mysql example basespider basespider settings (snippet)

Python mysql example 'basespider basespider settings'

python basespider basespider settings

Python mysql example: basespider basespider settings

# -*- coding: utf-8 -*-

# Scrapy settings for basespider project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     http://doc.scrapy.org/en/latest/topics/settings.html
#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'basespider'

SPIDER_MODULES = ['basespider.spiders']
NEWSPIDER_MODULE = 'basespider.spiders'

LOG_LEVEL = "INFO"

COOKIE_DEBUG = True

# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.110 Safari/537.36'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# scrapy-redis
# Enables scheduling storing requests queue in redis.
# SCHEDULER = "scrapy_redis.scheduler.Scheduler"

# Ensure all spiders share same duplicates filter through redis.
# DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"

# Configure maximum concurrent requests performed by Scrapy (default: 16)
# CONCURRENT_REQUESTS = 3

# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
# DOWNLOAD_DELAY = 1
# 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': 'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',
}

# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
SPIDER_MIDDLEWARES = {
    #    'xbzxproject.middlewares.MyCustomSpiderMiddleware': 543,
    'scrapy_splash.SplashDeduplicateArgsMiddleware': 100,
}

# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {

    'basespider.middlewares.Proxyip.ProxyMiddleware': 543,
    # 'xbzxproject.middlewares.downloadwebkit.WebDriverDownloader': 542,
    'scrapy_splash.SplashCookiesMiddleware': 723,
    'scrapyjs.SplashMiddleware': 725,
    'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
}

DUPEFILTER_CLASS = 'scrapyjs.SplashAwareDupeFilter'
SPLASH_URL = 'http://192.168.99.100:32775/'

# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
# EXTENSIONS = {
#     'scrapy.extensions.telnet.TelnetConsole': None,
# }

# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
    # 'scrapy_redis.pipelines.RedisPipeline': 300,
    'basespider.pipelines.BasespiderPipeline': 350,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.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 http://scrapy.readthedocs.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'

BASECONFIG = {
    "mysql": {
        "databases": "test",
        "host": "127.0.0.1",
        "port": 3306,
        "user": "root",
        "passwd": "root"
    },
    "scrapy": {
        "project": "testproject",
        "path": "E:\\scrapy_webconfig"
    },
    "scrapyd": {
        "host": "127.0.0.1",
        "port": 6800
    }
}

Python links

• Learn Python: https://pythonbasics.org/
• Python Tutorial: https://pythonprogramminglanguage.com