MediaCrawler/config/base_config.py

76 lines
2.0 KiB
Python
Raw Normal View History

# 基础配置
PLATFORM = "xhs"
2023-08-16 11:49:41 +00:00
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" # 爬取类型search(关键词搜索) | detail(帖子相亲)| creator(创作者主页数据)
# 是否开启 IP 代理
2023-12-08 16:06:57 +00:00
ENABLE_IP_PROXY = False
2023-12-07 16:10:04 +00:00
# 代理IP池数量
IP_PROXY_POOL_COUNT = 2
2023-12-30 10:54:21 +00:00
# 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
2023-07-29 07:35:40 +00:00
CRAWLER_MAX_NOTES_COUNT = 20
2023-07-15 14:25:56 +00:00
# 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
2023-11-18 07:53:10 +00:00
XHS_SPECIFIED_ID_LIST = [
2023-12-09 13:10:01 +00:00
"6422c2750000000027000d88",
"64ca1b73000000000b028dd2",
"630d5b85000000001203ab41",
# ........................
]
# 指定抖音需要爬取的ID列表
DY_SPECIFIED_ID_LIST = [
2023-12-09 13:10:01 +00:00
"7280854932641664319",
"7202432992642387233"
# ........................
2023-12-07 16:10:04 +00:00
]
# 指定快手平台需要爬取的ID列表
KS_SPECIFIED_ID_LIST = [
"3xf8enb8dbj6uig",
"3x6zz972bchmvqe"
]
2023-12-07 16:10:04 +00:00
# 指定B站平台需要爬取的视频bvid列表
2023-12-09 13:10:01 +00:00
BILI_SPECIFIED_ID_LIST = [
"BV1d54y1g7db",
"BV1Sz4y1U77N",
"BV14Q4y1n7jz",
2023-12-09 13:10:01 +00:00
# ........................
]
# 指定微博平台需要爬取的帖子列表
WEIBO_SPECIFIED_ID_LIST = [
"4982041758140155",
# ........................
2024-01-15 16:40:07 +00:00
]
# 指定小红书创作者ID列表
XHS_CREATOR_ID_LIST = [
"63e36c9a000000002703502b",
# ........................
]