mirror of
https://github.com/Mueller-Patrick/Betterzon.git
synced 2024-12-24 12:35:12 +00:00
26ba21156a
* BETTERZON-58: Basic Functionality with scrapy * Added independent crawler function, yielding price * moved logic to amazon.py * . * moved scrapy files to unused folder * Added basic amazon crawler using beautifulsoup4 * Connected Api to Crawler * Fixed string concatenation for sql statement in getProductLinksForProduct * BETTERZON-58: Fixing SQL insert * BETTERZON-58: Adding access key verification * BETTERZON-58: Fixing API endpoint of the crawler - The list of products in the API request was treated like a string and henceforth, only the first product has been crawled * Added another selector for price on amazon (does not work for books) Co-authored-by: root <root@DESKTOP-ARBPL82.localdomain> Co-authored-by: Patrick Müller <patrick@mueller-patrick.tech> Co-authored-by: Patrick <50352812+Mueller-Patrick@users.noreply.github.com>
89 lines
2.6 KiB
Python
89 lines
2.6 KiB
Python
import logging
|
|
|
|
import pymysql
|
|
import os
|
|
|
|
|
|
def __getConnection__() -> pymysql.Connection:
|
|
"""
|
|
Opens a new pymysql connection and returns it
|
|
:return: A pymysql Connection object
|
|
"""
|
|
logger = logging.getLogger()
|
|
try:
|
|
conn = pymysql.connect(
|
|
user=os.environ['BETTERZON_CRAWLER_USER'],
|
|
password=os.environ['BETTERZON_CRAWLER_PASSWORD'],
|
|
host=os.environ['BETTERZON_CRAWLER_HOST'],
|
|
port=3306,
|
|
database=os.environ['BETTERZON_CRAWLER_DB']
|
|
)
|
|
|
|
return conn
|
|
except pymysql.Error as e:
|
|
logger.error('SQL Connection error: %s', e)
|
|
return
|
|
|
|
|
|
def getProductsForVendor(vendor_id: int) -> [{}]:
|
|
"""
|
|
Queries the product links for all products of the given shop
|
|
:param vendor_id: The vendor / shop to query products for
|
|
:return: A list of product objects, each having the following parameters:
|
|
product_id, vendor_id, url
|
|
"""
|
|
conn = __getConnection__()
|
|
cur = conn.cursor()
|
|
|
|
query = 'SELECT product_id, url FROM product_links WHERE vendor_id = %s'
|
|
|
|
cur.execute(query, (vendor_id,))
|
|
|
|
products = list(map(lambda x: {'product_id': x[0], 'vendor_id': vendor_id, 'url': x[1]}, cur.fetchall()))
|
|
|
|
return products
|
|
|
|
def getProductLinksForProduct(product_id: int) -> [dict]:
|
|
"""
|
|
Queries all the product links for the given product
|
|
:param product_id: The product to query data for
|
|
:return: A list of product objects, each having the following parameters:
|
|
product_id, vendor_id, url
|
|
"""
|
|
conn = __getConnection__()
|
|
cur = conn.cursor()
|
|
|
|
query = 'SELECT vendor_id, url FROM product_links WHERE product_id = %s'
|
|
cur.execute(query, (product_id,))
|
|
|
|
products = list(map(lambda x: {'product_id': product_id, 'vendor_id': x[0], 'url': x[1]}, cur.fetchall()))
|
|
|
|
return products
|
|
|
|
|
|
|
|
def insertData(data_to_insert: [tuple]) -> bool:
|
|
"""
|
|
Inserts the given list of tuples into the DB
|
|
:param dataToInsert: A list of tuples, where each tuple has to contain product id, vendor id and the price
|
|
in exactly this order
|
|
:return: If the insert was successful
|
|
"""
|
|
conn = __getConnection__()
|
|
cur = conn.cursor()
|
|
|
|
query = 'INSERT INTO prices (product_id, vendor_id, price_in_cents, timestamp) VALUES (%s, %s, %s, NOW())'
|
|
|
|
affectedRows = cur.executemany(query, data_to_insert)
|
|
|
|
if affectedRows != len(data_to_insert):
|
|
# Something went wrong, revert the changes
|
|
conn.rollback()
|
|
else:
|
|
conn.commit()
|
|
|
|
cur.close()
|
|
conn.close()
|
|
|
|
return affectedRows == len(data_to_insert)
|