusev Anton <gusev_aa@groupbwt.com>
Date: Wed, 12 Jun 2019 19:13:11 +0300
Subject: [PATCH] change book model
---
src/database/README | 1 +
src/database/env.py | 83 +++++++++++++++++++
src/database/models/Book.py | 27 ++++++
src/database/models/Model.py | 7 ++
src/database/models/__init__.py | 0
src/database/script.py.mako | 25 ++++++
.../versions/f36bd8e8d8c1_add_books_table.py | 46 ++++++++++
src/items/BookItem.py | 9 +-
src/spiders/books_spider.py | 23 ++---
9 files changed, 205 insertions(+), 16 deletions(-)
create mode 100644 src/database/README
create mode 100644 src/database/env.py
create mode 100644 src/database/models/Book.py
create mode 100644 src/database/models/Model.py
create mode 100644 src/database/models/__init__.py
create mode 100644 src/database/script.py.mako
create mode 100644 src/database/versions/f36bd8e8d8c1_add_books_table.py
diff --git a/src/database/README b/src/database/README
new file mode 100644
index 0000000..98e4f9c
--- /dev/null
+++ b/src/database/README
@@ -0,0 +1 @@
+Generic single-database configuration.
\ No newline at end of file
diff --git a/src/database/env.py b/src/database/env.py
new file mode 100644
index 0000000..62621fb
--- /dev/null
+++ b/src/database/env.py
@@ -0,0 +1,83 @@
+
+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()
diff --git a/src/database/models/Book.py b/src/database/models/Book.py
new file mode 100644
index 0000000..8110e56
--- /dev/null
+++ b/src/database/models/Book.py
@@ -0,0 +1,27 @@
+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)
+
+ title = Column(String(255), unique=True, nullable=False, index=True)
+ description = Column(Text)
+ image_path = Column(String(255))
+ rating = Column(SmallInteger)
+
+ upc = Column(String(32))
+ product_type = Column(String(32)) # -> Books
+ price_excl_tax = Column(Numeric(6, 2))
+ price_incl_tax = Column(Numeric(6, 2))
+ tax = Column(Numeric(6, 2))
+ in_stock = Column(Integer)
+ count_reviews = Column(Integer)
+
+ category = Column(String(32))
+
+ currency_type = Column(String(4))
diff --git a/src/database/models/Model.py b/src/database/models/Model.py
new file mode 100644
index 0000000..5cdcba2
--- /dev/null
+++ b/src/database/models/Model.py
@@ -0,0 +1,7 @@
+
+
+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
diff --git a/src/database/models/__init__.py b/src/database/models/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/src/database/script.py.mako b/src/database/script.py.mako
new file mode 100644
index 0000000..916ce7f
--- /dev/null
+++ b/src/database/script.py.mako
@@ -0,0 +1,25 @@
+# -*- 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"}
diff --git a/src/database/versions/f36bd8e8d8c1_add_books_table.py b/src/database/versions/f36bd8e8d8c1_add_books_table.py
new file mode 100644
index 0000000..42df59c
--- /dev/null
+++ b/src/database/versions/f36bd8e8d8c1_add_books_table.py
@@ -0,0 +1,46 @@
+"""add books table
+
+Revision ID: f36bd8e8d8c1
+Revises:
+Create Date: 2019-06-12 18:58:58.292063
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = 'f36bd8e8d8c1'
+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('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')
+ )
+ op.create_index(op.f('ix_books_title'), 'books', ['title'], unique=True)
+ # ### 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_table('books')
+ # ### end Alembic commands ###
diff --git a/src/items/BookItem.py b/src/items/BookItem.py
index 205efbc..2387741 100644
--- a/src/items/BookItem.py
+++ b/src/items/BookItem.py
@@ -13,7 +13,8 @@ class BookItem(scrapy.Item):
title = scrapy.Field()
description = scrapy.Field()
- image = scrapy.Field()
+ image_urls = scrapy.Field()
+ images = scrapy.Field()
rating = scrapy.Field()
upc = scrapy.Field()
@@ -22,4 +23,8 @@ class BookItem(scrapy.Item):
price_incl_tax = scrapy.Field()
tax = scrapy.Field()
in_stock = scrapy.Field()
- count_reviews = scrapy.Field()
\ No newline at end of file
+ count_reviews = scrapy.Field()
+
+ category = scrapy.Field()
+
+ currency_type = scrapy.Field()
diff --git a/src/spiders/books_spider.py b/src/spiders/books_spider.py
index 6c10a13..d8c4c13 100644
--- a/src/spiders/books_spider.py
+++ b/src/spiders/books_spider.py
@@ -5,20 +5,14 @@ from database.connectors.BookConnector import BookConnector
import logging
-class BooksSpider(scrapy.Spider):
class BooksSpider(BookConnector, scrapy.Spider):
name = 'books'
- start_urls = [
- 'http://books.toscrape.com/catalogue/page-1.html'
- ]
- ITEM_PIPELINES = {
- 'tutorial.pipelines.PricePipeline': 1,
- }
+ start_urls = ['http://books.toscrape.com/']
def parse(self, response):
# follow links to book pages
- for href in response.css('div.image_container a::attr(href)'): # TODO
- yield response.follow(href, self.parse_book)
+ for idx, href in enumerate(response.css('div.image_container a::attr(href)')): # TODO delete enumerate
+ yield response.follow(href, self.parse_book)
# pagination
next_page = response.css('li.next a::attr(href)').get()
@@ -30,18 +24,19 @@ class BooksSpider(BookConnector, scrapy.Spider):
table_data = response.css('table td::text').getall()
book.update({
- 'url': response.url,
'title': response.css('div.product_main h1::text').get(),
'description': response.xpath("//*[@id='product_description']/following::p/text()").get(),
- 'image': response.urljoin(response.css('div.active img::attr(src)').get()),
+ 'image_urls': [response.urljoin(response.css('div.active img::attr(src)').get())],
'rating': self._get_rating(response.css('p.star-rating::attr(class)').get().split(' ')),
'upc': table_data[0],
'product_type': table_data[1],
- 'price_excl_tax': table_data[2],
- 'price_incl_tax': table_data[3],
- 'tax': table_data[4],
+ 'price_excl_tax': table_data[2][1:],
+ 'price_incl_tax': table_data[3][1:],
+ 'tax': table_data[4][1:],
'in_stock': int(re.search(r'\d+', table_data[5]).group()),
'count_reviews': int(table_data[6]),
+ 'currency_type': table_data[2][0],
+ 'category': response.css('ul.breadcrumb li:nth-child(3) a::text').get()
})
yield book
--
GitLab