settings.py

# Scrapy settings for beatportscraper project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://docs.scrapy.org/en/latest/topics/settings.html
#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html
import json
import os
import psycopg2


BOT_NAME = "beatportscraper"

SPIDER_MODULES = ["beatportscraper.spiders"]
NEWSPIDER_MODULE = "beatportscraper.spiders"

# FEEDS = {
#     'data.csv': {'format': 'csv'}
# }

parent_directory = os.path.split(os.path.dirname(__file__))[0]
file_path = os.path.join(parent_directory, 'credentials.json')

with open(file_path, 'r') as f:
    credentials = json.load(f)

POSTGRES_HOSTNAME = credentials["hostname"]
POSTGRES_USERNAME = credentials["username"]
POSTGRES_PASSWORD = credentials["password"]
POSTGRES_DATABASE = credentials["database"]
SCRAPEOPS_API_KEY = credentials["scrapeops_api"]
SCRAPEOPS_NUM_RES = 5
SCRAPEOPS_ENPOINT = 'https://headers.scrapeops.io/v1/browser-headers'

# GET LATEST ENTRY FROM POSTGRES

# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = "beatportscraper (+http://www.yourdomain.com)"

# Obey robots.txt rules
ROBOTSTXT_OBEY = False


# Configure maximum concurrent requests performed by Scrapy (default: 16)
# CONCURRENT_REQUESTS = 1

# Configure a delay for requests for the same website (default: 0)
# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
#    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
#    "Accept-Language": "en",
#}

# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
SPIDER_MIDDLEWARES = {
#   "beatportscraper.middlewares.BeatportscraperSpiderMiddleware": 543,
    "scrapy_deltafetch.DeltaFetch": 200,
}

DELTAFETCH_ENABLED = True
# DELTAFETCH_RESET = True

# RUN LINE TO RESET DELTAFETCH

# LOG_ENABLED = True
# LOG_FILE = "log.log"
# LOG_FILE_APPEND = False


# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
#    "beatportscraper.middlewares.BeatportscraperDownloaderMiddleware": 543,
    "beatportscraper.middlewares.ScrapeOpsFakeBrowserHeaders": 500,
}

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
EXTENSIONS = {
   "scrapy.extensions.closespider.CloseSpider": 15,
}

CLOSESPIDER_TIMEOUT_NO_ITEM = 15

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
    "beatportscraper.pipelines.BeatportscraperPipeline": 400,
    "beatportscraper.pipelines.SaveToPostgresPipeline": 500,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = "httpcache"
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = "scrapy.extensions.httpcache.FilesystemCacheStorage"

# Set settings whose default value is deprecated to a future-proof value
REQUEST_FINGERPRINTER_IMPLEMENTATION = "2.7"
TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
FEED_EXPORT_ENCODING = "utf-8"