106 lines
3.5 KiB
Python
106 lines
3.5 KiB
Python
# Scrapy settings for crawler2 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 scrapy.settings.default_settings import RANDOMIZE_DOWNLOAD_DELAY, RETRY_TIMES, RETRY_HTTP_CODES, \
|
|
DOWNLOADER_MIDDLEWARES
|
|
|
|
BOT_NAME = "crawler2"
|
|
|
|
SPIDER_MODULES = ["crawler2.spiders"]
|
|
NEWSPIDER_MODULE = "crawler2.spiders"
|
|
|
|
ADDONS = {}
|
|
|
|
|
|
# Crawl responsibly by identifying yourself (and your website) on the user-agent
|
|
USER_AGENT = "Mozilla/5.0 (compatible; crawler2/+thomassazeratdev@gmail.com)"
|
|
|
|
# Obey robots.txt rules
|
|
ROBOTSTXT_OBEY = True
|
|
DOWNLOAD_DELAY = 1
|
|
RANDOMIZE_DOWNLOAD_DELAY = True
|
|
|
|
# Concurrency and throttling settings
|
|
CONCURRENT_REQUESTS = 4
|
|
CONCURRENT_REQUESTS_PER_DOMAIN = 2
|
|
CONCURRENT_REQUESTS_PER_IP = 2
|
|
|
|
# Errors handling
|
|
RETRY_TIMES = 3
|
|
RETRY_HTTP_CODES = [500, 502, 503, 504, 400, 403, 404, 408]
|
|
|
|
DOWNLOADER_MIDDLEWARES = {
|
|
'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware': None, # Désactive l'user-agent par défaut
|
|
'scrapy.downloadermiddlewares.retry.RetryMiddleware': 90, # Enable the retries
|
|
}
|
|
|
|
ITEM_PIPELINES = {
|
|
'crawler2.pipelines.CleanTextPipeline': 300, # Nettoyage des données
|
|
'crawler2.pipelines.MongoDBPipeline': 300, # Sauvegarde sur Mongo
|
|
}
|
|
|
|
# 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 = {
|
|
# "crawler2.middlewares.Crawler2SpiderMiddleware": 543,
|
|
#}
|
|
|
|
# Enable or disable downloader middlewares
|
|
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
|
|
#DOWNLOADER_MIDDLEWARES = {
|
|
# "crawler2.middlewares.Crawler2DownloaderMiddleware": 543,
|
|
#}
|
|
|
|
# Enable or disable extensions
|
|
# See https://docs.scrapy.org/en/latest/topics/extensions.html
|
|
#EXTENSIONS = {
|
|
# "scrapy.extensions.telnet.TelnetConsole": None,
|
|
#}
|
|
|
|
# Configure item pipelines
|
|
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
|
|
#ITEM_PIPELINES = {
|
|
# "crawler2.pipelines.Crawler2Pipeline": 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 = 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
|
|
FEED_EXPORT_ENCODING = "utf-8"
|