jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-06-08 19:07:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

temp commit

Browse Source
This commit is contained in:
Relakkes
2024-08-06 19:21:34 +08:00
parent d347cf5a2c
commit 1b585cb215
4 changed files with 7644 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
config/base_config.py
View File

@@ -1,6 +1,6 @@
# 基础配置
PLATFORM = "xhs"
KEYWORDS = "编程副业,编程兼职"
KEYWORDS = "缅甸边境,缅北边境,缅北边境线,缅甸边境线"
LOGIN_TYPE = "qrcode" # qrcode or phone or cookie
COOKIES = ""
# 具体值参见media_platform.xxx.field下的枚举值，暂时只支持小红书
@@ -28,7 +28,7 @@ HEADLESS = False
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
SAVE_DATA_OPTION = "db" # 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
@@ -37,7 +37,7 @@ USER_DATA_DIR = "%s_user_data_dir" # %s will be replaced by platform name
START_PAGE = 1
# 爬取视频/帖子的数量控制
CRAWLER_MAX_NOTES_COUNT = 20
CRAWLER_MAX_NOTES_COUNT = 100
# 并发爬虫数量控制
MAX_CONCURRENCY_NUM = 1