104 lines
3.5 KiB
Python
104 lines
3.5 KiB
Python
# Scrapy settings for huggingface 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
|
|
|
|
BOT_NAME = "huggingface"
|
|
|
|
SPIDER_MODULES = ["huggingface.spiders"]
|
|
NEWSPIDER_MODULE = "huggingface.spiders"
|
|
|
|
# Crawl responsibly by identifying yourself (and your website) on the user-agent
|
|
USER_AGENT = "'Mozilla/5.0 (iPhone; CPU iPhone OS 16_5_1 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) CriOS/115.0.5790.130 Mobile/15E148 Safari/604.1'"
|
|
|
|
# Obey robots.txt rules
|
|
ROBOTSTXT_OBEY = False
|
|
|
|
# Configure maximum concurrent requests performed by Scrapy (default: 16)
|
|
CONCURRENT_REQUESTS = 100
|
|
|
|
# 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 = 0
|
|
# 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 = {
|
|
# "huggingface.middlewares.HuggingfaceSpiderMiddleware": 543,
|
|
# }
|
|
|
|
# Enable or disable downloader middlewares
|
|
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
|
|
DOWNLOADER_MIDDLEWARES = {
|
|
"huggingface.middlewares.RoundRobinProxyMiddleware": 100,
|
|
}
|
|
|
|
# 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 = {
|
|
"huggingface.pipelines.FilePipeline": 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
|
|
REQUEST_FINGERPRINTER_IMPLEMENTATION = "2.7"
|
|
TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
|
|
FEED_EXPORT_ENCODING = "utf-8"
|
|
|
|
PROXIES = [
|
|
"http://172.0.4.7:3128",
|
|
"http://172.0.4.8:3128",
|
|
"http://172.0.4.10:3128",
|
|
"http://172.0.4.12:3128",
|
|
]
|
|
|
|
LOG_LEVEL = 'CRITICAL'
|
|
|
|
HTTPCACHE_ENABLED = True
|