injectlib/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2025-11-25 11:29:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: xhs帖子详情问题更新

Browse Source
This commit is contained in:
Relakkes
2024-10-20 00:59:08 +08:00
parent 9fe3e47b0f
commit 03e393949a
6 changed files with 85 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
config/base_config.py
View File

@@ -57,18 +57,26 @@ MAX_CONCURRENCY_NUM = 1
ENABLE_GET_IMAGES = False
# 是否开启爬评论模式, 默认开启爬评论
ENABLE_GET_COMMENTS = False
ENABLE_GET_COMMENTS = True
# 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
# 指定小红书需要爬虫的笔记ID列表
XHS_SPECIFIED_ID_LIST = [
"6422c2750000000027000d88",
# 已废弃⚠️⚠️⚠️指定小红书需要爬虫的笔记ID列表
# 已废弃⚠️⚠️⚠️ 指定笔记ID笔记列表会因为缺少xsec_token和xsec_source参数导致爬取失败
# XHS_SPECIFIED_ID_LIST = [
# "66fad51c000000001b0224b8",
# # ........................
# ]
# 指定小红书需要爬虫的笔记URL列表, 目前要携带xsec_token和xsec_source参数
XHS_SPECIFIED_NOTE_URL_LIST = [
"https://www.xiaohongshu.com/explore/66fad51c000000001b0224b8?xsec_token=AB3rO-QopW5sgrJ41GwN01WCXh6yWPxjSoFI9D5JIMgKw=&xsec_source=pc_search"
# ........................
]
# 指定抖音需要爬取的ID列表
DY_SPECIFIED_ID_LIST = [
"7280854932641664319",