Files
2024-12-20 23:02:51 +05:30

117 lines
3.9 KiB
Python

# Scrapy settings for mediafusion_scrapy 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
from db.config import settings
BOT_NAME = "mediafusion_scrapy"
SPIDER_MODULES = ["mediafusion_scrapy.spiders"]
NEWSPIDER_MODULE = "mediafusion_scrapy.spiders"
# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = "Mozilla/5.0 (Linux; Android 6.0.1; Nexus 5X Build/MMB29P) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.96 Mobile Safari/537.36 (compatible; Google Search Console)"
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
# Configure maximum concurrent requests performed by Scrapy (default: 16)
CONCURRENT_REQUESTS = 10
# 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 = {
"mediafusion_scrapy.middlewares.DatabaseInitializationMiddleware": 100,
}
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
"mediafusion_scrapy.middlewares.FlaresolverrMiddleware": 542,
"mediafusion_scrapy.middlewares.TooManyRequestsRetryMiddleware": 543,
"scrapy.downloadermiddlewares.retry.RetryMiddleware": 550,
}
EXTENSIONS = {
"mediafusion_scrapy.extensions.CloseSpiderExtended": 100,
}
# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
# ITEM_PIPELINES = {
# "mediafusion_scrapy.pipelines.MediafusionScrapyPipeline": 300,
# }
# 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 = (
900 # 15 minutes to avoid a multiple scraping task of same time.
)
HTTPCACHE_DIR = "/tmp/httpcache"
HTTPCACHE_IGNORE_HTTP_CODES = [500, 502, 503, 504, 522, 524, 408, 429]
HTTPCACHE_STORAGE = "scrapy.extensions.httpcache.FilesystemCacheStorage"
# HTTPCACHE_POLICY = "scrapy.extensions.httpcache.RFC2616Policy"
TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
FEED_EXPORT_ENCODING = "utf-8"
LOG_LEVEL = "INFO"
STATS_CLASS = "mediafusion_scrapy.custom_stats.RedisStatsCollector"
RETRY_ENABLED = True
RETRY_HTTP_CODES = [
500,
502,
503,
504,
522,
524,
408,
403,
] # 429 is handled by the middleware
RETRY_TIMES = 5
FLARESOLVERR_URL = settings.flaresolverr_url
CLOSESPIDER_TIMEOUT_NO_ITEM = 600 # 10 minutes