177 lines
7.2 KiB
Python
177 lines
7.2 KiB
Python
# -*- coding: utf-8 -*-
|
||
|
||
BOT_NAME = 'WebsiteSpider'
|
||
|
||
SPIDER_MODULES = ['WebsiteSpider.spiders']
|
||
NEWSPIDER_MODULE = 'WebsiteSpider.spiders'
|
||
|
||
SCHEDULER = "scrapy_redis.scheduler.Scheduler"
|
||
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
|
||
SCHEDULER_PERSIST = True
|
||
|
||
SELENIUM_DRIVER_NAME = 'firefox'
|
||
SELENIUM_DRIVER_EXECUTABLE_PATH = [
|
||
'http://10.55.13.121:28095',
|
||
# 'http://10.55.13.108:28095',
|
||
'http://10.55.13.3:28095',
|
||
'http://74.121.148.204:28095'
|
||
]
|
||
SELENIUM_DRIVER_ARGUMENTS = ['-headless'] # '--headless' if using chrome instead of firefox
|
||
SELENIUM_DRIVER_PREFERENCES = {
|
||
"permissions.default.stylesheet": 2
|
||
# "permissions.default.image": 2
|
||
}
|
||
|
||
PROXY_SERVICE = 'http://107.182.191.3:6800'
|
||
PER_BATCH_IP_USE_TIMES = 5 # 代理中间件每次从ip池获取一批ip，定义这批ip使用次数，达到次数后重新从ip池获取新的一批
|
||
|
||
# REDIS_HOST = '38.54.94.107'
|
||
# REDIS_PORT = '28097'
|
||
# REDIS_HOST = '10.55.13.3'
|
||
# REDIS_PORT = '7379'
|
||
REDIS_HOST = '107.182.191.3'
|
||
REDIS_PORT = 7379
|
||
REDIS_PWD = 'jlkj-841-2-redis'
|
||
REDIS_PARAMS = {
|
||
'password': 'jlkj-841-2-redis',
|
||
}
|
||
|
||
USCARRIERS_KEY = 'USCARRIERS_ID'
|
||
|
||
ZIP_FILE_PATH = ''
|
||
# KAFKA_PROCESS_QUEUE = ['stream-protobuf']
|
||
KAFKA_PROCESS_QUEUE = ['stream-protobuf', 'stream-db']
|
||
KAFKA_SERVER = '47.113.231.200:9092'
|
||
|
||
RANDOMIZE_DOWNLOAD_DELAY = True
|
||
|
||
# If True, it uses redis' ``SPOP`` operation. You have to use the ``SADD``
|
||
# command to add URLs to the redis queue. This could be useful if you
|
||
# want to avoid duplicates in your start urls list and the order of
|
||
# processing does not matter.
|
||
# REDIS_START_URLS_AS_SET = True
|
||
|
||
# If True, it uses redis ``zrevrange`` and ``zremrangebyrank`` operation. You have to use the ``zadd``
|
||
# command to add URLS and Scores to redis queue. This could be useful if you
|
||
# want to use priority and avoid duplicates in your start urls list.
|
||
REDIS_START_URLS_AS_ZSET = True
|
||
|
||
DOWNLOAD_TIMEOUT = 90
|
||
CRAWL_DEEPTH = 3 # 若起始url为门户首页或板块首页，则深度至少要设为2，若起始url为内容页则深度至少设为1
|
||
|
||
# Configure maximum concurrent requests performed by Scrapy (default: 16)
|
||
# 控制并发采集数量，即同时请求url数量，也可控制scrapy-redis从队列中读取url得数量
|
||
CONCURRENT_REQUESTS = 12
|
||
|
||
PROTO_MODULE_PATH = 'WebsiteSpider.proto.Es_pb2'
|
||
PROTO_CLASS_NAME = 'EsSets'
|
||
PROTO_FIELD_NAME = 'Es'
|
||
PROTO_SAVE_FILE_NAME = r'public_info_data_'
|
||
|
||
FILES_STORE = r'/usr/local/temp_file'
|
||
FILES_URLS_FIELD = 'es_attachment'
|
||
FILES_RESULT_FIELD = 'es_attachment'
|
||
FILE_ZIP_FILE_NAME = 'attach_data_publicinfo_'
|
||
|
||
IMAGES_STORE = r'/usr/local/temp_image'
|
||
IMAGES_URLS_FIELD = 'es_urlimage'
|
||
IMAGES_RESULT_FIELD = 'es_urlimage'
|
||
IMG_ZIP_FILE_NAME = 'image_data_publicinfo_'
|
||
|
||
MYEXT_ENABLED = True # 开启超时关闭scrapy扩展
|
||
IDLE_NUMBER = 36 # 配置允许的空闲时长，每5秒会增加一次IDLE_NUMBER，直到增加到60，程序才会close,空闲时间=5*IDLE_NUMBER 秒
|
||
|
||
CRAWL_JOB_UPDATE_API = 'http://47.115.228.133:28081/api/open/crawljob'
|
||
WORD_BANK_QUERY_API = 'http://47.115.228.133:28081/api/open/wordBank/queryAll'
|
||
CRAWL_RULE_QUERY_API = 'http://47.115.228.133:28081/api/open/target/website/queryAll'
|
||
|
||
BATCH_SAVE_SIZE = 5
|
||
PROTO_SAVE_FILE_PATH = '/usr/local/spider_data'
|
||
FILE_TRANS_PATH = '/usr/local/spider_data'
|
||
RETENTION_HOURS = 120
|
||
|
||
LOG_LEVEL = 'INFO'
|
||
|
||
# DEPTH_LIMIT=0
|
||
|
||
# Crawl responsibly by identifying yourself (and your website) on the user-agent
|
||
# USER_AGENT = 'WebsiteSpider (+http://www.yourdomain.com)'
|
||
|
||
# Obey robots.txt rules
|
||
# ROBOTSTXT_OBEY = 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
|
||
DOWNLOAD_DELAY = 0.1
|
||
|
||
# The download delay setting will honor only one of:
|
||
# 每个域名的并发采集数量，若等于CONCURRENT_REQUESTS，则可能会一段时间内只采集某一个站点，若假设该值等于1则可能并发采集16个站点，假设该值等于2则可能并发采集8个站点
|
||
CONCURRENT_REQUESTS_PER_DOMAIN = 4
|
||
# 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 = {
|
||
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
|
||
}
|
||
|
||
CUSTOM_USER_AGENT = [
|
||
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36',
|
||
'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:77.0) Gecko/20100101 Firefox/77.0',
|
||
'Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko',
|
||
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.18363',
|
||
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
|
||
'Opera/9.80 (Windows NT 6.1; U; zh-cn) Presto/2.9.168 Version/11.50',
|
||
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E; SE 2.X MetaSr 1.0',
|
||
'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E',
|
||
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.41 Safari/535.1 QQBrowser/6.9.11079.201'
|
||
]
|
||
|
||
# Enable or disable spider middlewares
|
||
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
|
||
SPIDER_MIDDLEWARES = {
|
||
'WebsiteSpider.middlewares.SimhashFilterSpiderMiddleware': 543,
|
||
'WebsiteSpider.middlewares.DumpFilterSpiderMiddleware': 544,
|
||
# 'WebsiteSpider.middlewares.KeywordFilterSpiderMiddleware': 545
|
||
}
|
||
|
||
# Enable or disable downloader middlewares
|
||
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
|
||
DOWNLOADER_MIDDLEWARES = {
|
||
'WebsiteSpider.middlewares.InitDownloaderMiddleware': 299,
|
||
'WebsiteSpider.middlewares.DeepLimitDownloaderMiddleware': 300,
|
||
'WebsiteSpider.middlewares.KeywordFilterDownloaderMiddleware': 301,
|
||
'WebsiteSpider.middlewares.DumpFilterDownloaderMiddleware': 302,
|
||
'WebsiteSpider.middlewares.AutoProxyDownloaderMiddleware': 305,
|
||
'WebsiteSpider.middlewares.UserAgentDownloaderMiddleware': 799,
|
||
'WebsiteSpider.scrapy_selenium.SeleniumMiddleware': 800
|
||
}
|
||
|
||
# Enable or disable extensions
|
||
# See https://docs.scrapy.org/en/latest/topics/extensions.html
|
||
EXTENSIONS = {
|
||
'WebsiteSpider.extensions.RedisSpiderSmartIdleClosedExtensions': 500,
|
||
'WebsiteSpider.extensions.SetCrawlerStatusExtensions': 501
|
||
}
|
||
|
||
# Configure item pipelines
|
||
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
|
||
ITEM_PIPELINES = {
|
||
'WebsiteSpider.pipelines.CustomAttachmentDownload': 1,
|
||
'scrapy.pipelines.images.ImagesPipeline': 2,
|
||
'WebsiteSpider.pipelines.ProtobufSavePipeline': 300,
|
||
}
|
||
|
||
############################## 翻译
|
||
MAX_TEXT_LENGTH = 5999
|
||
# 翻译 API 地址（替换为你的服务器 IP 或域名）
|
||
TRANSLATE_API_URL = "http://47.113.231.200:28082/translate"
|
||
# 单次请求间隔（秒），避免 API 被限流
|
||
REQUEST_DELAY = 1
|