osc-group/osc
1
1
Fork 0
Code Pull Requests Projects Wiki Activity
osc/spiders/MediaSpiders/MediaSpiders/settings.py

251 lines
10 KiB
Python
Raw Normal View History

init
2025-05-28 19:16:17 +08:00
# -*- coding: utf-8 -*-
BOT_NAME = 'MediaSpiders'
[twitter]新增用户信息采集功能
2026-01-21 17:52:17 +08:00
LOG_LEVEL = 'INFO'
init
2025-05-28 19:16:17 +08:00
SPIDER_MODULES = ['MediaSpiders.spiders']
NEWSPIDER_MODULE = 'MediaSpiders.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
# USER_AGENT = 'MediaSpiders (+http://www.yourdomain.com)'
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
PROTO_SAVE_FILE_PATH = '/usr/local/spider_data'
FILE_TRANS_PATH = '/usr/local/spider_data'
TOKEN_API = 'http://127.0.0.1:8088/api/token/'
PROXY_SERVICE = 'http://39.101.194.63:6800/'
PER_BATCH_IP_USE_TIMES = 50 # 代理中间件每次从ip池获取一批ip，定义这批ip使用次数，达到次数后重新从ip池获取新的一批
REDIS_HOST = '107.182.191.3'
REDIS_PORT = 7379
REDIS_PWD = 'jlkj-841-2-redis'
REDIS_PARAMS = {
'password': 'jlkj-841-2-redis',
}
MYSQL_DB_HOST = '39.101.194.63'
MYSQL_DB_PORT = 23306
MYSQL_DB_USER = 'root'
MYSQL_DB_PASSWD = 'passok123A'
MYSQL_DB_SCHEMA = 'oscm'
[twitter]新增用户信息采集功能
2026-01-21 17:52:17 +08:00
TWITTER_USER_MYSQL_DB_HOST = '47.113.231.200'
TWITTER_USER_MYSQL_DB_PORT = 28089
TWITTER_USER_MYSQL_DB_USER = 'root'
TWITTER_USER_MYSQL_DB_PASSWD = 'passok123A'
TWITTER_USER_MYSQL_DB_SCHEMA = 'dsp'
init
2025-05-28 19:16:17 +08:00
CRAWL_JOB_UPDATE_API = 'http://47.115.228.133:28081/api/open/crawljob'
WORD_BANK_QUERY_API = 'http://47.115.228.133:28081/api/open/wordBank/queryAll'
RULES_PARSER_QUERY_API = 'http://47.115.228.133:28081/api/rules/parser/queryPageable/0/1'
KAFKA_SERVER = '47.113.231.200:9092'
KAFKA_TOPIC = 'stream-protobuf'
BATCH_SAVE_SIZE = 5
TWITTER_FILTER_KEY = 'URL_Filter:MediaSpiders:Twitter_Filter'
FACEBOOK_FILTER_KEY = 'URL_Filter:MediaSpiders:Facebook_Filter'
[linkedin] 用户基本信息采集
2026-01-28 11:00:03 +08:00
LINKEDIN_FILTER_KEY = 'URL_Filter:MediaSpiders:Linkedin_Filter'
init
2025-05-28 19:16:17 +08:00
YOUTUBE_FILTER_KEY = 'URL_Filter:MediaSpiders:Youtube_Filter'
WEIBO_FILTER_KEY = 'URL_Filter:MediaSpiders:Weibo_Filter'
WECHAT_FILTER_KEY = 'URL_Filter:MediaSpiders:Wechat_Filter'
FLICKR_FILTER_KEY = 'URL_Filter:MediaSpiders:Flickr_Filter'
TWITTER_SIMHASH_FILTER_KEY = 'SimHash_Filter:MediaSpiders:Twitter_Filter'
FACEBOOK_SIMHASH_FILTER_KEY = 'SimHash_Filter:MediaSpiders:Facebook_Filter'
[linkedin] 用户基本信息采集
2026-01-28 11:00:03 +08:00
LINKEDIN_SIMHASH_FILTER_KEY = 'SimHash_Filter:MediaSpiders:Linkedin_Filter'
init
2025-05-28 19:16:17 +08:00
YOUTUBE_SIMHASH_FILTER_KEY = 'SimHash_Filter:MediaSpiders:Youtube_Filter'
WEIBO_SIMHASH_FILTER_KEY = 'SimHash_Filter:MediaSpiders:Weibo_Filter'
WECHAT_SIMHASH_FILTER_KEY = 'SimHash_Filter:MediaSpiders:Wechat_Filter'
FLICKR_SIMHASH_FILTER_KEY = 'SimHash_Filter:MediaSpiders:Flickr_Filter'
WECHAT_LINKS_KEY = "MediaSpiders:Wechat_links"
[twitterSpider]1、新增仿生物操作配置，2、修改业务逻辑，若自动化获取Cookie失败，则直接从redis中获取cookie；3、修改采集信息json层级
2026-01-16 16:30:41 +08:00
# TWITTER_BEARER_TOKEN = "AAAAAAAAAAAAAAAAAAAAANRILgAAAAAAnNwIzUejRCOuH5E6I8xnZz4puTs%3D1Zv7ttfk8LF81IUq16cHjhLTvJu4FA33AGWWjCpTnA" # old
TWITTER_API_KEY = "JFY7dt"
TWITTER_BEARER_TOKEN = "AAAAAAAAAAAAAAAAAAAAAO8MTQEAAAAAQWidbP34N0nykDnUEDweEpyRgsc%3Dxt0hX1whV1hlmbMsStkB7ZU3pjXOINOCh2DMPoIAwljwrOWgvE"
TWITTER_ACCESS_TOKEN = "1294829483816398849-gscLJCEF9ZObZJikjCmjXtxoW6YVWu"
TWITTER_ACCESS_TOKEN_SECRET = "1XvTHZXzN0JBQulTBOvCTgXVPzVGYWe50zH1r4qXLper3"
init
2025-05-28 19:16:17 +08:00
SOCIAL_USER_QUERY_ALL_API = "http://47.115.228.133:28081/api/open/target/social/queryAll?sortBy={sortBy}&shuffleResult={shuffleResult}"
SOCIAL_USER_UPDATE_API = "http://47.115.228.133:28081/api/open/target/social/update"
WEIBO_USER_TYPE = 0
[twitterSpider]1、新增仿生物操作配置，2、修改业务逻辑，若自动化获取Cookie失败，则直接从redis中获取cookie；3、修改采集信息json层级
2026-01-16 16:30:41 +08:00
TWITTER_USER_TYPE = 21
init
2025-05-28 19:16:17 +08:00
FACEBOOK_USER_TYPE = 2
YOUTUBE_USER_TYPE = 3
FLICKR_USER_TYPE = 4
WECHAT_USER_TYPE = 5
TWITTER_COMMENT_FILTER_KEY = 'MediaSpiders:Twitter_Comment_Filter'
TWITTER_COMMENT_URL_KEY = 'MediaSpiders:Twitter_Comment_URL_Key'
TWITTER_URL_KEY = 'MediaSpiders:Twitter_URL_Key'
TWITTER_PID_KEY = ''
KAFKA_PROCESS_QUEUE = ['stream-protobuf', 'stream-db']
[twitterSpider]1、新增仿生物操作配置，2、修改业务逻辑，若自动化获取Cookie失败，则直接从redis中获取cookie；3、修改采集信息json层级
2026-01-16 16:30:41 +08:00
# CUSTOM_USER_AGENT = [
# 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36',
# 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:77.0) Gecko/20100101 Firefox/77.0',
# 'Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko',
# 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.18363',
# 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
# 'Opera/9.80 (Windows NT 6.1; U; zh-cn) Presto/2.9.168 Version/11.50',
# 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E; SE 2.X MetaSr 1.0',
# 'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E',
# 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.41 Safari/535.1 QQBrowser/6.9.11079.201'
# ]
init
2025-05-28 19:16:17 +08:00
CUSTOM_USER_AGENT = [
[twitterSpider]1、新增仿生物操作配置，2、修改业务逻辑，若自动化获取Cookie失败，则直接从redis中获取cookie；3、修改采集信息json层级
2026-01-16 16:30:41 +08:00
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/132.0.0.0 Safari/537.36',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/132.0.0.0 Safari/537.36 Edg/132.0.0.0',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:134.0) Gecko/20100101 Firefox/134.0',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.1958',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/132.0.0.0 Safari/537.36 OPR/117.0.0.',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.3'
init
2025-05-28 19:16:17 +08:00
]
# 部署在外网采集fb时使用selenium_chrome
SELENIUM_DRIVER_NAME = 'chrome'
针对6s采集的改动
2026-02-12 09:35:23 +08:00
# SELENIUM_DRIVER_EXECUTABLE_PATH = 'local'
SELENIUM_DRIVER_EXECUTABLE_PATH = 'http://144.34.185.108:28098'
init
2025-05-28 19:16:17 +08:00
SELENIUM_DRIVER_ARGUMENTS = [
'--headless',
'--no-sandbox',
'--disable-dev-shm-usage',
'--disable-gpu',
'--window-size=1920,1080'
]
# 本地调试用
# SELENIUM_DRIVER_NAME = 'edge'
# SELENIUM_DRIVER_EXECUTABLE_PATH = "MicrosoftWebDriver.exe"
# # '--headless' if using chrome instead of firefox
# SELENIUM_DRIVER_ARGUMENTS = [
# # '--headless',
# '--start-maximized',
# '--no-sandbox',
# '--disable-dev-shm-usage',
# '--disable-gpu'
# ]
FACEBOOK_LOGIN_USER_KEYNAME = 'FACEBOOK_LOGIN_USERS'
# SELENIUM_DRIVER_EXECUTABLE_PATH = which('chromedriver')
# SELENIUM_DRIVER_NAME = 'firefox'
# SELENIUM_DRIVER_EXECUTABLE_PATH = 'http://selenium_firefox/wd/hub'
# SELENIUM_DRIVER_EXECUTABLE_PATH = which('geckodriver')
# SELENIUM_DRIVER_ARGUMENTS=['-headless'] # '--headless' if using chrome instead of firefox ,'--proxy-server=http://192.168.199.243:10809'
SPLASH_URL = 'http://107.182.191.3:28050/'
# 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
RANDOMIZE_DOWNLOAD_DELAY = True
DOWNLOAD_DELAY = 5
DOWNLOAD_TIMEOUT = 60
# 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 = True
RETENTION_HOURS = 120
# 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',
# }
# DEFAULT_REQUEST_HEADERS = {
# 'Accept': 'application/json, text/plain, */*',
# 'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
# 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:74.0) Gecko/20100101 Firefox/74.0',
# 'Connection': 'keep-alive',
# 'Host': 'm.weibo.cn',
# # 'Referer':'https://m.weibo.cn/u/3893259857?uid=3893259857&luicode=10000011&lfid=1076033893259857',
# 'TE':'Trailers',
# 'X-Requested-With':'XMLHttpRequest'
# }
# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
SPIDER_MIDDLEWARES = {
'MediaSpiders.middlewares.DumpFilterSpiderMiddleware': 543,
'MediaSpiders.middlewares.KeywordFilterSpiderMiddleware': 544,
'MediaSpiders.middlewares.SimhashFilterSpiderMiddleware': 545,
'scrapy_splash.SplashDeduplicateArgsMiddleware': 700,
}
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# 本地测试时需要开启MyProxyDownloaderMiddleware，同时注意修改middleware中的相应位置的代码用于本地测试
# 采集微博时可不开启MediaSpiders.scrapy_selenium.SeleniumMiddleware
DOWNLOADER_MIDDLEWARES = {
'MediaSpiders.middlewares.DumpFilterDownloaderMiddleware': 543,
# 'MediaSpiders.middlewares.MyProxyDownloaderMiddleware': 544,
'MediaSpiders.middlewares.UserAgentDownloaderMiddleware': 545,
'scrapy_splash.SplashCookiesMiddleware': 723,
'scrapy_splash.SplashMiddleware': 725,
'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
'MediaSpiders.scrapy_selenium.SeleniumMiddleware': 820
}
EXTENSIONS = {
'MediaSpiders.extensions.SetCrawlerStatusExtensions': 501
}
[twitter]新增推特用户信息采集字段
2026-01-22 13:51:16 +08:00
############################## 翻译
MAX_TEXT_LENGTH = 100
# 翻译 API 地址（替换为你的服务器 IP 或域名）
TRANSLATE_API_URL = "http://47.113.231.200:28082/translate"
# 单次请求间隔（秒），避免 API 被限流
REQUEST_DELAY = 1
init
2025-05-28 19:16:17 +08:00
# 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 = {
# 'MediaSpiders.pipelines.MediaspidersPipeline': 300,
# }
# 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'
Copy Permalink