165 lines
6.1 KiB
Python
165 lines
6.1 KiB
Python
# Scrapy settings for WikipediaSpiders 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 = "WikipediaSpiders"
|
|
|
|
SPIDER_MODULES = ["WikipediaSpiders.spiders"]
|
|
NEWSPIDER_MODULE = "WikipediaSpiders.spiders"
|
|
|
|
ZIP_FILE_PATH = ''
|
|
KAFKA_PROCESS_QUEUE = ['stream-protobuf']
|
|
KAFKA_SERVER = '47.113.231.200:9092'
|
|
|
|
MYSQL_DB_HOST = '39.101.194.63'
|
|
MYSQL_DB_PORT = 23306
|
|
MYSQL_DB_USER = 'root'
|
|
MYSQL_DB_PASSWD = 'passok123A'
|
|
MYSQL_DB_SCHEMA = 'oscm'
|
|
|
|
DOWNLOAD_TIMEOUT = 90
|
|
|
|
PROTO_MODULE_PATH = 'WikipediaSpiders.proto.Es_pb2'
|
|
PROTO_CLASS_NAME = 'EsSets'
|
|
PROTO_FIELD_NAME = 'Es'
|
|
PROTO_SAVE_FILE_NAME = r'wiki_page_data_'
|
|
|
|
FILES_STORE = r'/usr/local/temp_file'
|
|
FILES_URLS_FIELD = 'es_attachment'
|
|
FILES_RESULT_FIELD = 'es_attachment'
|
|
FILE_ZIP_FILE_NAME = 'attach_data_wiki_'
|
|
|
|
IMAGES_STORE = r'/usr/local/temp_image'
|
|
IMAGES_URLS_FIELD = 'es_urlimage'
|
|
IMAGES_RESULT_FIELD = 'es_urlimage'
|
|
IMG_ZIP_FILE_NAME = 'image_data_wiki_'
|
|
|
|
# Crawl responsibly by identifying yourself (and your website) on the user-agent
|
|
# USER_AGENT = "WikipediaSpiders (+http://www.yourdomain.com)"
|
|
|
|
# Obey robots.txt rules
|
|
ROBOTSTXT_OBEY = False
|
|
|
|
CRAWL_JOB_UPDATE_API = 'http://47.115.228.133:28081/api/open/crawljob'
|
|
|
|
BATCH_SAVE_SIZE = 3
|
|
PROTO_SAVE_FILE_PATH = '/usr/local/spider_data'
|
|
FILE_TRANS_PATH = '/usr/local/spider_data'
|
|
RETENTION_HOURS = 24
|
|
|
|
LOG_LEVEL = 'INFO'
|
|
|
|
CONCURRENT_REQUESTS = 8
|
|
|
|
# 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 = 4
|
|
|
|
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'
|
|
]
|
|
|
|
DOWNLOADER_MIDDLEWARES = {
|
|
'WikipediaSpiders.middlewares.UserAgentDownloaderMiddleware': 799,
|
|
}
|
|
|
|
EXTENSIONS = {
|
|
'WikipediaSpiders.extensions.SetCrawlerStatusExtensions': 501
|
|
}
|
|
|
|
ITEM_PIPELINES = {
|
|
'scrapy.pipelines.files.FilesPipeline': 1,
|
|
'scrapy.pipelines.images.ImagesPipeline': 2,
|
|
'WikipediaSpiders.pipelines.ProtobufSavePipeline': 300,
|
|
}
|
|
# Configure maximum concurrent requests performed by Scrapy (default: 16)
|
|
# CONCURRENT_REQUESTS = 32
|
|
|
|
# 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 = 3
|
|
# 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 = {
|
|
# "WikipediaSpiders.middlewares.WikipediaspidersSpiderMiddleware": 543,
|
|
# }
|
|
|
|
# Enable or disable downloader middlewares
|
|
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
|
|
# DOWNLOADER_MIDDLEWARES = {
|
|
# "WikipediaSpiders.middlewares.WikipediaspidersDownloaderMiddleware": 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 = {
|
|
# "WikipediaSpiders.pipelines.WikipediaspidersPipeline": 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"
|