Merge branch 'dev'

JianshuResearchTools/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "2.10.0"
+__version__ = "2.10.1"
 
 from . import (article, beikeisland, collection, island, notebook, objects,
                rank, user)

JianshuResearchTools/article.py

@@ -192,6 +192,7 @@ def GetArticlePublishTime(article_url: str, disable_check: bool = False) -> date
 
     Args:
         article_url (str): 文章 URL
+        disable_check (str): 禁用参数有效性检查. Defaults to False.
 
     Returns:
         datetime: 文章发布时间
@@ -530,7 +531,6 @@ def GetArticleAllCommentsData(article_id: int, count: int = 10, author_only: boo
         author_only (bool, optional): 为 True 时只获取作者发布的评论，包含作者发布的子评论及其父评论. Defaults to False.
         sorting_method (str, optional): 排序方式，为”positive“时按时间正序排列，为”reverse“时按时间倒序排列. Defaults to "positive".
         max_count (int, optional): 获取的文章评论信息数量上限，Defaults to None.
-        disable_check (bool): 禁用参数有效性检查. Defaults to False.
 
     Yields:
         Iterator[Dict], None, None]: 文章信息

JianshuResearchTools/assert_funcs.py

@@ -1,6 +1,6 @@
 from functools import lru_cache
-from typing import Any
 from re import compile as re_compile
+from typing import Any
 
 from .basic_apis import (GetArticleJsonDataApi, GetCollectionJsonDataApi,
                          GetIslandJsonDataApi, GetNotebookJsonDataApi,
@@ -28,18 +28,18 @@
 JIANSHU_ISLAND_POST_URL_REGEX = re_compile(r"^https://www\.jianshu\.com/gp/\w{16}/?$")
 
 
-def AssertType(object: Any, type_obj: Any) -> None:
+def AssertType(obj: Any, type_obj: Any) -> None:
     """判断对象是否是指定类型
 
     Args:
-        object (Any): 需要进行判断的对象
+        obj (Any): 需要进行判断的对象
         type_obj (object): 目标类型
 
     Raises:
         TypeError: 对象类型错误时抛出此错误
     """
-    if not isinstance(object, type_obj):
-        raise TypeError(f"{object} 不是 {type_obj.__name__} 类型，而是 { type(object).__name__ } 类型")
+    if not isinstance(obj, type_obj):
+        raise TypeError(f"{obj} 不是 {type_obj.__name__} 类型，而是 { type(obj).__name__ } 类型")
 
 
 def AssertJianshuUrl(string: str) -> None:

JianshuResearchTools/basic_apis.py

@@ -1,8 +1,9 @@
-from typing import Dict, List, Union
+from typing import Dict, List, Union, Optional
 
 from httpx import get as httpx_get
 from httpx import post as httpx_post
 from lxml import etree
+from lxml.etree import _Element
 
 from .headers import (BeikeIsland_request_header, PC_header,
                       api_request_header, mobile_header)
@@ -37,7 +38,7 @@ def GetArticleJsonDataApi(article_url: str) -> Dict:
     return json_obj
 
 
-def GetArticleHtmlJsonDataApi(article_url: str) -> Dict:
+def GetArticleHtmlJsonDataApi(article_url: str) -> _Element:
     source = httpx_get(article_url, headers=PC_header).content
     html_obj = etree.HTML(source)
     json_obj = json_loads(html_obj.xpath("//script[@id='__NEXT_DATA__']/text()")[0])
@@ -190,7 +191,7 @@ def GetDailyArticleRankListJsonDataApi() -> Dict:
     return json_obj
 
 
-def GetArticlesFPRankListJsonDataApi(date: str, type_: str) -> Dict:  # 避免覆盖内置函数
+def GetArticlesFPRankListJsonDataApi(date: str, type_: Optional[str]) -> Dict:  # 避免覆盖内置函数
     params = {
         "date": date,
         "type": type_
@@ -207,7 +208,7 @@ def GetUserJsonDataApi(user_url: str) -> Dict:
     return json_obj
 
 
-def GetUserPCHtmlDataApi(user_url: str) -> Dict:
+def GetUserPCHtmlDataApi(user_url: str) -> _Element:
     source = httpx_get(user_url, headers=PC_header).content
     html_obj = etree.HTML(source)
     return html_obj
@@ -236,7 +237,7 @@ def GetUserArticlesListJsonDataApi(user_url: str, page: int,
     return json_obj
 
 
-def GetUserFollowingListHtmlDataApi(user_url: str, page: int):
+def GetUserFollowingListHtmlDataApi(user_url: str, page: int) -> _Element:
     request_url = user_url.replace("/u/", "/users/") + "/following"
     params = {
         "page": page
@@ -246,7 +247,7 @@ def GetUserFollowingListHtmlDataApi(user_url: str, page: int):
     return html_obj
 
 
-def GetUserFollowersListHtmlDataApi(user_url: str, page: int):
+def GetUserFollowersListHtmlDataApi(user_url: str, page: int) -> _Element:
     request_url = user_url.replace("/u/", "/users/") + "/followers"
     params = {
         "page": page
@@ -256,7 +257,7 @@ def GetUserFollowersListHtmlDataApi(user_url: str, page: int):
     return html_obj
 
 
-def GetUserNextAnniversaryDayHtmlDataApi(user_slug: str):
+def GetUserNextAnniversaryDayHtmlDataApi(user_slug: str) -> _Element:
     request_url = f"https://www.jianshu.com/mobile/u/{user_slug}/anniversary"
     source = httpx_get(request_url, headers=mobile_header).content
     html_obj = etree.HTML(source)
@@ -270,7 +271,7 @@ def GetIslandPostJsonDataApi(post_slug: str) -> List[Dict]:
     return json_obj
 
 
-def GetUserTimelineHtmlDataApi(uslug: str, max_id: int) -> Dict:
+def GetUserTimelineHtmlDataApi(uslug: str, max_id: int) -> _Element:
     request_url = f"https://www.jianshu.com/users/{uslug}/timeline"
     params = {
         "max_id": max_id

JianshuResearchTools/beikeisland.py

@@ -126,30 +126,45 @@ def GetBeikeIslandTradeOrderInfo(trade_type: str, page: int = 1) -> List[Dict]:
         "buy": 2,
         "sell": 1
     }[trade_type]
-    json_obj = GetBeikeIslandTradeListJsonDataApi(pageIndex=page, retype=retype)
+    json_obj = GetBeikeIslandTradeListJsonDataApi(pageIndex=page,
+                                                  retype=retype)
     result = []
     for item in json_obj["data"]["tradelist"]:
         item_data = {
-            "tradeid": item["id"],
-            "tradeslug": item["tradeno"],  # ? 我也不确定这个 no 什么意思,回来去问问
-            "user": {
-                "jianshuname": item["jianshuname"],
-                "bkname": item["reusername"],  # ? 还有个 nickname，不知道哪个对
-                "avatar_url": item["avatarurl"],
-                "userlevelcode": item["levelnum"],
-                "userlevel": item["userlevel"],
-                "user_trade_count": item["tradecount"]
+            "trade_id": item["id"],
+            "trade_slug": item["tradeno"],
+            "publish_time": datetime.fromisoformat(item["releasetime"]),
+            "status": {
+                "code": item["statuscode"],
+                "text": item["statustext"]
             },
-            "total": item["recount"],
-            "traded": item["recount"] - item["cantradenum"],
-            "remaining": item["cantradenum"],
-            "price": item["reprice"],
-            "minimum_limit": item["minlimit"],
-            "percentage": item["compeletper"],
-            "statuscode": item["statuscode"],
-            "status": item["statustext"],
-            "publish_time": datetime.fromisoformat(item["releasetime"])
+            "trade": {
+                "total": item["recount"],
+                "traded": item["recount"] - item["cantradenum"],
+                "remaining": item["cantradenum"],
+                "minimum_trade_limit": item["minlimit"],
+                "traded_percentage": round(
+                    float(item["compeletper"]) / 100, 3
+                ),
+                "price": item["reprice"],
+            }
         }
+
+        if item["anonymity"]:
+            item_data["user"] = {
+                "is_anonymity": True
+            }
+        else:
+            item_data["user"] = {
+                "is_anonymity": False,
+                "name": item["reusername"],
+                "avatar_url": item["avatarurl"],
+                "level": {
+                    "code": item["levelnum"],
+                    "text": item["userlevel"]
+                }
+            }
+
         result.append(item_data)
     return result
 

JianshuResearchTools/convert.py

@@ -38,7 +38,7 @@ def UserSlugToUserId(user_slug: str) -> int:
     """用户 Slug 转用户 ID
 
     Args:
-        user_url (str): 用户 Slug
+        user_slug (str): 用户 Slug
 
     Returns:
         int: 用户 ID
@@ -318,7 +318,7 @@ def IslandPostUrlToIslandPostSlug(post_url: str) -> str:
     """小岛文章 URL 转小岛帖子 Slug
 
     Args:
-        island_url (str): 小岛帖子 URL
+        post_url (str): 小岛帖子 URL
 
     Returns:
         str: 小岛帖子 Slug
@@ -333,7 +333,7 @@ def IslandPostSlugToIslandPostUrl(post_slug: str) -> str:
     """小岛帖子 Slug 转小岛帖子 URL
 
     Args:
-        island_url (str): 小岛帖子 Slug
+        post_slug (str): 小岛帖子 Slug
 
     Returns:
         str: 小岛帖子 URL

JianshuResearchTools/island.py

@@ -11,7 +11,7 @@
 __all__ = [
     "GetIslandName", "GetIslandAvatarUrl", "GetIslandIntroduction",
     "GetIslandMembersCount", "GetIslandPostsCount", "GetIslandCategory",
-    "GetIslandPostFullConetnt", "GetIslandPosts", "GetIslandAllBasicData",
+    "GetIslandPostFullContent", "GetIslandPosts", "GetIslandAllBasicData",
     "GetIslandAllPostsData"
 ]
 
@@ -124,11 +124,11 @@ def GetIslandCategory(island_url: str, disable_check: bool = False) -> str:
     return result
 
 
-def GetIslandPostFullConetnt(post_url: str, disable_check: bool = False) -> str:
+def GetIslandPostFullContent(post_url: str, disable_check: bool = False) -> str:
     """获取小岛帖子完整内容
 
     Args:
-        island_url (str): 小岛 URL
+        post_url (str): 小岛帖子 URL
         disable_check (bool): 禁用参数有效性检查. Defaults to False.
 
     Returns:
@@ -153,9 +153,9 @@ def GetIslandPosts(island_url: str, start_sort_id: int = None, count: int = 10,
             count (int, optional): 每次返回的数据数量. Defaults to 10.
             topic_id (int, optional): 话题 ID. Defaults to None.
             sorting_method (str, optional): 排序方法，"time" 为按照发布时间排序，
-        "comment_time" 为按照最近评论时间排序，"hot" 为按照热度排序. Defaults to "time".
+            "comment_time" 为按照最近评论时间排序，"hot" 为按照热度排序. Defaults to "time".
             get_full_content (bool, optional): 为 True 时，当检测到获取的帖子内容不全时，
-        自动调用 GetIslandPostFullConetnt 函数获取完整内容并替换. Defaults to False.
+            自动调用 GetIslandPostFullContent 函数获取完整内容并替换. Defaults to False.
             disable_check (bool): 禁用参数有效性检查. Defaults to False.
 
         Returns:
@@ -170,7 +170,8 @@ def GetIslandPosts(island_url: str, start_sort_id: int = None, count: int = 10,
         "most_valuable": "best"
     }[sorting_method],
     json_obj = GetIslandPostsJsonDataApi(group_slug=IslandUrlToIslandSlug(island_url),
-                                         max_id=start_sort_id, count=count, topic_id=topic_id, order_by=order_by)
+                                         max_id=start_sort_id, count=count, topic_id=topic_id,
+                                         order_by=order_by)
 
     result = []
     for item in json_obj:
@@ -228,7 +229,7 @@ def GetIslandPosts(island_url: str, start_sort_id: int = None, count: int = 10,
         except KeyError:
             pass  # 没有话题则跳过
         if get_full_content and "..." in item_data["content"]:  # 获取到的帖子内容不全
-            item_data["content"] = GetIslandPostFullConetnt(IslandPostSlugToIslandPostUrl(item_data["pslug"]),
+            item_data["content"] = GetIslandPostFullContent(IslandPostSlugToIslandPostUrl(item_data["pslug"]),
                                                             disable_check=True)
         result.append(item_data)
     return result
@@ -272,7 +273,7 @@ def GetIslandAllPostsData(island_url: str, count: int = 10,
         sorting_method (str, optional): 排序方法，time 为按照发布时间排序，
         comment_time 为按照最近评论时间排序，hot 为按照热度排序. Defaults to "time".
         get_full_content (bool, optional): 为 True 时，当检测到获取的帖子内容不全时，
-    自动调用 GetIslandPostFullConetnt 函数获取完整内容并替换. Defaults to False.
+        自动调用 GetIslandPostFullContent 函数获取完整内容并替换. Defaults to False.
         max_count (int, optional): 获取的小岛帖子信息数量上限，Defaults to None.
         disable_check (bool): 禁用参数有效性检查. Defaults to False.
 

JianshuResearchTools/objects.py

@@ -10,7 +10,8 @@
 from .convert import (ArticleSlugToArticleUrl, CollectionSlugToCollectionUrl,
                       IslandSlugToIslandUrl, IslandUrlToIslandSlug,
                       NotebookSlugToNotebookUrl, UserSlugToUserUrl,
-                      UserUrlToUserSlug)
+                      UserUrlToUserSlug, ArticleUrlToArticleSlug,
+                      NotebookUrlToNotebookId, NotebookUrlToNotebookSlug, CollectionUrlToCollectionSlug)
 from .exceptions import InputError
 from .utils import CallWithoutCheck, NameValueMappingToString, OnlyOne
 
@@ -85,7 +86,7 @@ def clear_cache():
     _cache_dict.clear()
 
 
-class User():
+class User:
     """用户类
     """
     def __init__(self, user_url: str = None, *, user_slug: str = None):
@@ -416,7 +417,7 @@ def __str__(self) -> str:
         }, title="用户信息摘要")
 
 
-class Article():
+class Article:
     """文章类
     """
     def __init__(self, article_url: str = None, article_slug: str = None):
@@ -479,7 +480,7 @@ def slug(self) -> str:
         Returns:
             str: 文章 Slug
         """
-        return article.GetArticleSlug(self._url)
+        return ArticleUrlToArticleSlug(self._url)
 
     @property
     @cache_result_wrapper
@@ -709,7 +710,7 @@ def __str__(self) -> str:
         }, title="文章信息摘要")
 
 
-class Notebook():
+class Notebook:
     """文集类
     """
     def __init__(self, notebook_url: str = None, notebook_slug: str = None):
@@ -772,7 +773,7 @@ def id(self) -> int:
         Returns:
             int: 文集 ID
         """
-        return notebook.GetNotebookId(self._url)
+        return NotebookUrlToNotebookId(self._url)
 
     @property
     @cache_result_wrapper
@@ -782,7 +783,7 @@ def slug(self) -> str:
         Returns:
             str: 文集 Slug
         """
-        return notebook.GetNotebookSlug(self._url)
+        return NotebookUrlToNotebookSlug(self._url)
 
     @property
     @cache_result_wrapper
@@ -910,7 +911,7 @@ def __str__(self) -> str:
         }, title="文集信息摘要")
 
 
-class Collection():
+class Collection:
     """专题类
     """
     def __init__(self, collection_url: str = None, collection_slug: str = None,
@@ -979,7 +980,7 @@ def slug(self) -> str:
         Returns:
             str: 专题 Slug
         """
-        return collection.GetCollectionSlug(self._url)
+        return CollectionUrlToCollectionSlug(self._url)
 
     @property
     @cache_result_wrapper
@@ -1076,7 +1077,7 @@ def editors_info(self, page: int = 1) -> List[Dict]:
         """获取专题编辑信息
 
         Args:
-            page (int, optional): 页码. Defause to 1.
+            page (int, optional): 页码. Default to 1.
 
         Raises:
             InputError: 因缺少 ID 参数而无法获取结果时抛出此异常
@@ -1181,7 +1182,7 @@ def __str__(self) -> str:
         }, title="专题信息摘要")
 
 
-class Island():
+class Island:
     """小岛类
     """
     def __init__(self, island_url: str = None, island_slug: str = None):