jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-06-09 11:27:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor: update xhs note detail

Browse Source
This commit is contained in:
程序员阿江(Relakkes)
2025-11-10 18:13:51 +08:00
parent b5dab6d1e8
commit 1e3637f238
2 changed files with 11 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
config/xhs_config.py
View File

@@ -17,7 +17,7 @@ SORT_TYPE = "popularity_descending"
# 指定笔记URL列表, 必须要携带xsec_token参数 # 指定笔记URL列表, 必须要携带xsec_token参数
XHS_SPECIFIED_NOTE_URL_LIST = [ XHS_SPECIFIED_NOTE_URL_LIST = [
"https://www.xiaohongshu.com/explore/68f99f6d0000000007033fcf?xsec_token=ABZEzjuN2fPjKF9EcMsCCxfbt3IBRsFZldGFoCJbdDmXI=&xsec_source=pc_feed" "https://www.xiaohongshu.com/explore/64b95d01000000000c034587?xsec_token=AB0EFqJvINCkj6xOCKCQgfNNh8GdnBC_6XecG4QOddo3Q=&xsec_source=pc_cfeed"
# ........................ # ........................
] ]

11
media_platform/xhs/core.py
View File

@@ -279,10 +279,17 @@ class XiaoHongShuCrawler(AbstractCrawler):
Dict: note detail Dict: note detail
""" """
note_detail = None note_detail = None
utils.logger.info(f"[get_note_detail_async_task] Begin get note detail, note_id: {note_id}")
async with semaphore: async with semaphore:
try: try:
utils.logger.info(f"[get_note_detail_async_task] Begin get note detail, note_id: {note_id}") try:
note_detail = await self.xhs_client.get_note_by_id_from_html(note_id, xsec_source, xsec_token, enable_cookie=True) note_detail = await self.xhs_client.get_note_by_id(note_id, xsec_source, xsec_token)
except RetryError:
pass
if not note_detail:
note_detail = await self.xhs_client.get_note_by_id_from_html(note_id, xsec_source, xsec_token,
enable_cookie=True)
if not note_detail: if not note_detail:
raise Exception(f"[get_note_detail_async_task] Failed to get note detail, Id: {note_id}") raise Exception(f"[get_note_detail_async_task] Failed to get note detail, Id: {note_id}")