121 lines
4.7 KiB
Python
121 lines
4.7 KiB
Python
# Scrapy settings for scrapy_proj 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 = "scrapy_proj"
|
||
|
||
SPIDER_MODULES = ["scrapy_proj.spiders"]
|
||
NEWSPIDER_MODULE = "scrapy_proj.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/91.0.4472.124 Safari/537.36"
|
||
|
||
# Obey robots.txt rules
|
||
ROBOTSTXT_OBEY = False
|
||
|
||
# Configure maximum concurrent requests performed by Scrapy (default: 16)
|
||
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 = 1
|
||
# The download delay setting will honor only one of:
|
||
CONCURRENT_REQUESTS_PER_DOMAIN = 8
|
||
CONCURRENT_REQUESTS_PER_IP = 8
|
||
|
||
# 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=0.9,en;q=0.8",
|
||
}
|
||
|
||
# Enable or disable spider middlewares
|
||
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
|
||
#SPIDER_MIDDLEWARES = {
|
||
# "scrapy_proj.middlewares.ScrapyProjSpiderMiddleware": 543,
|
||
#}
|
||
|
||
# Enable or disable downloader middlewares
|
||
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
|
||
DOWNLOADER_MIDDLEWARES = {
|
||
"scrapy_proj.middlewares.ScrapyProjDownloaderMiddleware": 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 = {
|
||
# "scrapy_proj.pipelines.AliyunVodPipeline": 300, # 上传到阿里云视频点播
|
||
# "scrapy_proj.pipelines.SQLitePipeline": 400, # 保存到SQLite
|
||
# "scrapy_proj.pipelines.MariaDBPipeline": 500, # 最后保存到MariaDB
|
||
}
|
||
|
||
# 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"
|
||
|
||
# 项目根目录配置（用于SQLite数据库文件路径）
|
||
import os
|
||
from dotenv import load_dotenv
|
||
|
||
load_dotenv() # 加载.env文件中的环境变量
|
||
PROJECT_ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
||
|
||
# 数据库配置
|
||
SQLITE_FILE = os.getenv("SQLITE_FILE", "data/videos.db")
|
||
|
||
# MariaDB配置
|
||
MYSQL_HOST = os.getenv("MYSQL_HOST", "localhost") # 数据库主机
|
||
MYSQL_PORT = int(os.getenv("MYSQL_PORT", "3306")) # 数据库端口
|
||
MYSQL_USER = os.getenv("MYSQL_USER", "root") # 数据库用户名
|
||
MYSQL_PASSWORD = os.getenv("MYSQL_PASSWORD") # 数据库密码
|
||
MYSQL_DATABASE = os.getenv("MYSQL_DATABASE", "dev_yszy") # 数据库名称
|
||
|
||
# 阿里云配置
|
||
ALIYUN_ACCESS_KEY_ID = os.getenv("ALIYUN_ACCESS_KEY_ID") # 阿里云AccessKey ID
|
||
ALIYUN_ACCESS_KEY_SECRET = os.getenv("ALIYUN_ACCESS_KEY_SECRET") # 阿里云AccessKey Secret
|
||
ALIYUN_TEMPLATE_GROUP_ID = os.getenv("ALIYUN_TEMPLATE_GROUP_ID") # 转码模板组ID
|
||
|
||
# 阿里云OSS配置
|
||
ALIYUN_OSS_BUCKET = os.getenv("ALIYUN_OSS_BUCKET") # 阿里云OSS Bucket名称
|
||
ALIYUN_OSS_ENDPOINT = os.getenv("ALIYUN_OSS_ENDPOINT") # 阿里云OSS Endpoint |