RYDE-WORK/MediaCrawler
1
0
Fork 0
mirror of https://github.com/RYDE-WORK/MediaCrawler.git synced 2026-02-05 08:14:46 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

fix: xhs 帖子详情优化

Browse Source
This commit is contained in:
Relakkes 2024-11-27 09:41:24 +08:00
parent 43dffeb2d1
commit ca9b47ef63
1 changed files with 6 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
media_platform/xhs/core.py
View File

@ -273,26 +273,25 @@ class XiaoHongShuCrawler(AbstractCrawler):
note_detail_from_html, note_detail_from_api = None, None note_detail_from_html, note_detail_from_api = None, None
async with semaphore: async with semaphore:
try: try:
# 尝试直接获取网页版笔记详情，不携带cookie # 尝试直接获取网页版笔记详情，携带cookie
note_detail_from_html: Dict = ( note_detail_from_html: Optional[Dict] = (
await self.xhs_client.get_note_by_id_from_html( await self.xhs_client.get_note_by_id_from_html(
note_id, xsec_source, xsec_token, enable_cookie=False note_id, xsec_source, xsec_token, enable_cookie=True
) )
) )
if not note_detail_from_html: if not note_detail_from_html:
# 如果网页版笔记详情获取失败，则尝试使用cookie获取 # 如果网页版笔记详情获取失败，则尝试不使用cookie获取
note_detail_from_html = ( note_detail_from_html = (
await self.xhs_client.get_note_by_id_from_html( await self.xhs_client.get_note_by_id_from_html(
note_id, xsec_source, xsec_token, enable_cookie=True note_id, xsec_source, xsec_token, enable_cookie=False
) )
) )
utils.logger.error( utils.logger.error(
f"[XiaoHongShuCrawler.get_note_detail_async_task] Get note detail error, note_id: {note_id}" f"[XiaoHongShuCrawler.get_note_detail_async_task] Get note detail error, note_id: {note_id}"
) )
return None
if not note_detail_from_html: if not note_detail_from_html:
# 如果网页版笔记详情获取失败，则尝试API获取 # 如果网页版笔记详情获取失败，则尝试API获取
note_detail_from_api: Dict = await self.xhs_client.get_note_by_id( note_detail_from_api: Optional[Dict] = await self.xhs_client.get_note_by_id(
note_id, xsec_source, xsec_token note_id, xsec_source, xsec_token
) )
note_detail = note_detail_from_html or note_detail_from_api note_detail = note_detail_from_html or note_detail_from_api