classroom htmlからの取得

Author: kakeruzoku

scapi/sites/classroom.py

@@ -26,6 +26,7 @@
     dt_from_isoformat,
     temporary_httpclient,
     page_api_iterative,
+    page_html_iterative,
     split
 )
 from ..utils.client import HTTPClient
@@ -228,45 +229,60 @@ async def create_class_studio(self,title:str,description:str|None=None) -> Studi
         studio.title = data.get("gallery_title")
         return studio
 
-    async def get_class_studios(self,start_page:int|None=None,end_page:int|None=None) -> AsyncGenerator[Studio]:
+    async def get_class_studios(self,start_page:int|None=None,end_page:int|None=None,*,use_api:bool=False) -> AsyncGenerator[Studio]:
         """
         クラスのスタジオを取得する。
 
         Args:
             start_page (int|None, optional): 取得するスタジオの開始ページ位置。初期値は1です。
             end_page (int|None, optional): 取得するスタジオの終了ページ位置。初期値はstart_pageの値です。
+            use_api (bool, optional): 教師向けAPIを使用するか。教師の場合のみ使用できます。
 
         Yields:
             Studio: 取得したスタジオ
         """
-        self.require_session()
-        async for _s in page_api_iterative(
-            self.client,f"https://scratch.mit.edu/site-api/classrooms/studios/{self.id}/",
-            start_page,end_page
-        ):
-            _s:OldAnyObjectPayload[OldStudioPayload]
-            yield Studio._create_from_data(_s["pk"],_s["fields"],self.client_or_session,Studio._update_from_old_data)
+        if use_api:
+            self.require_session()
+            async for _s in page_api_iterative(
+                self.client,f"https://scratch.mit.edu/site-api/classrooms/studios/{self.id}/",
+                start_page,end_page
+            ):
+                yield Studio._create_from_data(_s["pk"],_s["fields"],self.client_or_session,Studio._update_from_old_data)
+        else:
+            async for _t in page_html_iterative(
+                self.client,f"https://scratch.mit.edu/classes/{self.id}/studios/",
+                start_page,end_page,list_class="gallery thumb item"
+            ):
+                yield Studio._create_from_html(_t,self.client_or_session,host=self.educator)
 
-    async def get_class_students(self,start_page:int|None=None,end_page:int|None=None) -> AsyncGenerator[User]:
+    async def get_students(self,start_page:int|None=None,end_page:int|None=None,*,use_api:bool=False) -> AsyncGenerator[User]:
         """
         クラスの生徒を取得する。
 
         Args:
             start_page (int|None, optional): 取得するユーザーの開始ページ位置。初期値は1です。
             end_page (int|None, optional): 取得するユーザーの終了ページ位置。初期値はstart_pageの値です。
+            use_api (bool, optional): 教師向けAPIを使用するか。教師の場合のみ使用できます。
 
         Yields:
             User: 取得したユーザー
         """
-        self.require_session()
-        async for _u in page_api_iterative(
-            self.client,f"https://scratch.mit.edu/site-api/classrooms/students/{self.id}/",
-            start_page,end_page
-        ):
-            _u:OldAnyObjectPayload[StudentPayload]
-            yield User._create_from_data(_u["fields"]["user"]["username"],_u["fields"],self.client_or_session,User._update_from_student_data)
+        if use_api:
+            self.require_session()
+            async for _u in page_api_iterative(
+                self.client,f"https://scratch.mit.edu/site-api/classrooms/students/{self.id}/",
+                start_page,end_page
+            ):
+                _u:OldAnyObjectPayload[StudentPayload]
+                yield User._create_from_data(_u["fields"]["user"]["username"],_u["fields"],self.client_or_session,User._update_from_student_data)
+        else:
+            async for _t in page_html_iterative(
+                self.client,f"https://scratch.mit.edu/classes/{self.id}/students/",
+                start_page,end_page,list_class="user thumb item"
+            ):
+                yield User._create_from_html(_t,self.client_or_session)
 
-    async def get_class_activity(
+    async def get_privete_activity(
             self,
             start_page:int|None=None,
             end_page:int|None=None,

scapi/sites/studio.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import datetime
-from typing import TYPE_CHECKING, AsyncGenerator, Final, Literal
+from typing import TYPE_CHECKING, AsyncGenerator, Final, Literal, Self
 
 import aiohttp
 from ..utils.types import (
@@ -20,7 +20,9 @@
     UNKNOWN_TYPE,
     api_iterative,
     dt_from_isoformat,
-    _AwaitableContextManager
+    _AwaitableContextManager,
+    Tag,
+    split
 )
 from ..utils.client import HTTPClient
 from ..utils.error import (
@@ -141,6 +143,17 @@ def _update_from_old_data(self, data:OldStudioPayload):
 
             description=data.get("description")
         )
+
+    @classmethod
+    def _create_from_html(cls,data:Tag,client_or_session:"HTTPClient|Session",*,host:"User|None|UNKNOWN_TYPE"=None) -> Self:
+        _span:Tag = data.find("span",{"class":"title"})
+        _a:Tag = _span.find("a")
+        studio = cls(int(split(str(_a["href"]),"/studios/","/",True)),client_or_session)
+        studio.title = _a.get_text().strip()
+        if host:
+            studio._host = host
+            studio.host_id = host.id
+        return studio
 
     @property
     def created_at(self) -> datetime.datetime|UNKNOWN_TYPE:

scapi/sites/user.py

@@ -3,7 +3,7 @@
 import datetime
 from enum import Enum
 import random
-from typing import TYPE_CHECKING, AsyncGenerator, Final, NamedTuple, Sequence
+from typing import TYPE_CHECKING, AsyncGenerator, Final, NamedTuple, Self, Sequence
 
 import aiohttp
 import bs4
@@ -21,6 +21,7 @@
     MAYBE_UNKNOWN,
     UNKNOWN_TYPE,
     api_iterative,
+    page_html_iterative,
     dt_from_isoformat,
     _AwaitableContextManager,
     Tag,
@@ -124,6 +125,16 @@ def _update_from_student_data(self,data:StudentPayload):
             is_banned=data.get("is_banned")
         )
         self._update_from_old_data(data["user"])
+
+    @classmethod
+    def _create_from_html(cls,data:Tag,client_or_session:"HTTPClient|Session") -> Self:
+        _a:Tag = data.find("a")
+        _img:Tag = data.find("img")
+        user = cls(split(str(_a["href"]),"/users/","/",True),client_or_session)
+        user_id = split(str(_img["data-original"]),"/user/","_") or ""
+        if user_id.isdecimal():
+            user.id = int(user_id)
+        return user
 
     @property
     def joined_at(self) -> datetime.datetime|UNKNOWN_TYPE:
@@ -343,18 +354,12 @@ async def get_loves(self,start_page:int|None=None,end_page:int|None=None) -> Asy
         Yields:
             Project: 取得したプロジェクト
         """
-        start_page = start_page or 1
-        end_page = end_page or start_page
-        if TYPE_CHECKING: _p:Tag
-        for i in range(start_page,end_page+1):
-            try:
-                response = await self.client.get(f"https://scratch.mit.edu/projects/all/{self.username}/loves/",params={"page":i})
-            except NotFound:
-                return
-            data = bs4.BeautifulSoup(response.text, "html.parser")
-            content:Tag = data.find("div",{"class":"box-content"})
-            for _p in content.find_all("li",{"class":"project thumb item"}):
-                yield Project._create_from_html(_p,self.client_or_session)
+
+        async for _t in page_html_iterative(
+            self.client,f"https://scratch.mit.edu/projects/all/{self.username}/loves/",
+            start_page=start_page,end_page=end_page,list_class="project thumb item"
+        ):
+            yield Project._create_from_html(_t,self.client_or_session)
 
 
     async def get_message_count(self) -> int:

scapi/utils/common.py

@@ -172,6 +172,33 @@ async def page_api_iterative(
         if not data:
             return
 
+async def page_html_iterative(
+        _client:"HTTPClient",
+        url:str,
+        start_page:int|None=None,
+        end_page:int|None=None,
+        params:dict[str,str|int|float]|None=None,
+        *,
+        outside_class:str|None="media-grid",
+        list_class:str,
+        list_name:str|None="li"
+    ) -> AsyncGenerator[Tag]:
+    params = params or {}
+    start_page = start_page or 1
+    end_page = end_page or start_page
+    for i in range(start_page,end_page+1):
+        try:
+            response = await _client.get(url,params={"page":i}|params)
+        except NotFound:
+            return
+        data:Tag = bs4.BeautifulSoup(response.text, "html.parser")
+        if outside_class is not None:
+            data = data.find("div",{"class":outside_class})
+        
+        objs:Sequence[Tag] = data.find_all(list_name,{"class":list_class}) # pyright: ignore[reportArgumentType]
+        for obj in objs:
+            yield obj
+        
 def get_client_and_session(client_or_session:"HTTPClient|Session|None") -> tuple["HTTPClient","Session|None"]:
     from .client import HTTPClient
     if client_or_session is None: