mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-06-01 15:37:26 +08:00
finish_all
This commit is contained in:
@@ -46,7 +46,7 @@ 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, 最好保存到DB,有排重的功能。
|
||||
SAVE_DATA_OPTION = "csv" # csv or db or 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
|
||||
@@ -72,12 +72,6 @@ ENABLE_GET_COMMENTS = True
|
||||
# 爬取一级评论的数量控制(单视频/帖子)
|
||||
CRAWLER_MAX_COMMENTS_COUNT_SINGLENOTES = 10
|
||||
|
||||
# 爬取作者粉丝和关注列表数量控制(单作者)
|
||||
CRAWLER_MAX_CONTACTS_COUNT_SINGLENOTES = 100
|
||||
|
||||
# 爬取作者动态粉丝和关注列表数量控制(单作者)
|
||||
CRAWLER_MAX_DYNAMICS_COUNT_SINGLENOTES = 50
|
||||
|
||||
# 是否开启爬二级评论模式, 默认不开启爬二级评论
|
||||
# 老版本项目使用了 db, 则需参考 schema/tables.sql line 287 增加表字段
|
||||
ENABLE_GET_SUB_COMMENTS = False
|
||||
@@ -206,4 +200,10 @@ END_DAY = '2024-01-01'
|
||||
# 是否开启按每一天进行爬取的选项,仅支持 bilibili 关键字搜索
|
||||
# 若为 False,则忽略 START_DAY 与 END_DAY 设置的值
|
||||
# 若为 True,则按照 START_DAY 至 END_DAY 按照每一天进行筛选,这样能够突破 1000 条视频的限制,最大程度爬取该关键词下的所有视频
|
||||
ALL_DAY = False
|
||||
ALL_DAY = False
|
||||
|
||||
# 爬取作者粉丝和关注列表数量控制(单作者)
|
||||
CRAWLER_MAX_CONTACTS_COUNT_SINGLENOTES = 100
|
||||
|
||||
# 爬取作者动态粉丝和关注列表数量控制(单作者)
|
||||
CRAWLER_MAX_DYNAMICS_COUNT_SINGLENOTES = 50
|
||||
Reference in New Issue
Block a user