2018-11-05-4-scrapy - settings.py相关修改调整

上一篇末尾的时候，说完结。你真天真地以为完结了啊？？？？
继续写。23333

多数scrapy是先修改items.py，其实items后面修改也没问题。
我们这里先修改settings.py。
注意下面亮色代码上下部分注释。实在想要弄懂的话，就去百度谷歌一下相关代码就好。
关于爬虫并发、下载等限速，百度或者谷歌一下，有很多文章有介绍settings各段代码的作用，这里不做更多介绍。

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

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

BOT_NAME = 'xiamiuser'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
#这块是将爬虫代码模拟成浏览器，网上还有随机USER_AGENT ，用于反反爬虫。

# Obey robots.txt rules
ROBOTSTXT_OBEY = False
#ROBOTSTXT_OBEY 默认为True，也就是说默认遵守爬取的网站的ROBOTS协议，我们改成False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
# CONCURRENT_REQUESTS = 6

# Configure a delay for requests for the same website (default: 0)
# See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs


#限速 https://www.cnblogs.com/hyit/articles/7882396.html
#AUTOTHROTTLE_ENABLED = True
#DOWNLOAD_DELAY = 3

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:
#这块注释就是模拟浏览器，以及直接使用登录后的cookie
DEFAULT_REQUEST_HEADERS = {
'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'zh-CN,zh;q=0.9',
'cookie':'这部分粘帖你自己登录帐号的cookie就行',
'upgrade-insecure-requests':1
}

# Enable or disable spider middlewares
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
# SPIDER_MIDDLEWARES = {
#    'xiamiuser.middlewares.XiamiuserSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
#    'xiamiuser.middlewares.XiamiuserDownloaderMiddleware': 543,
#}

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

# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'xiamiuser.pipelines.XiamiuserPipeline': 300,
}
#这个是写mysql，启用Pipeline。

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/autothrottle.html
# AUTOTHROTTLE_ENABLED = True
# The initial download delay
# AUTOTHROTTLE_START_DELAY = 1
# 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 = True

# Enable and configure HTTP caching (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#这部分取消注释，就是开启缓存下载，具体百度搜索一下相关代码，就能理解
 HTTPCACHE_ENABLED = True
 HTTPCACHE_EXPIRATION_SECS = 0
 HTTPCACHE_DIR = 'httpcache'
 HTTPCACHE_IGNORE_HTTP_CODES = []
 HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'