mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-07-28 07:20:25 +08:00
refactor: 教学版移除全平台用户个人信息采集与持久化
- 用户 ID 转为匿名 creator_hash,昵称中间脱敏,IP/头像/主页/签名/性别不再采集 - 覆盖 xhs/weibo/bilibili/douyin/kuaishou/tieba/zhihu 7 个平台 - 删除 7 张 creator 档案 ORM 表,15 张内容/评论表新增 creator_hash 列 - B 站禁用粉丝/关注/联系人列表抓取 - 新增 tools/user_hash.py 与 4 个平台的 mock+SQLite 端到端测试 测试: pytest tests/test_no_user_info.py tests/test_weibo_no_user_info.py tests/test_douyin_no_user_info.py tests/test_kuaishou_no_user_info.py (21 passed)
This commit is contained in:
@@ -33,14 +33,12 @@ class TiebaNote(BaseModel):
|
||||
desc: str = Field(default="", description="Post description")
|
||||
note_url: str = Field(..., description="Post link")
|
||||
publish_time: str = Field(default="", description="Publish time")
|
||||
user_link: str = Field(default="", description="User homepage link")
|
||||
user_nickname: str = Field(default="", description="User nickname")
|
||||
user_avatar: str = Field(default="", description="User avatar URL")
|
||||
creator_hash: str = Field(default="", description="创作者匿名哈希(不存原始用户链接)")
|
||||
user_nickname: str = Field(default="", description="User nickname (已脱敏)")
|
||||
tieba_name: str = Field(..., description="Tieba name")
|
||||
tieba_link: str = Field(..., description="Tieba link")
|
||||
total_replay_num: int = Field(default=0, description="Total reply count")
|
||||
total_replay_page: int = Field(default=0, description="Total reply pages")
|
||||
ip_location: Optional[str] = Field(default="", description="IP location")
|
||||
source_keyword: str = Field(default="", description="Source keyword")
|
||||
|
||||
|
||||
@@ -52,11 +50,9 @@ class TiebaComment(BaseModel):
|
||||
comment_id: str = Field(..., description="Comment ID")
|
||||
parent_comment_id: str = Field(default="", description="Parent comment ID")
|
||||
content: str = Field(..., description="Comment content")
|
||||
user_link: str = Field(default="", description="User homepage link")
|
||||
user_nickname: str = Field(default="", description="User nickname")
|
||||
user_avatar: str = Field(default="", description="User avatar URL")
|
||||
creator_hash: str = Field(default="", description="创作者匿名哈希(不存原始用户链接)")
|
||||
user_nickname: str = Field(default="", description="User nickname (已脱敏)")
|
||||
publish_time: str = Field(default="", description="Publish time")
|
||||
ip_location: Optional[str] = Field(default="", description="IP location")
|
||||
sub_comment_count: int = Field(default=0, description="Sub-comment count")
|
||||
note_id: str = Field(..., description="Post ID")
|
||||
note_url: str = Field(..., description="Post link")
|
||||
@@ -67,14 +63,10 @@ class TiebaComment(BaseModel):
|
||||
|
||||
class TiebaCreator(BaseModel):
|
||||
"""
|
||||
Baidu Tieba creator
|
||||
Baidu Tieba creator(教学版:个人资料不再落库,仅作内存对象)
|
||||
"""
|
||||
user_id: str = Field(..., description="User ID")
|
||||
user_name: str = Field(..., description="Username")
|
||||
nickname: str = Field(..., description="User nickname")
|
||||
gender: str = Field(default="", description="User gender")
|
||||
avatar: str = Field(..., description="User avatar URL")
|
||||
ip_location: Optional[str] = Field(default="", description="IP location")
|
||||
creator_hash: str = Field(default="", description="创作者匿名哈希(不存原始用户链接)")
|
||||
user_nickname: str = Field(default="", description="User nickname (已脱敏)")
|
||||
follows: int = Field(default=0, description="Follows count")
|
||||
fans: int = Field(default=0, description="Fans count")
|
||||
registration_duration: str = Field(default="", description="Registration duration")
|
||||
|
||||
@@ -19,8 +19,6 @@
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
from typing import Optional
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
@@ -40,12 +38,8 @@ class ZhihuContent(BaseModel):
|
||||
voteup_count: int = Field(default=0, description="Upvote count")
|
||||
comment_count: int = Field(default=0, description="Comment count")
|
||||
source_keyword: str = Field(default="", description="Source keyword")
|
||||
|
||||
user_id: str = Field(default="", description="User ID")
|
||||
user_link: str = Field(default="", description="User homepage link")
|
||||
user_nickname: str = Field(default="", description="User nickname")
|
||||
user_avatar: str = Field(default="", description="User avatar URL")
|
||||
user_url_token: str = Field(default="", description="User url_token")
|
||||
creator_hash: str = Field(default="", description="Creator anonymized hash")
|
||||
user_nickname: str = Field(default="", description="User nickname (masked)")
|
||||
|
||||
|
||||
class ZhihuComment(BaseModel):
|
||||
@@ -57,30 +51,21 @@ class ZhihuComment(BaseModel):
|
||||
parent_comment_id: str = Field(default="", description="Parent comment ID")
|
||||
content: str = Field(default="", description="Comment content")
|
||||
publish_time: int = Field(default=0, description="Publish time")
|
||||
ip_location: Optional[str] = Field(default="", description="IP location")
|
||||
sub_comment_count: int = Field(default=0, description="Sub-comment count")
|
||||
like_count: int = Field(default=0, description="Like count")
|
||||
dislike_count: int = Field(default=0, description="Dislike count")
|
||||
content_id: str = Field(default="", description="Content ID")
|
||||
content_type: str = Field(default="", description="Content type (article | answer | zvideo)")
|
||||
|
||||
user_id: str = Field(default="", description="User ID")
|
||||
user_link: str = Field(default="", description="User homepage link")
|
||||
user_nickname: str = Field(default="", description="User nickname")
|
||||
user_avatar: str = Field(default="", description="User avatar URL")
|
||||
creator_hash: str = Field(default="", description="Creator anonymized hash")
|
||||
user_nickname: str = Field(default="", description="User nickname (masked)")
|
||||
|
||||
|
||||
class ZhihuCreator(BaseModel):
|
||||
"""
|
||||
Zhihu creator
|
||||
Zhihu creator (in-memory only; personal profile is no longer persisted)
|
||||
"""
|
||||
user_id: str = Field(default="", description="User ID")
|
||||
user_link: str = Field(default="", description="User homepage link")
|
||||
user_nickname: str = Field(default="", description="User nickname")
|
||||
user_avatar: str = Field(default="", description="User avatar URL")
|
||||
url_token: str = Field(default="", description="User url_token")
|
||||
gender: str = Field(default="", description="User gender")
|
||||
ip_location: Optional[str] = Field(default="", description="IP location")
|
||||
creator_hash: str = Field(default="", description="Creator anonymized hash")
|
||||
user_nickname: str = Field(default="", description="User nickname (masked)")
|
||||
follows: int = Field(default=0, description="Follows count")
|
||||
fans: int = Field(default=0, description="Fans count")
|
||||
anwser_count: int = Field(default=0, description="Answer count")
|
||||
|
||||
Reference in New Issue
Block a user