Add SingleFile support for saving transcript whole local

README.md

@@ -10,7 +10,7 @@
 ### 安装
 
 ```
-pip3 install -r requirements.txt
+pip3 install .
 ```
 
 ### 运行
@@ -19,7 +19,7 @@ pip3 install -r requirements.txt
 
 执行以下命令运行：
 ```
-python3 vistopia/main.py --token [token] [subcommand]
+python3 -m vistopia.main --token [token] [subcommand]
 ```
 
 子命令目前支持：
@@ -29,6 +29,19 @@ python3 vistopia/main.py --token [token] [subcommand]
 - `save-show`: 保存节目至本地，并添加封面和 ID3 信息
 - `save-transcript`: 保存节目文稿至本地
 
+### 使用 SingleFile 将文稿网页保存为纯本地文件
+
+1. 下载 [SingleFile CLI](https://github.com/gildas-lormeau/single-file-cli/releases) 命令行程序
+2. 浏览器登陆网页版看理想，使用 cookie 导出工具（如：EditThisCookie）导出 json 格式的 cookies，并保存为本地文件
+3. 运行 `save-transcript` 命令，并传入 `--single-file-exec-path` 和 `--cookie-file-path` 参数
+
+命令格式：
+```
+python3 -m vistopia.main --token [token] save-transcript --id [id] \
+--single-file-exec-path=/path/to/local/single-file \
+--cookie-file-path=/path/to/vistopia.cookie
+```
+
 ## 不足
 
 目前不支持 API 签名。

vistopia/main.py

@@ -1,6 +1,7 @@
 import json
 import logging
 from logging import getLogger
+from typing import Optional
 
 import click
 from tabulate import tabulate
@@ -14,8 +15,8 @@
 
 class Context:
     def __init__(self):
-        self.token: str = None
-        self.visitor: Visitor = None
+        self.token: Optional[str] = None
+        self.visitor: Optional[Visitor] = None
 
 
 # def _print_table(list):
@@ -115,7 +116,7 @@ def show_content(ctx, **argv):
 def save_show(ctx, **argv):
     content_id = argv.pop("id")
     episode_id = argv.pop("episode_id", None)
-    episodes = set(range_expand(episode_id) if episode_id else None)
+    episodes = set(range_expand(episode_id) if episode_id else [])
 
     logger.debug(json.dumps(
         ctx.obj.visitor.get_catalog(content_id), indent=2, ensure_ascii=False))
@@ -130,19 +131,35 @@ def save_show(ctx, **argv):
 @main.command("save-transcript")
 @click.option("--id", type=click.INT, required=True)
 @click.option("--episode-id", help="Episode ID in the form '1-3,4,8'")
+@click.option("--single-file-exec-path", type=click.Path(),
+              help="Path to the single-file CLI tool")
+@click.option("--cookie-file-path", type=click.Path(),
+              help=(
+                  "Path to the browser cookie file "
+                  "(only needed in single-file mode)"))
 @click.pass_context
 def save_transcript(ctx, **argv):
     content_id = argv.pop("id")
     episode_id = argv.pop("episode_id", None)
-    episodes = set(range_expand(episode_id) if episode_id else None)
+    single_file_exec_path = argv.pop("single_file_exec_path")
+    cookie_file_path = argv.pop("cookie_file_path")
+    episodes = set(range_expand(episode_id) if episode_id else [])
 
     logger.debug(json.dumps(
         ctx.obj.visitor.get_catalog(content_id), indent=2, ensure_ascii=False))
 
-    ctx.obj.visitor.save_transcript(
-        content_id,
-        episodes=episodes
-    )
+    if single_file_exec_path and cookie_file_path:
+        ctx.obj.visitor.save_transcript_with_single_file(
+            content_id,
+            episodes=episodes,
+            single_file_exec_path=single_file_exec_path,
+            cookie_file_path=cookie_file_path
+        )
+    else:
+        ctx.obj.visitor.save_transcript(
+            content_id,
+            episodes=episodes
+        )
 
 
 if __name__ == "__main__":

vistopia/visitor.py

@@ -69,8 +69,8 @@ def save_show(self, id: int,
         for part in catalog["catalog"]:
             for article in part["part"]:
 
-                if episodes is not None and \
-                      int(article["sort_number"]) not in episodes:
+                if episodes and \
+                        int(article["sort_number"]) not in episodes:
                     continue
 
                 fname = show_dir / "{}.mp3".format(article["title"])
@@ -95,8 +95,8 @@ def save_transcript(self, id: int, episodes: Optional[set] = None):
         for part in catalog["catalog"]:
             for article in part["part"]:
 
-                if episodes is not None and \
-                      int(article["sort_number"]) not in episodes:
+                if episodes and \
+                        int(article["sort_number"]) not in episodes:
                     continue
 
                 fname = show_dir / "{}.html".format(article["title"])
@@ -114,19 +114,62 @@ def save_transcript(self, id: int, episodes: Optional[set] = None):
                     with open(fname, "w") as f:
                         f.write(content)
 
+    def save_transcript_with_single_file(self, id: int,
+                                         episodes: Optional[set] = None,
+                                         single_file_exec_path: str = "",
+                                         cookie_file_path: str = ""):
+        import subprocess
+        from pathlib import Path
+        logger.debug(f"save_transcript_with_single_file id {id}")
+
+        catalog = self.get_catalog(id)
+        show_dir = Path(catalog["title"])
+        show_dir.mkdir(exist_ok=True)
+
+        for part in catalog["catalog"]:
+            for article in part["part"]:
+                if episodes and int(article["sort_number"]) not in episodes:
+                    continue
+
+                fname = show_dir / "{}.html".format(article["title"])
+                if not fname.exists():
+                    command = [
+                        single_file_exec_path,
+                        "https://www.vistopia.com.cn/article/"
+                        + article["article_id"],
+                        str(fname),
+                        "--browser-cookies-file=" + cookie_file_path
+                    ]
+                    logger.debug(f"singlefile command {command}")
+                    try:
+                        subprocess.run(command, check=True)
+                        print(
+                            f"Successfully fetched and saved to {fname}")
+                    except subprocess.CalledProcessError as e:
+                        print(f"Failed to fetch page using single-file: {e}")
+
     @staticmethod
     def retag(fname, article_info, catalog_info, series_info):
 
         from mutagen.easyid3 import EasyID3
-
-        track = EasyID3(fname)
-        track["title"] = article_info["title"]
-        track["album"] = series_info["title"]
-        track["artist"] = series_info["author"]
-        track["tracknumber"] = article_info["sort_number"]
-        # track["tracksort"] = article_info["sort_number"]
-        track["website"] = article_info["content_url"]
-        track.save()
+        from mutagen.id3 import ID3NoHeaderError
+
+        try:
+            track = EasyID3(fname)
+        except ID3NoHeaderError:
+            # No ID3 tag found, creating a new ID3 tag
+            track = EasyID3()
+
+        track['title'] = article_info['title']
+        track['album'] = series_info['title']
+        track['artist'] = series_info['author']
+        track['tracknumber'] = str(article_info['sort_number'])
+        track['website'] = article_info['content_url']
+
+        try:
+            track.save(fname)
+        except Exception as e:
+            print(f"Error saving ID3 tags: {e}")
 
     @staticmethod
     def retag_cover(fname, article_info, catalog_info, series_info):