jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-03-02 12:10:46 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: 修复zhihu评论爬取分页问题

Browse Source
This commit is contained in:
ravenling
2026-02-28 15:57:55 +08:00
parent 13b6140f22
commit 95c3293b97
1 changed files with 10 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
media_platform/zhihu/client.py
View File

@@ -299,8 +299,10 @@ class ZhiHuClient(AbstractApiClient, ProxyRefreshMixin):
result: List[ZhihuComment] = []
is_end: bool = False
offset: str = ""
prev_offset: str = ""
limit: int = 10
while not is_end:
prev_offset = offset
root_comment_res = await self.get_root_comments(content.content_id, content.content_type, offset, limit)
if not root_comment_res:
break
@@ -312,6 +314,9 @@ class ZhiHuClient(AbstractApiClient, ProxyRefreshMixin):
if not comments:
break
if prev_offset == offset:
break
if callback:
await callback(comments)
@@ -348,8 +353,10 @@ class ZhiHuClient(AbstractApiClient, ProxyRefreshMixin):
is_end: bool = False
offset: str = ""
prev_offset: str = ""
limit: int = 10
while not is_end:
prev_offset = offset
child_comment_res = await self.get_child_comments(parment_comment.comment_id, offset, limit)
if not child_comment_res:
break
@@ -361,6 +368,9 @@ class ZhiHuClient(AbstractApiClient, ProxyRefreshMixin):
if not sub_comments:
break
if prev_offset == offset:
break
if callback:
await callback(sub_comments)