Skip to content

Commit 79bf9fc

Browse files
NanmiCoderNanmiCoder
committed
chore: add xhs field comment for issue #526 
1 parent 29ab6fe commit 79bf9fc

File tree

1 file changed

+44
-44
lines changed

1 file changed

+44
-44
lines changed

‎store/xhs/__init__.py‎

Lines changed: 44 additions & 44 deletions
Original file line numberDiff line numberDiff line change
@@ -87,27 +87,27 @@ async def update_xhs_note(note_item: Dict):
8787
video_url = ','.join(get_video_url_arr(note_item))
8888

8989
local_db_item = {
90-
"note_id": note_item.get("note_id"),
91-
"type": note_item.get("type"),
92-
"title": note_item.get("title") or note_item.get("desc", "")[:255],
93-
"desc": note_item.get("desc", ""),
94-
"video_url": video_url,
95-
"time": note_item.get("time"),
96-
"last_update_time": note_item.get("last_update_time", 0),
97-
"user_id": user_info.get("user_id"),
98-
"nickname": user_info.get("nickname"),
99-
"avatar": user_info.get("avatar"),
100-
"liked_count": interact_info.get("liked_count"),
101-
"collected_count": interact_info.get("collected_count"),
102-
"comment_count": interact_info.get("comment_count"),
103-
"share_count": interact_info.get("share_count"),
104-
"ip_location": note_item.get("ip_location", ""),
105-
"image_list": ','.join([img.get('url', '') for img in image_list]),
106-
"tag_list": ','.join([tag.get('name', '') for tag in tag_list if tag.get('type') == 'topic']),
107-
"last_modify_ts": utils.get_current_timestamp(),
108-
"note_url": f"https://www.xiaohongshu.com/explore/{note_id}?xsec_token={note_item.get('xsec_token')}&xsec_source=pc_search",
109-
"source_keyword": source_keyword_var.get(),
110-
"xsec_token": note_item.get("xsec_token"),
90+
"note_id": note_item.get("note_id"), # 帖子id
91+
"type": note_item.get("type"), # 帖子类型
92+
"title": note_item.get("title") or note_item.get("desc", "")[:255], # 帖子标题
93+
"desc": note_item.get("desc", ""), # 帖子描述
94+
"video_url": video_url, # 帖子视频url
95+
"time": note_item.get("time"), # 帖子发布时间
96+
"last_update_time": note_item.get("last_update_time", 0), # 帖子最后更新时间
97+
"user_id": user_info.get("user_id"), # 用户id
98+
"nickname": user_info.get("nickname"), # 用户昵称
99+
"avatar": user_info.get("avatar"), # 用户头像
100+
"liked_count": interact_info.get("liked_count"), # 点赞数
101+
"collected_count": interact_info.get("collected_count"), # 收藏数
102+
"comment_count": interact_info.get("comment_count"), # 评论数
103+
"share_count": interact_info.get("share_count"), # 分享数
104+
"ip_location": note_item.get("ip_location", ""), # ip地址
105+
"image_list": ','.join([img.get('url', '') for img in image_list]), # 图片url
106+
"tag_list": ','.join([tag.get('name', '') for tag in tag_list if tag.get('type') == 'topic']), # 标签
107+
"last_modify_ts": utils.get_current_timestamp(), # 最后更新时间戳（MediaCrawler程序生成的，主要用途在db存储的时候记录一条记录最新更新时间）
108+
"note_url": f"https://www.xiaohongshu.com/explore/{note_id}?xsec_token={note_item.get('xsec_token')}&xsec_source=pc_search", # 帖子url
109+
"source_keyword": source_keyword_var.get(), # 搜索关键词
110+
"xsec_token": note_item.get("xsec_token"), # xsec_token
111111
}
112112
utils.logger.info(f"[store.xhs.update_xhs_note] xhs note: {local_db_item}")
113113
await XhsStoreFactory.create_store().store_content(local_db_item)
@@ -144,18 +144,18 @@ async def update_xhs_note_comment(note_id: str, comment_item: Dict):
144144
comment_pictures = [item.get("url_default", "") for item in comment_item.get("pictures", [])]
145145
target_comment = comment_item.get("target_comment", {})
146146
local_db_item = {
147-
"comment_id": comment_id,
148-
"create_time": comment_item.get("create_time"),
149-
"ip_location": comment_item.get("ip_location"),
150-
"note_id": note_id,
151-
"content": comment_item.get("content"),
152-
"user_id": user_info.get("user_id"),
153-
"nickname": user_info.get("nickname"),
154-
"avatar": user_info.get("image"),
155-
"sub_comment_count": comment_item.get("sub_comment_count", 0),
156-
"pictures": ",".join(comment_pictures),
157-
"parent_comment_id": target_comment.get("id", 0),
158-
"last_modify_ts": utils.get_current_timestamp(),
147+
"comment_id": comment_id, # 评论id
148+
"create_time": comment_item.get("create_time"), # 评论时间
149+
"ip_location": comment_item.get("ip_location"), # ip地址
150+
"note_id": note_id, # 帖子id
151+
"content": comment_item.get("content"), # 评论内容
152+
"user_id": user_info.get("user_id"), # 用户id
153+
"nickname": user_info.get("nickname"), # 用户昵称
154+
"avatar": user_info.get("image"), # 用户头像
155+
"sub_comment_count": comment_item.get("sub_comment_count", 0), # 子评论数
156+
"pictures": ",".join(comment_pictures), # 评论图片
157+
"parent_comment_id": target_comment.get("id", 0), # 父评论id
158+
"last_modify_ts": utils.get_current_timestamp(), # 最后更新时间戳（MediaCrawler程序生成的，主要用途在db存储的时候记录一条记录最新更新时间）
159159
"like_count": comment_item.get("like_count", 0),
160160
}
161161
utils.logger.info(f"[store.xhs.update_xhs_note_comment] xhs note comment:{local_db_item}")
@@ -186,18 +186,18 @@ async def save_creator(user_id: str, creator: Dict):
186186
interaction = i.get('count')
187187

188188
local_db_item = {
189-
'user_id': user_id,
190-
'nickname': user_info.get('nickname'),
191-
'gender': '女' if user_info.get('gender') == 1 else '男',
192-
'avatar': user_info.get('images'),
193-
'desc': user_info.get('desc'),
194-
'ip_location': user_info.get('ipLocation'),
195-
'follows': follows,
196-
'fans': fans,
197-
'interaction': interaction,
189+
'user_id': user_id, # 用户id
190+
'nickname': user_info.get('nickname'), # 昵称
191+
'gender': '女' if user_info.get('gender') == 1 else '男', # 性别
192+
'avatar': user_info.get('images'), # 头像
193+
'desc': user_info.get('desc'), # 个人描述
194+
'ip_location': user_info.get('ipLocation'), # ip地址
195+
'follows': follows, # 关注数
196+
'fans': fans, # 粉丝数
197+
'interaction': interaction, # 互动数
198198
'tag_list': json.dumps({tag.get('tagType'): tag.get('name') for tag in creator.get('tags')},
199-
ensure_ascii=False),
200-
"last_modify_ts": utils.get_current_timestamp(),
199+
ensure_ascii=False), # 标签
200+
"last_modify_ts": utils.get_current_timestamp(), # 最后更新时间戳（MediaCrawler程序生成的，主要用途在db存储的时候记录一条记录最新更新时间）
201201
}
202202
utils.logger.info(f"[store.xhs.save_creator] creator:{local_db_item}")
203203
await XhsStoreFactory.create_store().store_creator(local_db_item)

0 commit comments

Comments
 (0)