podflow 20250205__py3-none-any.whl → 20250212__py3-none-any.whl

Podflow/__init__.py

@@ -19,6 +19,7 @@ default_config = {
     "token": "",  # token认证, 如为null或""将不启用token
     "delete_incompletement": False,  # 是否删除下载中断媒体(下载前处理流程)
     "remove_media": True,  # 是否删除无用的媒体文件
+    "upload": False,  # 是否将长期媒体进行上传
     "channelid_youtube": {  # Youtube频道列表
         "youtube": {
             "update_size": 15,  # 每次获取频道媒体数量
@@ -100,9 +101,7 @@ class Application_gVar:
         self.channelid_bilibili_ids_update = {}  # 需更新的哔哩哔哩频道字典
         self.bilibili_content_bvid_update = {}  # 需下载哔哩哔哩视频字典
         self.channelid_bilibili_rss = {}  # 哔哩哔哩频道最新Rss Response字典
-        self.bilibili_content_bvid_backward_update = (
-            {}
-        )  # 向后更新需下载哔哩哔哩视频字典
+        self.bilibili_content_bvid_backward_update = {}  # 向后更新需下载哔哩哔哩视频字典
         self.video_id_failed = []  # YouTube&哔哩哔哩视频下载失败列表
         self.video_id_update_format = {}  # YouTube和哔哩哔哩视频下载的详细信息字典
         self.hash_rss_original = ""  # 原始rss哈希值文本
@@ -115,6 +114,8 @@ class Application_gVar:
         self.overall_rss = ""  # 更新后的rss文本
         self.make_up_file_format = {}  # 补全缺失媒体字典
         self.make_up_file_format_fail = {}  # 补全缺失媒体失败字典
+        
+        self.upload_original = {}  # 原始上传信息字典
 
         self.shortcuts_url = {}  # 输出至shortcut的url字典
 

Podflow/bilibili/build.py

@@ -144,9 +144,9 @@ def bilibili_xml_items(output_dir):
             )
             if item["description"] and item["description"][0] == "『":
                 original_judgment = False
-            entry_num += 1
-            if entry_num >= channelid_bilibili_value["update_size"]:
-                break
+        entry_num += 1
+        if entry_num >= channelid_bilibili_value["update_size"]:
+            break
     items_guid = re.findall(r"(?<=<guid>).+?(?=</guid>)", "".join(items_list))
     # 存量接入
     entry_count = channelid_bilibili_value["last_size"] - len(items_guid)

Podflow/config/build_original.py

@@ -6,8 +6,8 @@ from Podflow.config.get_config import get_config
 from Podflow.basic.folder_build import folder_build
 from Podflow.config.get_channelid import get_channelid
 from Podflow.config.correct_config import correct_config
-from Podflow.config.correct_channelid import correct_channelid
 from Podflow.config.get_channelid_id import get_channelid_id
+from Podflow.config.correct_channelid import correct_channelid
 
 
 def build_original():

Podflow/config/correct_config.py

@@ -101,3 +101,8 @@ def correct_config():
         config["remove_media"], bool
     ):
         config["remove_media"] = default_config["remove_media"]
+    # 对upload进行纠正
+    if "upload" not in config or not isinstance(
+        config["upload"], bool
+    ):
+        config["upload"] = default_config["upload"]

Podflow/main.py

@@ -58,12 +58,17 @@ from Podflow.remove.remove_dir import remove_dir
 # 处理 YouTube 信息模块
 from Podflow.youtube.build import get_youtube_introduction
 
+# 长期媒体进行上传模块
+from Podflow.upload.get_upload_original import get_upload_original
+
 
 def main():
     # 获取传入的参数
     parse_arguments()
     # 开始运行
-    print(f"{datetime.now().strftime('%H:%M:%S')}|Podflow|{version('Podflow')}开始运行.....")
+    print(
+        f"{datetime.now().strftime('%H:%M:%S')}|Podflow|{version('Podflow')}开始运行....."
+    )
     # 判断是否安装ffmpeg
     ffmpeg_judge()
     # 初始化
@@ -116,6 +121,12 @@ def main():
         gVar.xmls_original, gVar.hash_rss_original, gVar.xmls_original_fail = (
             get_original_rss()
         )
+        # 初始化原始上传信息
+        if gVar.config["upload"]:
+            if upload_original := get_upload_original():
+                gVar.upload_original = upload_original
+            else:
+                gVar.config["upload"] = False
         # 更新Youtube和哔哩哔哩频道xml
         update_youtube_bilibili_rss()
         # 判断是否有更新内容

Podflow/message/fail_message_initialize.py

@@ -135,7 +135,7 @@ error_reason = [
         "text",
     ],
     [
-        r"Got error: HTTPSConnectionPool\(host='rr[0-9]---sn-.{8}\.googlevideo.com', port=443\): Read timed out\.",
+        r"Got error: HTTPSConnectionPool\(host='rr[0-9]---sn-.{8}\.googlevideo.com', port=443\): Read timed out\. \(read timeout=20\.0\)",
         "\033[31m响应超时\033[0m",
         "regexp",
     ],
@@ -144,6 +144,8 @@ error_reason = [
 
 # 失败信息初始化模块
 def fail_message_initialize(message_error, video_url):
+    if video_url[:2] == "BV":
+        video_url = video_url[:12]
     fail_message = (
         str(message_error)
         .replace("ERROR: ", "")

Podflow/message/get_original_rss.py

@@ -48,7 +48,9 @@ def get_original_rss():
         get_xmls_original = {}
         rss_original = ""
     # 如原始xml无对应的原频道items, 将尝试从对应频道的xml中获取
-    for channelid_key in (gVar.channelid_youtube_ids | gVar.channelid_bilibili_ids).keys():
+    for channelid_key in (
+        gVar.channelid_youtube_ids | gVar.channelid_bilibili_ids
+    ).keys():
         if channelid_key not in get_xmls_original.keys():
             try:
                 with open(

Podflow/upload/__init__.py

@@ -0,0 +1,2 @@
+# Podflow/upload/__init__.py
+# coding: utf-8

Podflow/upload/get_upload_original.py

@@ -0,0 +1,105 @@
+# Podflow/upload/get_upload_original.py
+# coding: utf-8
+
+import re
+import json
+from collections import Counter
+from email.utils import parsedate_tz, mktime_tz
+from Podflow import gVar
+from Podflow.basic.file_save import file_save
+from Podflow.basic.write_log import write_log
+
+
+# 获取原始上传数据模块
+def get_upload_original():
+    xmls_original = gVar.xmls_original
+    try:
+        # 尝试打开并读取 JSON 文件
+        with open("channel_data/upload.json", "r") as file:
+            upload_original = file.read()  # 读取原始上传数据
+        upload_original = json.loads(
+            upload_original
+        )  # 将读取的字符串转换为 Python 对象（列表或字典）
+    except Exception:
+        # 如果读取或解析失败，将 upload_original 初始化为空列表
+        upload_original = []
+
+    # 如果 upload_original 不为空
+    if upload_original:
+        # 提取每个条目的 channel_id
+        channel_ids = [item.get("channel_id") for item in upload_original]
+
+        # 统计每个 channel_id 的出现次数
+        channelid_counts = Counter(channel_ids)
+
+        # 将出现次数转换为字典
+        age_counts = dict(channelid_counts)
+
+        # 统计 xmls_original 中每个键对应的 <guid> 标签内的元素数量
+        xmls_original_counts = {
+            key: len(re.findall(r"(?<=<guid>).+(?=</guid>)", value))
+            for key, value in xmls_original.items()
+        }
+
+        # 如果两个计数字典不相等，清空 upload_original
+        if age_counts != xmls_original_counts:
+            upload_original = []
+
+    # 如果 upload_original 仍然为空
+    if not upload_original:
+        # 遍历 xmls_original 的每个键值对
+        for xmls_original_key, xmls_original_value in xmls_original.items():
+            # 如果当前键在 channelid_youtube_ids 中
+            if xmls_original_key in gVar.channelid_youtube_ids:
+                # 使用正则表达式解析包含特定格式媒体ID的字符串
+                media = re.findall(
+                    r"(?:/UC.{22}/)(.{11}\.m4a|.{11}\.mp4)(?=\"|\?)",
+                    xmls_original_value,
+                )
+            # 如果当前键在 channelid_bilibili_ids 中
+            elif xmls_original_key in gVar.channelid_bilibili_ids:
+                media = re.findall(
+                    r"(?:/[0-9]+/)(BV.{10}\.m4a|BV.{10}\.mp4|BV.{10}_p[0-9]+\.m4a|BV.{10}_p[0-9]+\.mp4|BV.{10}_[0-9]{9}\.m4a|BV.{10}_[0-9]{9}\.mp4)(?=\"|\?)",
+                    xmls_original_value,
+                )
+            else:
+                media = []
+
+            # 查找每个上传条目的发布时间
+            upload_time = re.findall(
+                r"(?<=<pubDate>).+(?=</pubDate>)",
+                xmls_original_value,
+            )
+
+            # 将日期字符串列表转换为 Unix 时间戳列表
+            timestamps = [
+                mktime_tz(
+                    parsedate_tz(date_string)
+                )  # 解析和转换每个日期字符串为 Unix 时间戳
+                for date_string in upload_time
+                if parsedate_tz(date_string)  # 确保解析成功
+            ]
+
+            # 如果媒体和时间戳的数量不匹配，记录错误并清空 upload_original
+            if len(media) != len(timestamps):
+                write_log("获取原始上传内容失败")  # 错误日志
+                upload_original.clear()  # 清空 upload_original
+                break  # 退出循环
+
+            # 如果数量匹配，则整合 media_id、channel_id 和上传时间到 upload_original 列表
+            upload_original += [
+                {
+                    "media_id": key,
+                    "channel_id": xmls_original_key,
+                    "media_time": value,
+                    "upload": False,
+                }
+                for value, key in zip(
+                    timestamps, media
+                )  # 使用 zip() 将 media 和 timestamps 组合成对
+            ]
+
+        # 如果成功填充 upload_original
+        if upload_original:
+            file_save(upload_original, "upload.json", "channel_data")  # 保存到文件
+    return upload_original

Podflow/youtube/build.py

@@ -194,7 +194,6 @@ def youtube_xml_items(output_dir):
                     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] == "『"
@@ -214,9 +213,9 @@ def youtube_xml_items(output_dir):
                 items_list.append(
                     f"{youtube_xml_item(entry, title_change)}<!-- {output_dir} -->"
                 )
-                entry_num += 1
                 if re.search(r"(?<=<media:description>)『", entry):
                     original_judgment = False
+            entry_num += 1
             if entry_num >= update_size:
                 break
     items_guid = re.findall(r"(?<=<guid>).+?(?=</guid>)", "".join(items_list))

{podflow-20250205.dist-info → podflow-20250212.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: podflow
-Version: 20250205
+Version: 20250212
 Summary: A podcast server that includes YouTube and BiliBili
 Home-page: https://github.com/gruel-zxz/podflow
 Author: gruel_zxz
@@ -21,7 +21,7 @@ Requires-Dist: cherrypy>=18.10.0
 Requires-Dist: requests>=2.32.3
 Requires-Dist: pycryptodome>=3.21.0
 Requires-Dist: ffmpeg-python>=0.2.0
-Requires-Dist: BeautifulSoup4>=4.12.3
+Requires-Dist: BeautifulSoup4>=4.13.3
 
 # Podflow
 

{podflow-20250205.dist-info → podflow-20250212.dist-info}/RECORD

@@ -1,6 +1,6 @@
-Podflow/__init__.py,sha256=fkPG1o_2qAA_qeUgBPs9FPWc5-7p8WuQ-h2FqrgsZS4,6803
+Podflow/__init__.py,sha256=lXlJ6btdmA-rtsJH7fH4gvaRobCe5woXRuD5PCtXMRM,6908
 Podflow/ffmpeg_judge.py,sha256=krttVs1PDot_0CDq5rmtUIpchiaiqtAkPYFQRLG6OQM,1275
-Podflow/main.py,sha256=wIpxvDoC62Feeig43GU8VmJ557MFJ1tsLAwP3llHdJo,9757
+Podflow/main.py,sha256=k_rb5ssdHZIqkdb7GCPtsGALPQnM_gpGpxGtF3uDJsM,10120
 Podflow/parse_arguments.py,sha256=qa5228sralPV7s4JdB6UgS1ug66rBqckDvSOwjz2tIc,2171
 Podflow/basic/__init__.py,sha256=SyFA_F_0-zn1VejCL83IPeZx1k2HCiqNY-0l0bp1N88,44
 Podflow/basic/file_save.py,sha256=mstWM6njYtCpq2sa28JD_neClvVLcjJOrGlCXBjUnZs,696
@@ -17,14 +17,14 @@ Podflow/basic/time_stamp.py,sha256=vf0p6FIK2-ZN2p2sotbpf4dewQMy-Vior-aREYfT0Zc,1
 Podflow/basic/vary_replace.py,sha256=aecFDuAOvQjTpgtoSW5uDu8Tx_YTs4bCFF9imVFkfVY,211
 Podflow/basic/write_log.py,sha256=Sm6qzTSb1x6X2uQnnmVD4dU6BsY1PONxenwsWAdFxso,1358
 Podflow/bilibili/__init__.py,sha256=ekvpCzR4bg6ar73Gq0YWQcPXND4TEqP46pb9iLyke9g,47
-Podflow/bilibili/build.py,sha256=G-MhhURoTRmGNJGRySltraFsslIEDtJxhL93_DnqlfY,7948
+Podflow/bilibili/build.py,sha256=Z62hEUDT0YB_NNR9rDpmvvOYrSOBR644Kvkdc05FGU0,7936
 Podflow/bilibili/get.py,sha256=PXPh_H8B_zP9dhqe6sA_QCeJcdnriBCpbF7mPq46xMw,20337
 Podflow/bilibili/login.py,sha256=aYKEj5re-JYXnA0aCOKUF9Cqwwd7FTOuAu_yvcaqdag,10944
 Podflow/config/__init__.py,sha256=BroaS1uvdLb00OQeJXc1i7QeuErD-U-2QjynQH5IDdE,45
-Podflow/config/build_original.py,sha256=wfHpze2Z-0IjKMqkA5nBz5gwM8zPnnMx7wtl4owYKAs,1809
+Podflow/config/build_original.py,sha256=tZtsGUi1rG6DH6cxaiaVQPRtIl6U0-FqOdeho7CXl0s,1809
 Podflow/config/channge_icon.py,sha256=z2tFFiP7aZFiMP1RqXkrovWAxBOI77rTHKhuzzhFfn0,5653
 Podflow/config/correct_channelid.py,sha256=o88DH1RJVloeXHI2ZKP7vb-3VUqM2yQaaUWRq3V_rfg,9252
-Podflow/config/correct_config.py,sha256=DCN2TuuEmzwBYYMdFrI_uhaE_2Vs7eUj2J-fSA9MFiE,3791
+Podflow/config/correct_config.py,sha256=faER2s7jBB7siX0b5XNoMgjnR88CddQK2Yl53xVdQSI,3958
 Podflow/config/get_channelid.py,sha256=3Eeh_GN1qUJGhNl5uVDUZHZpcY-fa16BtfwWpJ4Yyjg,641
 Podflow/config/get_channelid_id.py,sha256=JAZ1nf_AnfOa19j4PTEwN2aITojvAvDFQj56FOWH8g8,586
 Podflow/config/get_config.py,sha256=xM_C1Vk5EUAdPKwR7guPSo2IVR_QOZ-EFHfbmtMtm30,1326
@@ -47,9 +47,9 @@ Podflow/message/__init__.py,sha256=SC42QCYhGwCvzvBnxiBz6L1MN-l57WHbH7PIh-UyPdI,4
 Podflow/message/backup_zip_save.py,sha256=cU1oLO68INKSlmckYNCWmdZKu51T-HNuVFSHYzA9a-8,1740
 Podflow/message/create_main_rss.py,sha256=pbi5h0EOPLtX9rh9IUZ4QWdXQnQXNRPTE35XCUqiiqw,1773
 Podflow/message/display_qrcode_and_url.py,sha256=72DwF1H2-cmVxsRlTb93Othc-6fkgFWEVHl3djm3acE,1183
-Podflow/message/fail_message_initialize.py,sha256=r3fT21bFDY1c72yrBxouT2RPw0n29FUZR9Qi2o7Q8n8,6042
+Podflow/message/fail_message_initialize.py,sha256=ilLoRBtHaDvcz9vZ3R57Ut1AknUOQxioR0mLWsLMFL0,6130
 Podflow/message/format_time.py,sha256=2Z7rPh3rrU68UoDO5fFF_ipV_SEmtotziBmBBl0mHdc,909
-Podflow/message/get_original_rss.py,sha256=CK_Q5enOzUafgL2l5OlXBpC08Nj_B7AKPzw5DomXLwA,2369
+Podflow/message/get_original_rss.py,sha256=QRtpHEYeS9rDh4Cv_EkTIC89eSw0I6540ykrTT3yr-4,2383
 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
@@ -69,12 +69,14 @@ Podflow/netscape/get_cookie_dict.py,sha256=ptT2H8ZwFseK8EmpH0jn-lhzh-KCciOOPwpAJ
 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/upload/__init__.py,sha256=9uOIL8vr_vP_XYrhfZ4IDZmfSGyCf0_MpLOc-KnbpSY,45
+Podflow/upload/get_upload_original.py,sha256=JLepP_0ROLexVNUV-Ji8r1kq81pACfJqdA4ewIgmujw,4194
 Podflow/youtube/__init__.py,sha256=-bdMyuw-wxoz2miVkp284amS4Qg0k7VN0JPuGF-cXlM,46
-Podflow/youtube/build.py,sha256=y1R5KI_R8ydYjjxZKvMtNaHUiyMm4iBa-MIEMbA92FY,11210
+Podflow/youtube/build.py,sha256=010SwUpvtYrAOxZEWOqt70XByPpPrnZ0HQZOCD96Qhg,11171
 Podflow/youtube/get.py,sha256=dFLyiHttygqdJltwC29jD_v8wwoLynE5NUdow_0wERI,16970
 Podflow/youtube/login.py,sha256=DlS_ZG4g6CKWqS5ojE4UwFJSCSZDsXbeuDVgHtQAa4A,1380
-podflow-20250205.dist-info/METADATA,sha256=dNGzFuJ-V7LfCMbJlSKRFrG9j6Cme9LT2ABuuVpA_EM,13801
-podflow-20250205.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-podflow-20250205.dist-info/entry_points.txt,sha256=44nj8jJB7bo1JLNrKQZmwMGEA1OalrALJ0tF_G0yXLY,131
-podflow-20250205.dist-info/top_level.txt,sha256=KcvRCiz_DRWWc9i-PgpARvFB0J4CKmpZOZgPqOdG-Lk,8
-podflow-20250205.dist-info/RECORD,,
+podflow-20250212.dist-info/METADATA,sha256=ikAvsNny5lZfu8dkgprsW2R3uLKCyHxpqNwlPp2F6yo,13801
+podflow-20250212.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+podflow-20250212.dist-info/entry_points.txt,sha256=44nj8jJB7bo1JLNrKQZmwMGEA1OalrALJ0tF_G0yXLY,131
+podflow-20250212.dist-info/top_level.txt,sha256=KcvRCiz_DRWWc9i-PgpARvFB0J4CKmpZOZgPqOdG-Lk,8
+podflow-20250212.dist-info/RECORD,,