# Scrapy settings for douban 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 = 'douban'
SPIDER_MODULES = ['douban.spiders']
NEWSPIDER_MODULE = 'douban.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36'
# Obey robots.txt rules
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 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',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36'
}
# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'douban.middlewares.DoubanSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'douban.middlewares.DoubanDownloaderMiddleware': 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 = {
'douban.pipelines.DoubanPipeline': 300,
'douban.pipelines.MySqlSavePipeline': 400,
}
# 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'
#使用scrapy_redis组件自己的调度器
SCHEDULER = "scrapy_redis.scheduler.Scheduler"
# 确保所有spider通过redis共享相同的重复过滤。
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
# 可选 不清理redis队列,允许暂停/恢复抓取。 允许暂定,redis数据不丢失
SCHEDULER_PERSIST = True
# REDIS 主机和端口
REDIS_HOST = '127.0.0.1' # 写自己电脑的ip地址
REDIS_PORT = 6379
# 伪分布式
没有合适的资源?快使用搜索试试~ 我知道了~
scrapy-redis分布式爬虫代码展示,按需自取
共15个文件
py:8个
pyc:6个
cfg:1个
需积分: 0 1 下载量 89 浏览量
2022-11-30
15:12:45
上传
评论
收藏 11KB ZIP 举报
温馨提示
scrapy-redis分布式爬虫代码展示,按需自取
资源推荐
资源详情
资源评论
收起资源包目录
19-2022.10.10-scrapy-redis.zip (15个子文件)
douban
douban
spider_start.py 60B
middlewares.py 4KB
pipelines.py 2KB
spiders
douban_moive.py 1002B
__pycache__
douban_moive.cpython-310.pyc 1KB
__init__.cpython-310.pyc 166B
__init__.py 176B
__pycache__
settings.cpython-310.pyc 853B
__init__.cpython-310.pyc 158B
items.cpython-310.pyc 446B
pipelines.cpython-310.pyc 2KB
items.py 376B
__init__.py 0B
settings.py 4KB
scrapy.cfg 255B
共 15 条
- 1
资源评论
莎萌玩家
- 粉丝: 394
- 资源: 9
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功