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

feat: 知乎支持创作者主页数据爬取(回答、文章、视频)

Browse Source
This commit is contained in:
Relakkes
2024-10-16 21:02:27 +08:00
parent af9d2d8e84
commit da8f1c62b8
8 changed files with 511 additions and 66 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
model/m_zhihu.py
View File

@@ -15,8 +15,8 @@ class ZhihuContent(BaseModel):
question_id: str = Field(default="", description="问题ID, type为answer时有值")
title: str = Field(default="", description="内容标题")
desc: str = Field(default="", description="内容描述")
created_time: int = Field(default="", description="创建时间")
updated_time: int = Field(default="", description="更新时间")
created_time: int = Field(default=0, description="创建时间")
updated_time: int = Field(default=0, description="更新时间")
voteup_count: int = Field(default=0, description="赞同人数")
comment_count: int = Field(default=0, description="评论数量")
source_keyword: str = Field(default="", description="来源关键词")
@@ -25,6 +25,7 @@ class ZhihuContent(BaseModel):
user_link: str = Field(default="", description="用户主页链接")
user_nickname: str = Field(default="", description="用户昵称")
user_avatar: str = Field(default="", description="用户头像地址")
user_url_token: str = Field(default="", description="用户url_token")
class ZhihuComment(BaseModel):
@@ -57,7 +58,15 @@ class ZhihuCreator(BaseModel):
user_link: str = Field(default="", description="用户主页链接")
user_nickname: str = Field(default="", description="用户昵称")
user_avatar: str = Field(default="", description="用户头像地址")
url_token: str = Field(default="", description="用户url_token")
gender: str = Field(default="", description="用户性别")
ip_location: Optional[str] = Field(default="", description="IP地理位置")
follows: int = Field(default=0, description="关注数")
fans: int = Field(default=0, description="粉丝数")
anwser_count: int = Field(default=0, description="回答数")
video_count: int = Field(default=0, description="视频数")
question_count: int = Field(default=0, description="提问数")
article_count: int = Field(default=0, description="文章数")
column_count: int = Field(default=0, description="专栏数")
get_voteup_count: int = Field(default=0, description="获得的赞同数")