138 lines
4.5 KiB
Python
138 lines
4.5 KiB
Python
# Scrapy settings for Comics 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 fake_useragent import UserAgent
|
|
import os
|
|
|
|
BOT_NAME = 'Comics'
|
|
|
|
SPIDER_MODULES = ['Comics.spiders']
|
|
NEWSPIDER_MODULE = 'Comics.spiders'
|
|
|
|
OUTPUT_DIR = "output"
|
|
# Crawl responsibly by identifying yourself (and your website) on the user-agent
|
|
#USER_AGENT = 'Comics (+http://www.yourdomain.com)'
|
|
USER_AGENT = UserAgent().random
|
|
# Obey robots.txt rules
|
|
ROBOTSTXT_OBEY = False
|
|
|
|
HTTPERROR_ALLOWED_CODES = [ 200 , 403]
|
|
# Configure maximum concurrent requests performed by Scrapy (default: 16)
|
|
CONCURRENT_REQUESTS = 16
|
|
|
|
# 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
|
|
IMAGES_STORE = os.path.join(OUTPUT_DIR, 'images')
|
|
IMAGES_NAME_FORMAT = "{:0>3d}"
|
|
COMIC_INFO_XML_STORE = IMAGES_STORE
|
|
DOWNLOAD_DELAY = 0
|
|
#重试
|
|
RETRY_ENABLED = True
|
|
RETRY_TIMES = 10 # 想重试几次就写几
|
|
# 下面这行可要可不要
|
|
RETRY_HTTP_CODES = [500, 502, 503, 504, 408, 401]
|
|
# The download delay setting will honor only one of:
|
|
CONCURRENT_REQUESTS_PER_DOMAIN = 16
|
|
CONCURRENT_REQUESTS_PER_IP = 16
|
|
PROXY_LIST = [
|
|
"http://127.0.0.1:7890",
|
|
]
|
|
# 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 = {
|
|
# 'Comics.middlewares.ComicsSpiderMiddleware': 543,
|
|
# 'Comics.middlewares.ProxyMiddleware' : 100,
|
|
# 'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware': 400,
|
|
#}
|
|
|
|
# Enable or disable downloader middlewares
|
|
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
|
|
DOWNLOADER_MIDDLEWARES = {
|
|
# 'Comics.middlewares.ComicsDownloaderMiddleware': 543,
|
|
# 'scrapy.downloadermiddlewares.retry.RetryMiddleware': 500,
|
|
'Comics.middlewares.ProxyMiddleware': 100,
|
|
'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware': 400,
|
|
}
|
|
|
|
# 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 = {
|
|
# 'scrapy.pipelines.images.ImagesPipeline' : 1,
|
|
'Comics.pipelines.ComicsPipeline': 300,
|
|
# 'Comics.pipelines.ImageParsePipeline': 400,
|
|
'Comics.pipelines.ImgDownloadPipeline': 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 = [500, 502, 404]
|
|
#HTTPCACHE_STORAGE = 'Comics.middlewares.MyFilesystemCacheStorage'
|
|
HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
|
|
|
|
# Logging configuration
|
|
LOG_LEVEL = "INFO" # 日志等级
|
|
LOG_STDOUT = True # 标准化输出
|
|
|
|
CBZ_EXPORT_PATH = "CBZ"
|
|
#数据导出类 排序
|
|
COMIC_INFO_XML_FILE = "ComicInfo.xml"
|
|
COMIC_INFO_FIELDS_TO_EXPORT = [
|
|
"Title",
|
|
"Series",
|
|
"Number",
|
|
"SeriesGroup",
|
|
"Summary",
|
|
"Year",
|
|
"Month",
|
|
"Day",
|
|
"Writer",
|
|
"Publisher",
|
|
"Genre",
|
|
"Tags",
|
|
"Web",
|
|
"PageCount",
|
|
"LanguageISO",
|
|
"AgeRating",
|
|
"Pages"
|
|
]
|