podflow 20250127__py3-none-any.whl → 20250130__py3-none-any.whl

Podflow/download/dl_aideo_video.py

@@ -35,7 +35,7 @@ def download_video(
             pass
 
         def error(self, msg):
-            msg = fail_message_initialize(msg, video_url)
+            msg = fail_message_initialize(msg, video_url).ljust(45)
             print(msg)
 
     outtmpl = f"channel_audiovisual/{output_dir}/{video_url}{sesuffix}.{output_format}"
@@ -68,15 +68,16 @@ def download_video(
             ydl.download([f"{video_website}"])  # 下载指定视频链接的视频
         return None, None
     except Exception as download_video_error:
-        fail_info = fail_message_initialize(download_video_error, video_url)
+        fail_info = fail_message_initialize(download_video_error, video_url).replace("\n","")
         remove_info = ""
         if fail_info in [
+            "",
             "\033[31m请求拒绝\033[0m",
             "\033[31m数据不完整\033[0m",
             "\033[31m传输中断\033[0m",
             "\033[31m请求超时\033[0m",
             "\033[31m响应超时\033[0m",
-        ]:
+        ] and "www.youtube.com" in video_website:
             if os.path.isfile(outtmpl):
                 os.remove(outtmpl)
                 remove_info = "|已删除失败文件"

Podflow/message/media_format.py

@@ -29,10 +29,16 @@ def duration_and_formats(video_website, video_url, cookies):
             "logger": MyLogger(),
         }
         if cookies:
-            ydl_opts["http_headers"] = {
-                "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36",
-                "Referer": "https://www.bilibili.com/",
-            }
+            if "www.bilibili.com" in video_website:
+                ydl_opts["http_headers"] = {
+                    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36",
+                    "Referer": "https://www.bilibili.com/",
+                }
+            elif "www.youtube.com" in video_website:
+                ydl_opts["http_headers"] = {
+                    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36",
+                    "Referer": "https://www.youtube.com/",
+                }
             ydl_opts["cookiefile"] = cookies  # cookies 是你的 cookies 文件名
         with yt_dlp.YoutubeDL(ydl_opts) as ydl:
             # 使用提供的 URL 提取视频信息

Podflow/youtube/build.py

@@ -21,6 +21,7 @@ from Podflow.message.xml_original_item import xml_original_item
 def get_youtube_introduction():
     # 创建线程锁
     youtube_xml_get_lock = threading.Lock()
+
     # 使用http获取youtube频道简介和图标模块
     def youtube_xml_get(output_dir):
         if channel_about := http_client(
@@ -47,6 +48,7 @@ def get_youtube_introduction():
             ).group()
             with youtube_xml_get_lock:
                 gVar.youtube_xml_get_tree[output_dir] = xml_tree
+
     # 创建线程列表
     youtube_xml_get_threads = []
     for output_dir in gVar.channelid_youtube_ids_update:
@@ -67,26 +69,43 @@ def get_youtube_playlist(url, channelid_title):
             0
         ]["tabRenderer"]["content"]["sectionListRenderer"]["contents"][0][
             "itemSectionRenderer"
-        ][
-            "contents"
-        ][
-            0
-        ][
-            "playlistVideoListRenderer"
-        ][
-            "contents"
-        ]
+        ]["contents"][0]["playlistVideoListRenderer"]["contents"]
         videoids.extend(
             content["playlistVideoRenderer"]["videoId"] for content in contents
         )
     return videoids
 
 
+# 从HTML获取YouTube媒体信息模块
+def youtube_html_guid_message(guid):
+    ytInitialPlayerResponse = get_html_dict(
+        f"https://www.youtube.com/watch?v={guid}",
+        f"{guid} HTML",
+        "ytInitialPlayerResponse",
+    )
+    try:
+        image = ytInitialPlayerResponse["microformat"]["playerMicroformatRenderer"][
+            "thumbnail"
+        ]["thumbnails"][0]["url"]
+        title = ytInitialPlayerResponse["microformat"]["playerMicroformatRenderer"][
+            "title"
+        ]["simpleText"]
+        description = ytInitialPlayerResponse["microformat"][
+            "playerMicroformatRenderer"
+        ]["description"]["simpleText"]
+        published = ytInitialPlayerResponse["microformat"]["playerMicroformatRenderer"][
+            "publishDate"
+        ]
+        return published, image, title, description
+    except KeyError:
+        return None
+
+
 # 生成YouTube的item模块
 def youtube_xml_item(entry, title_change=None):
     if title_change is None:
         title_change = {}
-    # sourcery skip: avoid-builtin-shadow
+
     # 输入时间字符串和原始时区
     time_str = re.search(r"(?<=<published>).+(?=</published>)", entry).group()
     pubDate = format_time(time_str)
@@ -115,14 +134,21 @@ def get_xml_item(guid, item, channelid_title, title_change, output_dir):
     video_website = f"https://youtube.com/watch?v={guid}"
     if item["yt-dlp"]:
         guid_value = gVar.video_id_update_format[guid]
-        title = html.escape(guid_value["title"])
-        description = html.escape(re.sub(r"\n+", "\n", guid_value["description"]))
-        timestamp = guid_value["timestamp"]
-        published = datetime.fromtimestamp(timestamp, timezone.utc).strftime(
-            "%Y-%m-%dT%H:%M:%S%z"
-        )
+        if timestamp := guid_value["timestamp"]:
+            published = datetime.fromtimestamp(timestamp, timezone.utc).strftime(
+                "%Y-%m-%dT%H:%M:%S%z"
+            )
+            title = guid_value["title"]
+            description = guid_value["description"]
+            image = guid_value["image"]
+        elif guid_message := youtube_html_guid_message(guid):
+            published, image, title, description = guid_message
+        else:
+            return None
+        title = html.escape(title)
+        description = html.escape(re.sub(r"\n+", "\n", description))
+        image = re.sub(r"\?.*$", "", image)
         pubDate = format_time(published)
-        image = re.sub(r"\?.*$", "", guid_value["image"])
     else:
         title = html.escape(item["title"])
         description = html.escape(re.sub(r"\n+", "\n", item["description"]))
@@ -164,16 +190,16 @@ def youtube_xml_items(output_dir):
         for guid in output_dir_value["content"]["list"]:
             if guid not in gVar.video_id_failed:
                 item = output_dir_value["content"]["item"][guid]
-                xml_item_text = get_xml_item(
+                if xml_item_text := get_xml_item(
                     guid, item, channelid_title, title_change, output_dir
-                )
-                items_list.append(f"{xml_item_text}<!-- {output_dir} -->")
-                entry_num += 1
-                if (
-                    gVar.video_id_update_format[guid]["description"]
-                    and gVar.video_id_update_format[guid]["description"][0] == "『"
                 ):
-                    original_judgment = False
+                    items_list.append(f"{xml_item_text}<!-- {output_dir} -->")
+                    entry_num += 1
+                    if (
+                        gVar.video_id_update_format[guid]["description"]
+                        and gVar.video_id_update_format[guid]["description"][0] == "『"
+                    ):
+                        original_judgment = False
     else:
         if output_dir_value["type"] == "html":  # 获取最新的rss信息
             file_xml = output_dir_value["content"].text
@@ -217,14 +243,14 @@ def youtube_xml_items(output_dir):
         for backward_guid in backward["list"]:
             if backward_guid not in gVar.video_id_failed:
                 backward_item = backward["item"][backward_guid]
-                backward_xml_item_text = get_xml_item(
+                if backward_xml_item_text := get_xml_item(
                     backward_guid,
                     backward_item,
                     channelid_title,
                     title_change,
                     output_dir,
-                )
-                items_list.append(f"{backward_xml_item_text}<!-- {output_dir} -->")
+                ):
+                    items_list.append(f"{backward_xml_item_text}<!-- {output_dir} -->")
     # 生成对应xml
     try:
         with open(

Podflow/youtube/get.py

@@ -15,61 +15,73 @@ from Podflow.basic.list_merge_tidy import list_merge_tidy
 
 # 从YouTube播放列表获取更新模块
 def get_youtube_html_playlists(
-    youtube_key,
-    youtube_value,
-    guids=[""],
-    direction_forward=True,
-    update_size=20,
-    youtube_content_ytid_original=[],
+    youtube_key,  # YouTube 频道的唯一标识
+    youtube_value,  # YouTube 账户或其他标识信息
+    guids=None,  # 视频 ID 列表（用于比较已有视频）
+    direction_forward=True,  # 控制获取方向，默认向前获取新的视频
+    update_size=20,  # 更新数量限制，最多获取 20 个新视频
+    youtube_content_ytid_original=None,  # 原始 YouTube 视频 ID 列表
 ):
-    idlist = []
-    item = {}
-    threads = []
-    fail = []
+    idlist = []  # 存储新获取的 YouTube 视频 ID
+    item = {}  # 存储视频信息（标题、描述、封面等）
+    threads = []  # 线程列表，用于并发获取视频详细信息
+    fail = []  # 存储获取失败的视频 ID
+
+    if guids is None:
+        guids = [""]
+    if youtube_content_ytid_original is None:
+        youtube_content_ytid_original = []
+
     try:
-        videoid_start = guids[0] if direction_forward else guids[-1]
+        videoid_start = guids[0] if direction_forward else guids[-1]  # 获取起始视频 ID
     except IndexError:
-        videoid_start = ""
+        videoid_start = ""  # 处理空列表情况，避免 IndexError
 
-    # 获取媒体相关信息模块
+    # 获取视频详细信息的内部函数
     def get_video_item(videoid, youtube_value):
         yt_Initial_Player_Response = get_html_dict(
             f"https://www.youtube.com/watch?v={videoid}",
             f"{youtube_value}|{videoid}",
             "ytInitialPlayerResponse",
-        )
+        )  # 解析 YouTube 页面，获取视频信息
         if not yt_Initial_Player_Response:
-            return None
+            return None  # 若获取失败，则返回 None
+
         try:
             player_Microformat_Renderer = yt_Initial_Player_Response["microformat"][
                 "playerMicroformatRenderer"
             ]
         except (KeyError, TypeError, IndexError, ValueError):
-            player_Microformat_Renderer = {}
-            fail.append(videoid)
+            player_Microformat_Renderer = {}  # 解析失败时，返回空字典
+            fail.append(videoid)  # 记录失败的视频 ID
+
         if player_Microformat_Renderer:
             try:
                 item[videoid]["description"] = player_Microformat_Renderer[
                     "description"
                 ]["simpleText"]
             except (KeyError, TypeError, IndexError, ValueError):
-                item[videoid]["description"] = ""
-            item[videoid]["pubDate"] = player_Microformat_Renderer["publishDate"]
+                item[videoid]["description"] = ""  # 若没有描述，则置为空
+            item[videoid]["pubDate"] = player_Microformat_Renderer[
+                "publishDate"
+            ]  # 获取发布时间
             item[videoid]["image"] = player_Microformat_Renderer["thumbnail"][
                 "thumbnails"
-            ][0]["url"]
+            ][0]["url"]  # 获取封面图
             with contextlib.suppress(KeyError, TypeError, IndexError, ValueError):
-                fail.remove(videoid)
+                fail.remove(videoid)  # 若成功获取，则从失败列表中移除
         else:
-            return None
+            return None  # 若无有效数据，返回 None
 
+    # 获取播放列表数据
     yt_initial_data = get_html_dict(
-        f"https://www.youtube.com/watch?v={videoid_start}&list=UULF{youtube_key[-22:]}",
+        f"https://www.youtube.com/watch?v={videoid_start}&list=UU{youtube_key[-22:]}",
         f"{youtube_value} HTML",
         "ytInitialData",
-    )
+    )  # 解析 YouTube 播放列表页面，获取数据
     if not yt_initial_data:
-        return None
+        return None  # 若获取失败，则返回 None
+
     try:
         playlists = yt_initial_data["contents"]["twoColumnWatchNextResults"][
             "playlist"
@@ -78,74 +90,70 @@ def get_youtube_html_playlists(
             "playlist"
         ]["playlist"]["ownerName"]["simpleText"]
     except (KeyError, TypeError, IndexError, ValueError):
-        return None
+        return None  # 若解析失败，返回 None
+
+    # 若方向是向前获取（最新视频）或没有起始视频 ID
     if direction_forward or not videoid_start:
         for playlist in playlists:
-            videoid = playlist["playlistPanelVideoRenderer"]["videoId"]
+            videoid = playlist["playlistPanelVideoRenderer"]["videoId"]  # 提取视频 ID
             if (
                 playlist["playlistPanelVideoRenderer"]["navigationEndpoint"][
                     "watchEndpoint"
                 ]["index"]
                 == update_size
             ):
-                break
-            if videoid not in guids:
-                title = playlist["playlistPanelVideoRenderer"]["title"]["simpleText"]
-                idlist.append(videoid)
-                item[videoid] = {
-                    "title": title,
-                    "yt-dlp": True,
-                }
-                if videoid in youtube_content_ytid_original:
-                    item[videoid]["yt-dlp"] = False
+                break  # 如果达到更新上限，则停止
+            if videoid not in guids:  # 确保视频 ID 不是已存在的
+                title = playlist["playlistPanelVideoRenderer"]["title"][
+                    "simpleText"
+                ]  # 获取视频标题
+                idlist.append(videoid)  # 添加到 ID 列表
+                item[videoid] = {"title": title, "yt-dlp": True}  # 记录视频信息
+                if videoid in youtube_content_ytid_original:  # 若视频已在原始列表中
+                    item[videoid]["yt-dlp"] = False  # 标记为已存在
                     item_thread = threading.Thread(
-                        target=get_video_item,
-                        args=(
-                            videoid,
-                            youtube_value,
-                        ),
-                    )
+                        target=get_video_item, args=(videoid, youtube_value)
+                    )  # 启动线程获取详细信息
                     item_thread.start()
                     threads.append(item_thread)
-    else:
+    else:  # 处理向后获取（获取较旧的视频）
         reversed_playlists = []
         for playlist in reversed(playlists):
             videoid = playlist["playlistPanelVideoRenderer"]["videoId"]
             if videoid not in guids:
-                reversed_playlists.append(playlist)
+                reversed_playlists.append(playlist)  # 收集未存在的旧视频
             else:
-                break
+                break  # 如果找到已存在的视频 ID，则停止
+
         for playlist in reversed(reversed_playlists[-update_size:]):
             videoid = playlist["playlistPanelVideoRenderer"]["videoId"]
             title = playlist["playlistPanelVideoRenderer"]["title"]["simpleText"]
             idlist.append(videoid)
-            item[videoid] = {
-                "title": title,
-                "yt-dlp": True,
-            }
+            item[videoid] = {"title": title, "yt-dlp": True}
             if videoid in youtube_content_ytid_original:
                 item[videoid]["yt-dlp"] = False
                 item_thread = threading.Thread(
-                    target=get_video_item,
-                    args=(
-                        videoid,
-                        youtube_value,
-                    ),
+                    target=get_video_item, args=(videoid, youtube_value)
                 )
                 item_thread.start()
                 threads.append(item_thread)
+
     for thread in threads:
-        thread.join()
+        thread.join()  # 等待所有线程完成
+
+    # 处理获取失败的视频
     for videoid in fail:
-        get_video_item(videoid, youtube_value)
-    if fail:
+        get_video_item(videoid, youtube_value)  # 重新尝试获取失败的视频
+
+    if fail:  # 如果仍然有失败的视频
         if direction_forward or not videoid_start:
             for videoid in fail:
                 print(
                     f"{datetime.now().strftime('%H:%M:%S')}|{youtube_value}|{videoid} HTML无法更新, 将不获取"
                 )
-                idlist.remove(videoid)
-                del item[videoid]
+                if videoid in idlist:
+                    idlist.remove(videoid)  # 安全地移除视频 ID，避免 `ValueError`
+                del item[videoid]  # 删除对应的字典项
         else:
             print(
                 f"{datetime.now().strftime('%H:%M:%S')}|{youtube_value} HTML有失败只更新部分"
@@ -153,12 +161,14 @@ def get_youtube_html_playlists(
             index = len(idlist)
             for videoid in fail:
                 if videoid in idlist:
-                    index = min(idlist.index(videoid), index)
-            idlist_fail = idlist[index:]
-            idlist = idlist[:index]
+                    index = min(idlist.index(videoid), index)  # 计算最早失败视频的索引
+            idlist_fail = idlist[index:]  # 截取失败的视频 ID 列表
+            idlist = idlist[:index]  # 只保留成功的视频 ID
             for videoid in idlist_fail:
-                idlist.remove(videoid)
-    return {"list": idlist, "item": item, "title": main_title}
+                if videoid in idlist:
+                    idlist.remove(videoid)  # 安全删除失败视频 ID
+
+    return {"list": idlist, "item": item, "title": main_title}  # 返回最终结果
 
 
 def get_youtube_shorts_id(youtube_key, youtube_value):

{podflow-20250127.dist-info → podflow-20250130.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: podflow
-Version: 20250127
+Version: 20250130
 Summary: A podcast server that includes YouTube and BiliBili
 Home-page: https://github.com/gruel-zxz/podflow
 Author: gruel_zxz
@@ -15,7 +15,7 @@ Description-Content-Type: text/markdown
 Requires-Dist: astral>=3.2
 Requires-Dist: bottle>=0.13.2
 Requires-Dist: qrcode>=8.0
-Requires-Dist: yt-dlp>=2025.1.15
+Requires-Dist: yt-dlp>=2025.1.26
 Requires-Dist: chardet>=5.2.0
 Requires-Dist: cherrypy>=18.10.0
 Requires-Dist: requests>=2.32.3

{podflow-20250127.dist-info → podflow-20250130.dist-info}/RECORD

@@ -31,7 +31,7 @@ Podflow/config/get_config.py,sha256=xM_C1Vk5EUAdPKwR7guPSo2IVR_QOZ-EFHfbmtMtm30,
 Podflow/download/__init__.py,sha256=1TgjbOdcnnPTBMXpzqaazcN50EUomBW0zHN0wXAa3cM,47
 Podflow/download/convert_bytes.py,sha256=33Fgeyt-yEmysFZaj23tGtjUkUtHuKZohRKR4TxOxyg,543
 Podflow/download/delete_part.py,sha256=G9lK8G8tOOmnEBmAHJKPdqPeLhJ61S5m8o6iL5g9SyE,679
-Podflow/download/dl_aideo_video.py,sha256=6PpzQF1sdGU24ruq0g3olLAWM_nVyPQ2dFp05wvJCUA,9916
+Podflow/download/dl_aideo_video.py,sha256=DDB03WfBzqHW9NOozGN6gj4BwG4jyiW79-_fbfVBX9c,9998
 Podflow/download/show_progress.py,sha256=7oGzhj_frO2A1o5JeGuHn7bHtma5oPpD_IWcctIO2rs,1595
 Podflow/download/wait_animation.py,sha256=E2V3cm-10e5Iif40oU722OfzDe7YiLMbDqsjZ6dshBE,1056
 Podflow/download/youtube_and_bilibili_download.py,sha256=jt6CWb8ZJ-dyIom7fJ_K1qve9pSzoW0hNwfWnZiju7w,1228
@@ -53,7 +53,7 @@ Podflow/message/get_original_rss.py,sha256=CK_Q5enOzUafgL2l5OlXBpC08Nj_B7AKPzw5D
 Podflow/message/get_video_format.py,sha256=RIX0fxuPYkoQPRWt-ulJPhfEWtMkyxwOEVqcuRsp4v8,4770
 Podflow/message/get_video_format_multithread.py,sha256=ZXzY9RwT59eOvP6Lmx-I07P3C1CWCl-4l_uw_pkozqE,1406
 Podflow/message/get_youtube_and_bilibili_video_format.py,sha256=RuaxL3JwZs3_Bqm77g9SIcyV8o-WJu_qOCWhEnD15WE,4321
-Podflow/message/media_format.py,sha256=zCiUixdk5ZvZz9J0OS3BFw8sHPgR3Jdb1tu7aLLg9uU,6948
+Podflow/message/media_format.py,sha256=WH0NnjWPLigU8Wy2kbqDIhj_RISnaCCXtsR5qIjLFdU,7346
 Podflow/message/original_rss_fail_print.py,sha256=pVVb_BGM1HofHDh9pCX5GS03gOnNAssfHDjj5Ytz_mw,502
 Podflow/message/rss_create_hash.py,sha256=NODhtprDPkpiuiezupARKm5Xr4Zt2Io_lcxmHedPAQc,638
 Podflow/message/title_correction.py,sha256=JR2q3PubOUUAfQEPjIzeRzUe4Jy86opGIO1st51qt2g,915
@@ -70,11 +70,11 @@ Podflow/remove/__init__.py,sha256=kns-jfTXH8lXh9OQ5E5-llsrAPlET5rl6RYpjoZKav8,45
 Podflow/remove/remove_dir.py,sha256=tah3LCD0bCcf5dDg3NrHuseaje3-31C5NLNupMg15TU,1099
 Podflow/remove/remove_file.py,sha256=R8Gr0d6bIAYKQ7YEfFl5_QJ_CcumTu_8XejP7xuRm2k,981
 Podflow/youtube/__init__.py,sha256=-bdMyuw-wxoz2miVkp284amS4Qg0k7VN0JPuGF-cXlM,46
-Podflow/youtube/build.py,sha256=PnRr_nI_DIMDF0IPZUIuO8mJBB57FS-VZNTYHVzRQKI,10143
-Podflow/youtube/get.py,sha256=Frk7NMAUpqyeoCHBplTu6P3C9lHXyMmnyUg3XxSuUnw,15171
+Podflow/youtube/build.py,sha256=y1R5KI_R8ydYjjxZKvMtNaHUiyMm4iBa-MIEMbA92FY,11210
+Podflow/youtube/get.py,sha256=dFLyiHttygqdJltwC29jD_v8wwoLynE5NUdow_0wERI,16970
 Podflow/youtube/login.py,sha256=DlS_ZG4g6CKWqS5ojE4UwFJSCSZDsXbeuDVgHtQAa4A,1380
-podflow-20250127.dist-info/METADATA,sha256=rVgZbUHkV4olDbi-mvMDHtiPl8tYTaw5yXppBNqDJuk,13801
-podflow-20250127.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-podflow-20250127.dist-info/entry_points.txt,sha256=44nj8jJB7bo1JLNrKQZmwMGEA1OalrALJ0tF_G0yXLY,131
-podflow-20250127.dist-info/top_level.txt,sha256=KcvRCiz_DRWWc9i-PgpARvFB0J4CKmpZOZgPqOdG-Lk,8
-podflow-20250127.dist-info/RECORD,,
+podflow-20250130.dist-info/METADATA,sha256=iGZO9mepzFymSkKGPRHulbz4avh3uzGaqXijdh6vUbo,13801
+podflow-20250130.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+podflow-20250130.dist-info/entry_points.txt,sha256=44nj8jJB7bo1JLNrKQZmwMGEA1OalrALJ0tF_G0yXLY,131
+podflow-20250130.dist-info/top_level.txt,sha256=KcvRCiz_DRWWc9i-PgpARvFB0J4CKmpZOZgPqOdG-Lk,8
+podflow-20250130.dist-info/RECORD,,