crawlab_feader/FworkSpider/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
WEBDRIVER = dict(
    pool_size=1,  # 浏览器的数量
    load_images=False,  # 是否加载图片
    user_agent=None,  # 字符串 或 无参函数，返回值为user_agent
    proxy=None,  # xxx.xxx.xx.xxx:xxxx 或 无参函数，返回值为代理地址
    headless=False,  # 是否为无头浏览器
    driver_type="CHROME",  # CHROME、FIREFOX
    timeout=30,  # 请求超时时间
    window_size=(1280, 800),  # 窗口大小
    executable_path=None,  # 浏览器路径，默认为默认路径
    render_time=0,  # 渲染时长，即打开网页等待指定时间后再获取源码
    custom_argument=["--ignore-certificate-errors"],  # 自定义浏览器渲染参数
    usages_local_driver=False,  # 是否加载本地驱动
    server_addr="http://172.17.162.28:6666/wd/hub",  # selenium 远程服务地址
    version="",  # 远程浏览器版本
    service_log_path=os.devnull  # 日志路径
)

# splash渲染
SPLASH_API = "http://splash.spdata.jianyu360.com/render.json"

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

# 设置代理，代理提取API ，返回的代理分割符为\r\n
PROXY_EXTRACT_API = "http://proxy.spdata.jianyu360.com/proxy/getallip"
PROXY_ENABLE = True
JY_PROXY_URL = "http://cc.spdata.jianyu360.com/crawl/proxy/socks5/fetch"
JY_PROXY_AUTHOR = "Basic amlhbnl1MDAxOjEyM3F3ZSFB"

# item去重
ITEM_FILTER_ENABLE = True
ITEM_FILTER_SETTING = dict(
    filter_type=6,
    redisdb_conf=[
        dict(
            fingerprint_pref="pylist_",
            ip_port="172.17.4.240:8361",
            user_pass="k5ZJR5KV4q7DRZ92DQ",
            db=0
        ),
        dict(
            fingerprint_pref="list_",
            ip_port="172.17.4.84:4679",
            user_pass="jytopnet123",
            db=0
        )
    ],
    expire_time=63072000,  # 过期时间2年
)

# 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 = "ERROR"
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
OTHERS_LOG_LEVAL = "ERROR"  # 第三方库的log等级 一般用不到

# 验证码
CAPTCHA_URL = "http://pycaptcha.spdata.jianyu360.com"

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