修复已知问题

Author: JoeanAmier

docs/TikTokDownloader文档.md

@@ -376,6 +376,11 @@ https://www.douyin.com/note/123456789
 <td align="center">每次从服务器接收的数据块大小, 单位字节; 默认值：<code>2621440</code>(2.5 MB)</td>
 </tr>
 <tr>
+<td align="center">timeout</td>
+<td align="center">int</td>
+<td align="center">请求数据的超时限制, 单位秒; 默认值：<code>10</code></td>
+</tr>
+<tr>
 <td align="center">max_retry</td>
 <td align="center">int</td>
 <td align="center">发送请求获取数据发生异常时重试的最大次数<br>设置为 <code>0</code> 代表关闭重试, 默认值: <code>10</code></td>
@@ -483,6 +488,7 @@ https://www.douyin.com/note/123456789
   "download": true,
   "max_size": 104857600,
   "chunk": 10485760,
+  "timeout": 5,
   "max_retry": 10,
   "max_pages": 2,
   "default_mode": "6 2 1",

src/application/main_complete.py

@@ -162,7 +162,7 @@ def __init__(self, parameter: "Parameter", database: "Database", ):
             ("批量下载账号作品(抖音)", self.account_acquisition_interactive,),
             ("批量下载链接作品(抖音)", self.detail_interactive,),
             ("获取直播推流地址(抖音)", self.live_interactive,),
-            ("采集作品评论数据(抖音)", self.comment_interactive,),
+            # ("采集作品评论数据(抖音)", self.comment_interactive,),
             ("批量下载合集作品(抖音)", self.mix_interactive,),
             # ("采集账号详细数据(抖音)", self.disable_function,),
             # ("采集搜索结果数据(抖音)", self.disable_function,),
@@ -486,17 +486,20 @@ async def _batch_process_detail(self,
                                     addition: str = None,
                                     tiktok=False,
                                     title: str = None,
+                                    collect_id: str = None,
                                     ):
         self.logger.info("开始提取作品数据")
         id_, name, mid, title, mark, data = self.extractor.preprocessing_data(
-            data, id_, mark, post, mix, tiktok, title, )
+            data, id_, mark, post, mix, tiktok, title, collect_id=collect_id, )
         self.__display_extracted_information(
             mix, id_, name, mid, title, mark, )
         addition = addition or ("合集作品" if mix else "发布作品" if post else "喜欢作品")
         old_mark = f"{m["MARK"]}_{addition}" if (
             m := await self.cache.has_cache(
                 mid if mix else id_)) else None
-        async with logger(root, name=f"{'MID' if mix else 'UID'}{mid if mix else id_}_{mark}_{addition}", old=old_mark,
+        async with logger(root,
+                          name=f"{self._generate_prefix(mix=mix, collect=bool(collect_id))}{self._generate_id(id_, mid, mix=mix, collect=bool(collect_id))}_{mark}_{addition}",
+                          old=old_mark,
                           console=self.console, **params) as recorder:
             data = await self.extractor.run(
                 data,
@@ -512,16 +515,35 @@ async def _batch_process_detail(self,
             return data
         await self.cache.update_cache(
             self.parameter.folder_mode,
-            "MID" if mix else "UID",
-            mid if mix else id_,
+            self._generate_prefix(mix=mix, collect=bool(collect_id)),
+            self._generate_id(id_, mid, mix=mix, collect=bool(collect_id)),
             mark,
             title if mix else name,
             addition,
         )
         await self.download_account_detail(
-            data, id_, name, mark, mid, title, addition, tiktok, )
+            data, id_, name, mark, self._generate_id(id_, mid, mix=mix, collect=bool(collect_id)), title, addition,
+            tiktok, collect=bool(collect_id), )
         return True
 
+    @staticmethod
+    def _generate_prefix(user=True, mix=False, collect=False):
+        if collect:
+            return "CID"
+        if mix:
+            return "MID"
+        if user:
+            return "UID"
+
+    @staticmethod
+    def _generate_id(id_, mid, user=True, mix=False, collect=False):
+        if collect:
+            return mid
+        if mix:
+            return mid
+        if user:
+            return id_
+
     def __display_extracted_information(
             self,
             mix: bool,
@@ -544,6 +566,7 @@ async def download_account_detail(
             title: str = None,
             addition: str = None,
             tiktok: bool = False,
+            collect=False,
     ):
         await self.downloader.run(
             data,
@@ -555,6 +578,7 @@ async def download_account_detail(
             addition=addition,
             mid=mid,
             title=title,
+            collect=collect,
         )
 
     async def detail_interactive(self, select="", *args, **kwargs):
@@ -906,7 +930,8 @@ async def mix_inquire_collection(self) -> list[str]:
         return self.input_download_index(data)
 
     def input_download_index(self, data: list[dict]) -> list[str]:
-        return self.__input_download_index(data)[-1]
+        _, id_ = self.__input_download_index(data)
+        return id_
 
     def __input_download_index(self,
                                data: list[dict],
@@ -917,15 +942,14 @@ def __input_download_index(self,
         self.console.print(f"{text}列表：")
         for i, j in enumerate(data, start=1):
             self.console.print(f"{i}. {j[key]}")
-        index = self.console.input(f"请输入需要下载的{text}序号(输入 ALL 下载全部{text})：")
+        index = self.console.input(f"请输入需要下载的{text}序号(多个序号使用空格分隔，输入 ALL 下载全部{text})：")
         try:
             if index.upper() == "ALL":
                 return zip(*[(d[key], d["id"]) for d in data])
-            if 0 <= (i := int(index) - 1) <= len(data):
-                return [data[i][key]], [data[i]["id"]]
-            self.console.print(f"{text}序号输入错误！", style=WARNING)
-            raise ValueError
+            index = {int(i) for i in index.split()}
+            return zip(*[(d[key], d["id"]) for i, d in enumerate(data, start=1) if i in index])
         except ValueError:
+            self.console.print(f"{text}序号输入错误！", style=WARNING)
             return []
 
     async def mix_txt(self, root, params, logger):
@@ -1331,7 +1355,10 @@ async def collection_interactive(self, *args, **kwargs):
     @check_cookie_state(tiktok=False)
     async def collects_interactive(self, *args, **kwargs):
         if sec_user_id := await self.__check_owner_url():
-            names, ids = await self.__get_collects_list()
+            try:
+                names, ids = await self.__get_collects_list()
+            except ValueError:
+                names, ids = [], []
             root, params, logger = self.record.run(self.parameter)
             start = time()
             for i, j in zip(names, ids):
@@ -1465,6 +1492,7 @@ async def _deal_collects_data(
             addition="收藏夹作品",
             tiktok=tiktok,
             title=name,
+            collect_id=id_,
         )
 
     async def hashtag_interactive(

src/config/parameter.py

@@ -383,8 +383,8 @@ def __check_chunk(self, chunk: int) -> int:
             self.logger.info(f"chunk 参数已设置为 {chunk}", False)
             return chunk
         self.logger.warning(
-            f"chunk 参数 {chunk} 设置错误，程序将使用默认值：{1024 * 1024}", )
-        return 1024 * 1024
+            f"chunk 参数 {chunk} 设置错误，程序将使用默认值：{int(1024 * 1024 * 2.5)}", )
+        return int(1024 * 1024 * 2.5)
 
     def __check_max_retry(self, max_retry: int) -> int:
         if isinstance(max_retry, int) and max_retry >= 0:

src/config/settings.py

@@ -87,7 +87,8 @@ class Settings:
         "twc_tiktok": "",
         "download": True,
         "max_size": 0,
-        "chunk": 1024 * 1024,  # 每次从服务器接收的数据块大小
+        "chunk": int(1024 * 1024 * 2.5),  # 每次从服务器接收的数据块大小
+        "timeout": 10,
         "max_retry": 5,  # 重试最大次数
         "max_pages": 0,
         "default_mode": "",

src/downloader/download.py

@@ -136,16 +136,18 @@ async def run_batch(
             addition="发布作品",
             mid: str = None,
             title: str = None,
+            collect=False,
     ):
         # assert addition in {"喜欢作品", "收藏作品", "发布作品", "合集作品"}, ValueError
         mix = addition == "合集作品"
         root = self.storage_folder(
-            mid if mix else id_,
+            mid if (mix or collect) else id_,
             title if mix else name,
             not mix,
             mark,
             addition,
-            mix)
+            mix,
+            collect=collect)
         await self.batch_processing(data, root, tiktok=tiktok, )
 
     async def run_general(self, data: list[dict], tiktok: bool):
@@ -547,11 +549,14 @@ def storage_folder(
             mark: str = None,
             addition: str = None,
             mix=False,
-            folder_name: str = None) -> Path:
-        if batch and all((id_, name, addition)):
+            folder_name: str = None,
+            collect=False, ) -> Path:
+        if collect and all((id_, name, addition)):
+            folder_name = f"CID{id_}_{mark or name}_{addition}"
+        elif batch and all((id_, name, addition)):
             folder_name = f"UID{id_}_{mark or name}_{addition}"
         elif mix and all((id_, name, addition)):
-            folder_name = f"MIX{id_}_{mark or name}_{addition}"
+            folder_name = f"MID{id_}_{mark or name}_{addition}"
         else:
             folder_name = folder_name or self.folder_name
         folder = self.root.joinpath(folder_name)

src/extract/extractor.py

@@ -526,6 +526,7 @@ def preprocessing_data(self,
                            mix=False,
                            tiktok=False,
                            title=None,
+                           collect_id=None,
                            ) -> tuple:
         if tiktok:
             params = {
@@ -552,6 +553,7 @@ def preprocessing_data(self,
             post,
             mix,
             **params,
+            collect_id=collect_id,
         )
 
     def __preprocessing_data(self,
@@ -566,6 +568,7 @@ def __preprocessing_data(self,
                              nickname="",
                              mix_name="",
                              title="",
+                             collect_id=None
                              ) -> tuple:
         for item in data:
             item = self.generate_data_object(item)
@@ -586,7 +589,7 @@ def __preprocessing_data(self,
                                          default="无效合集标题")
         mark = self.cleaner.filter_name(
             mark, inquire=False, default=title if mix else name)
-        return id_, name.strip(), mid, title.strip(
+        return id_, name.strip(), collect_id or mid, title.strip(
         ), mark.strip(), data[:None if post else -1]
 
     def __platform_classify_detail(

src/interface/account.py

@@ -154,11 +154,11 @@ async def favorite_mode(self):
         if self.sec_user_id != (s := info.get("sec_uid")):
             self.log.error(
                 f"sec_user_id {self.sec_user_id} 与 {s} 不一致")
-            self.__generate_temp_data()
+            self._generate_temp_data()
         else:
             self.response.append({"author": info})
 
-    def __generate_temp_data(self, ):
+    def _generate_temp_data(self, ):
         temp_data = timestamp()
         self.log.warning(f"获取账号昵称失败，本次运行将临时使用 {temp_data} 作为账号昵称和 UID")
         temp_dict = {

src/interface/account_tiktok.py

@@ -128,7 +128,7 @@ async def favorite_mode(self):
         if self.sec_user_id != (s := info.get("sec_uid")):
             self.log.error(
                 f"sec_user_id {self.sec_user_id} 与 {s} 不一致")
-            self.__generate_temp_data()
+            self._generate_temp_data()
         else:
             self.response.append({"author": info})
 

src/interface/template.py

@@ -4,7 +4,6 @@
 from typing import TYPE_CHECKING
 from typing import Type
 from typing import Union
-from urllib.parse import quote
 
 from httpx import AsyncClient
 from rich.progress import (
@@ -21,6 +20,8 @@
 from src.tools import TikTokDownloaderError
 from src.tools import capture_error_request
 
+# from urllib.parse import quote
+
 # from urllib.parse import urlencode
 
 if TYPE_CHECKING:
@@ -313,16 +314,9 @@ def __record_request_messages(
 
     def deal_url_params(self, params: dict, method="GET", **kwargs, ):
         if params:
-            params["a_bogus"] = quote(
-                self.ab.get_value(
-                    params,
-                    method,
-                ),
-                safe="",
-            )
-            # params["a_bogus"] = quote(
-            #     self.ab.generate_abogus(
-            #         urlencode(params), method, )[1], safe="", )
+            params["a_bogus"] = self.ab.get_value(params, method, )
+            # params["a_bogus"] = self.ab.generate_abogus(
+            #     urlencode(params), method, )[1]
 
     def summary_works(self, ) -> None:
         self.log.info(f"共获取到 {len(self.response)} 个{self.text}")
@@ -430,6 +424,6 @@ async def request_data(self,
 
     def deal_url_params(self, params: dict, number=8, **kwargs, ):
         if params:
-            params["X-Bogus"] = quote(self.xb.get_x_bogus(
+            params["X-Bogus"] = self.xb.get_x_bogus(
                 params, number, self.headers.get(
-                    "User-Agent", USERAGENT)), safe="", )
+                    "User-Agent", USERAGENT))

src/link/extractor.py

@@ -117,7 +117,7 @@ def extract_info(pattern, urls: str, index=1) -> list[str]:
 
 class ExtractorTikTok(Extractor):
     SEC_UID = compile(r'"secUid":"([a-zA-Z0-9_-]+)"')
-    ROOD_ID = compile(r'room_id=(\d+)"')
+    ROOD_ID = compile(r'"roomId":"(\d+)"')
     MIX_ID = compile(r'"playlistId":"(\d{19})"')
 
     account_link = compile(r"\S*?(https://www\.tiktok\.com/@[^\s/]+)\S*?")