jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-06-07 02:17:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor: xhs update

Browse Source
This commit is contained in:
程序员阿江(Relakkes)
2025-07-21 21:26:16 +08:00
parent 26a43358cb
commit a4d9aaa34a
5 changed files with 44 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
config/base_config.py
View File

@@ -39,7 +39,7 @@ SAVE_LOGIN_STATE = True
# 是否启用CDP模式 - 使用用户现有的Chrome/Edge浏览器进行爬取，提供更好的反检测能力
# 启用后将自动检测并启动用户的Chrome/Edge浏览器，通过CDP协议进行控制
# 这种方式使用真实的浏览器环境，包括用户的扩展、Cookie和设置，大大降低被检测的风险
ENABLE_CDP_MODE = False
ENABLE_CDP_MODE = True
# CDP调试端口，用于与浏览器通信
# 如果端口被占用，系统会自动尝试下一个可用端口

3
config/xhs_config.py
View File

@@ -15,9 +15,6 @@
# 排序方式，具体的枚举值在media_platform/xhs/field.py中
SORT_TYPE = "popularity_descending"
# 用户代理，xhs自定义User-Agent
UA = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36 Edg/131.0.0.0"
# 指定笔记URL列表, 必须要携带xsec_token参数
XHS_SPECIFIED_NOTE_URL_LIST = [
"https://www.xiaohongshu.com/explore/66fad51c000000001b0224b8?xsec_token=AB3rO-QopW5sgrJ41GwN01WCXh6yWPxjSoFI9D5JIMgKw=&xsec_source=pc_search"