爬取知名社区技术文章_setting_5

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

# Scrapy settings for JobBole 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 = ‘JobBole‘

SPIDER_MODULES = [‘JobBole.spiders‘]
NEWSPIDER_MODULE = ‘JobBole.spiders‘

# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = ‘JobBole (+http://www.yourdomain.com)‘

# 是否遵守爬虫协议，默认遵守，改成Fals，不遵守
ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# 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 = 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 http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html

# SPIDER_MIDDLEWARES = {
#    ‘JobBole.middlewares.JobboleSpiderMiddleware‘: 543,
# }

# 图片下载配置
import os
IMAGES_URLS_FIELD = ‘img_url‘
base_dir = os.path.abspath(os.path.dirname(__file__))
IMAGES_STORE = os.path.join(base_dir, ‘images‘)

# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
#    ‘JobBole.middlewares.MyCustomDownloaderMiddleware‘: 543,
# }

# 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 = {
   ‘JobBole.pipelines.JobboleImagerPipeline‘: 1,
   ‘JobBole.pipelines.SqlSave‘: 2,
}

# 数据库基本配置
SQL_DBA= {
   ‘host‘: ‘localhost‘,
   ‘db‘: ‘jobole‘,
   ‘user‘: ‘root‘,
   ‘password‘: ‘password‘,
   ‘charset‘: ‘utf-8‘,
    ‘use_unicode‘: True
}

# 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‘