78 lines
2.0 KiB
Python
78 lines
2.0 KiB
Python
# 基础配置
|
||
PLATFORM = "xhs"
|
||
KEYWORDS = "python,golang"
|
||
LOGIN_TYPE = "qrcode" # qrcode or phone or cookie
|
||
COOKIES = ""
|
||
SORT_TYPE = "popularity_descending" # 具体值参见media_platform.xxx.field下的枚举值，展示只支持小红书
|
||
CRAWLER_TYPE = "search"
|
||
|
||
# 是否开启 IP 代理
|
||
ENABLE_IP_PROXY = False
|
||
|
||
# 代理IP池数量
|
||
IP_PROXY_POOL_COUNT = 2
|
||
|
||
# 设置为True不会打开浏览器（无头浏览器），设置False会打开一个浏览器（小红书如果一直扫码登录不通过，打开浏览器手动过一下滑动验证码）
|
||
HEADLESS = True
|
||
|
||
# 是否保存登录状态
|
||
SAVE_LOGIN_STATE = True
|
||
|
||
# 数据保存类型选项配置,支持三种类型：csv、db、json
|
||
SAVE_DATA_OPTION = "json" # csv or db or json
|
||
|
||
# 用户浏览器缓存的浏览器文件配置
|
||
USER_DATA_DIR = "%s_user_data_dir" # %s will be replaced by platform name
|
||
|
||
# 爬取视频/帖子的数量控制
|
||
CRAWLER_MAX_NOTES_COUNT = 20
|
||
|
||
# 并发爬虫数量控制
|
||
MAX_CONCURRENCY_NUM = 4
|
||
|
||
# 是否开启爬评论模式, 默认不开启爬评论
|
||
ENABLE_GET_COMMENTS = False
|
||
|
||
# 指定小红书需要爬虫的笔记ID列表
|
||
XHS_SPECIFIED_ID_LIST = [
|
||
"6422c2750000000027000d88",
|
||
"64ca1b73000000000b028dd2",
|
||
"630d5b85000000001203ab41",
|
||
# ........................
|
||
]
|
||
|
||
# 指定抖音需要爬取的ID列表
|
||
DY_SPECIFIED_ID_LIST = [
|
||
"7280854932641664319",
|
||
"7202432992642387233"
|
||
# ........................
|
||
]
|
||
|
||
# 指定快手平台需要爬取的ID列表
|
||
KS_SPECIFIED_ID_LIST = [
|
||
"3xf8enb8dbj6uig",
|
||
"3x6zz972bchmvqe"
|
||
]
|
||
|
||
# 指定B站平台需要爬取的视频bvid列表
|
||
BILI_SPECIFIED_ID_LIST = [
|
||
"BV1d54y1g7db",
|
||
"BV1Sz4y1U77N",
|
||
"BV14Q4y1n7jz",
|
||
# ........................
|
||
]
|
||
|
||
# 指定微博平台需要爬取的帖子列表
|
||
WEIBO_SPECIFIED_ID_LIST = [
|
||
"4982041758140155",
|
||
# ........................
|
||
]
|
||
|
||
# 指定小红书创作者ID列表
|
||
XHS_CREATOR_ID_LIST = [
|
||
"59d8cb33de5fb4696bf17217",
|
||
"61b87386000000001000b18b",
|
||
"5e8558100000000001005bc5",
|
||
# ........................
|
||
]
|