platform-spiders/setting.py

# -*- coding: utf-8 -*-
"""爬虫配置文件"""
import datetime
import os
import sys

# 数据保存失败表
TAB_FAILED_ITEMS = "pyspider:s_failed_items"
# 任务失败表
TAB_FAILED_REQUESTS = "pyspider:z_failed_requests"
# 采集任务生产表
TASK_REQUEST_PRODUCE = "pyspider_listdata"
# 失败任务记录表
TASK_REQUEST_FAILED = "pyspider_listdata_err"
# 爬虫心跳与数据采集汇总统计指标表
SPIDER_HEARTBEAT_RECORD = "pyspider_heartbeat"

# MONGODB
MONGO_IP = "172.17.4.87"
MONGO_PORT = 27080
MONGO_DB = "py_spider"

# REDIS
REDISDB_IP_PORTS = "172.17.162.28:7361"
REDISDB_USER_PASS = "k5ZJR5KV4q7DRZ92DQ"
REDISDB_DB = 10

# rabbitMq
RABBITMQ_IP_PORT = "172.17.162.28:5672"
RABBITMQ_USER = "root"
RABBITMQ_USER_PASS = "V0O0049qBI2rV1554jLZPiBZ8H3Bo4"
RABBITMQ_EXCHANGE = "pyspider.data.spider"
RABBITMQ_EXCHANGE_TYPE = "direct"
RABBITMQ_VIRTUAL_HOST = "/"
RABBITMQ_SOCKET_TIMEOUT = 60
RABBITMQ_HEARTBEAT = 600

# 数据入库的pipeline
ITEM_PIPELINES = [
    # "feapder.pipelines.mongo_pipeline.MongoPipeline",
    "feapder.pipelines.rabbitmq_pipeline.RabbitMqPipeline",
]
# 导出数据时最大的失败次数，包括保存和更新，超过这个次数报警
EXPORT_DATA_MAX_FAILED_TIMES = 5
# 导出数据时最大的重试次数，包括保存和更新，超过这个次数则放弃重试
EXPORT_DATA_MAX_RETRY_TIMES = 5

COLLECTOR_TASK_COUNT = 100  # 每次获取任务数量

# 爬虫
SPIDER_THREAD_COUNT = 1  # 爬虫并发数，追求速度推荐32
SPIDER_MAX_RETRY_TIMES = 3  # 每个请求最大重试次数

# 浏览器渲染
DRISSIONPAGE = dict(
    pool_size=1,  # 浏览器标签页的数量
    browser_path=None,  # 浏览器可执行文件路径
    scope=None,  # 自动浏览器端口范围
    port=None,  # 浏览器端口
    user_data_path=None,  # 用户数据目录
    headless=False,  # 是否为无头浏览器
    load_images=False,  # 是否加载图片
    user_agent=None,  # 字符串
    proxy=None,  # xxx.xxx.xxx.xxx:xxxx
    window_size=(1024, 800),  # 窗口大小
    driver_type="chromium",
    load_mode="normal",  # 网页加载策略, 可选值："normal", "eager", "none"
    timeout=10,  # 请求超时时间
    retry=1,  # 连接失败浏览器重试次数
    interval=0.5,  # 连接失败重试间隔（秒）
    page_load=15,  # 页面加载超时时间（秒）
    render_time=20,  # 渲染时长，即打开网页等待加载超时时间
    download_path=None,  # 下载文件的路径
    custom_argument=[
        "--no-sandbox",
        "--ignore-certificate-errors"
    ]
)

# request网络请求超时时间
REQUEST_TIMEOUT = 60

# 设置代理
PROXY_EXTRACT_API = "http://cc.spdata.jianyu360.com/crawl/proxy/socks5/fetch"
# PROXY_EXTRACT_API = "http://172.17.162.28:16001/sam"
PROXY_ENABLE = True
PROXY_AUTH = "Basic amlhbnl1MDAxOjEyM3F3ZSFB"
PROXY_POOL = "feapder.network.proxy_pool.DirectProxyPool"
# PROXY_POOL = "feapder.network.proxy_pool.SpringBoardProxyPool"

# 下载器
DOWNLOADER = "feapder.network.downloader.RequestsDownloader"  # 请求下载器
SESSION_DOWNLOADER = "feapder.network.downloader.RequestsSessionDownloader"
# SESSION_DOWNLOADER = "feapder.network.downloader.RequestsJa3SessionDownloader"
RENDER_DOWNLOADER = "feapder.network.downloader.DrissionPageDownloader"  # 渲染下载器
MAKE_ABSOLUTE_LINKS = True  # 自动转成绝对连接

# item去重
ITEM_FILTER_ENABLE = True
ITEM_FILTER_SETTING = dict(
    filter_type=6,
    expire_time=1 * 365 * 24 * 3600,  # 过期时间
    config={
        "py": {
            "fingerprint_pref": "pylist_",
            "ip_port": "172.17.162.34:8361",
            "user_pass": "k5ZJR5KV4q7DRZ92DQ",
            "db": 0
        },
        "lua": {
            "fingerprint_pref": "list_",
            "ip_port": "172.17.4.84:4679",
            "user_pass": "jytopnet123",
            "db": 0
        }
    }
)

# 日志设置
DTIME = datetime.datetime.now().strftime("%Y-%m-%d")
LOG_NAME = os.path.split(sys.argv[0])[-1].split(".")[0]
LOG_PATH = "log/%s/%s.log" % (DTIME, LOG_NAME)  # log存储路径
LOG_LEVEL = "DEBUG"
LOG_COLOR = True  # 是否带有颜色
LOG_IS_WRITE_TO_CONSOLE = True  # 是否打印到控制台
LOG_IS_WRITE_TO_FILE = True  # 是否写文件
LOG_MODE = "w"  # 写文件的模式
LOG_MAX_BYTES = 10 * 1024 * 1024  # 每个日志文件的最大字节数
LOG_BACKUP_COUNT = 20  # 日志文件保留数量
LOG_ENCODING = "utf8"  # 日志文件编码

# 详情采集任务领取接口
JY_TASK_URL = "http://pytask.spdata.jianyu360.com"

# bucket配置
ALI_BUCKET_CONFIG = {
    "key_id": "LTAI4G5x9aoZx8dDamQ7vfZi",
    "key_secret": "Bk98FsbPYXcJe72n1bG3Ssf73acuNh",
    "endpoint": "oss-cn-beijing-internal.aliyuncs.com",
    "bucket_name": "jy-datafile"
}