# 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

PROJECT_KEY = "current_project"
BOT_NAME = 'Comics'

SPIDER_MODULES = ['Comics.spiders']
NEWSPIDER_MODULE = 'Comics.spiders'
BASE_OUTPUT = ""
#BASE_OUTPUT = "/mnt/Comics"
OUTPUT_DIR = os.path.join(BASE_OUTPUT, "output")
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'Comics (+http://www.yourdomain.com)'
USER_AGENT = UserAgent().random
# Override the default request headers:
# Obey robots.txt rules
ROBOTSTXT_OBEY = False

HTTPERROR_ALLOWED_CODES = [ 200 , 403, 301, 302]
# Configure maximum concurrent requests performed by Scrapy (default: 16)
CONCURRENT_REQUESTS = 16 

# 允许重定向
MEDIA_ALLOW_REDIRECTS = True
# 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 = OUTPUT_DIR
IMAGES_NAME_FORMAT = "{:0>3d}"
COMIC_INFO_XML_STORE = IMAGES_STORE 
# 随机化下载延迟
# RANDOMIZE_DOWNLOAD_DELAY = True 
#重试
DOWNLOAD_DELAY = 1  # 每次请求间隔2秒
# 增加下载超时时间
DOWNLOAD_TIMEOUT = 30  # 30秒
# 增加重试之间的延迟
RETRY_DELAY = 5  # 5秒

RETRY_ENABLED = True
RETRY_TIMES = 5 # 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]
RETRY_HTTP_CODES = [408, 401, 504, 110, 500, 502, 503, 522, 524, 429]
# 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",
#    "http://proxy.local:20172",
]
# 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._utils.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.IconDownloadPipeline': 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 = 10 
# 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 = os.path.join(BASE_OUTPUT,'httpcache')
HTTPCACHE_ALLOW_PREFIXS = [ 'jpg', 'png', 'gif', 'JPG', "PNG", "JPEG"]
HTTPCACHE_PROXY_DOMAINS = [ 'r5.rmcdn3.xyz' ]
HTTPCACHE_STORAGE = 'Comics._utils.middlewares.MyFilesystemCacheStorage'

# 队列
SCHEDULER = "scrapy.core.scheduler.Scheduler"
SCHEDULER_DISK_QUEUE = "scrapy.squeues.PickleFifoDiskQueue"
SCHEDULER_MEMORY_QUEUE = "scrapy.squeues.FifoMemoryQueue"

# Logging configuration
LOG_LEVEL = "INFO" # 日志等级
LOG_STDOUT = True # 标准化输出

CBZ_EXPORT_PATH = os.path.join(BASE_OUTPUT,"CBZ")
OLD_CBZ_EXPORT_PATH = os.path.join(BASE_OUTPUT,"Old_CBZ")
#数据导出类 排序
COMIC_INFO_XML_FILE = "ComicInfo.xml"
COMIC_INFO_XSD_FILE = "Comics/assets/ComicInfo_2.1.xsd"