podflow 2025.1.26__py3-none-any.whl

Podflow/__init__.py

@@ -0,0 +1,137 @@
+# Podflow/__init__.py
+# coding: utf-8
+
+# 默认参数
+default_config = {
+    "preparation_per_count": 100,  # 获取媒体信息每组数量
+    "completion_count": 100,  # 媒体缺失时最大补全数量
+    "retry_count": 5,  # 媒体下载重试次数
+    "url": "http://127.0.0.1",  # HTTP共享地址
+    "port": 8000,  # HTTP共享端口
+    "port_in_url": True,  # HTTP共享地址是否包含端口
+    "httpfs": False,  # HTTP共享日志
+    "title": "Podflow",  # 博客的名称
+    "filename": "Podflow",  # 主XML的文件名称
+    "link": "https://github.com/gruel-zxz/podflow",  # 博客主页
+    "description": "在iOS平台上借助workflow和a-shell搭建专属的播客服务器。",  # 博客信息
+    "icon": "https://raw.githubusercontent.com/gruel-zxz/podflow/main/Podflow.png",  # 博客图标
+    "category": "TV & Film",  # 博客类型
+    "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
+    "channelid_youtube": {  # Youtube频道列表
+        "youtube": {
+            "update_size": 15,  # 每次获取频道媒体数量
+            "id": "UCBR8-60-B28hp2BmDPdntcQ",  # 频道ID
+            "title": "YouTube",  # 频道名称
+            "quality": "480",  # 媒体分辨率(仅在media为视频时有效)
+            "last_size": 50,  # 媒体保留数量
+            "media": "m4a",  # 下载媒体类型
+            "DisplayRSSaddress": False,  # 是否在Print中显示子博客地址
+            "InmainRSS": True,  # 是否在主博客中
+            "QRcode": False,  # 是否显示子博客地址二维码(仅在DisplayRSSaddress为True时有效)
+            "BackwardUpdate": False,  # 是否向后更新
+            "BackwardUpdate_size": 3,  # 向后更新数量(仅在BackwardUpdate为True时有效)
+            "want_retry_count": 8,  # 媒体获取失败后多少次后重试(小于等于该数量时将一直重试)
+            "title_change": [  # 标题文本修改(默认为无, 可多个条件，以列表形式存在)
+                {  # match和url参数至少有一个, 如都有将同时生效
+                    "mode": "add-left",  # 修改模式(add-left: 开头添加, add-right: 结尾添加, replace: 内容替换)
+                    "match": "",  # 需要匹配的规则(为正则表达式)
+                    "url": "https://www.youtube.com/playlist?list=...",  # 播放列表网址(只适用于YouTube频道, 并且不适用replace模式, 选择后会失效)
+                    "text": "",  # 需要替换或添加的文本
+                },
+                {
+                    "mode": "add-right",
+                    "match": "",
+                    "url": "",
+                    "text": "",
+                },
+            ],
+            "NoShorts": False,  # 是否不下载Shorts媒体
+        },
+    },
+    "channelid_bilibili": {  # 哔哩哔哩频道列表
+        "哔哩哔哩弹幕网": {
+            "update_size": 25,
+            "id": "8047632",
+            "title": "哔哩哔哩弹幕网",
+            "quality": "480",
+            "last_size": 100,
+            "media": "m4a",
+            "DisplayRSSaddress": False,
+            "InmainRSS": True,
+            "QRcode": False,
+            "BackwardUpdate": False,
+            "BackwardUpdate_size": 3,
+            "want_retry_count": 8,
+            "title_change": {
+                "mode": "replace",
+                "match": "",
+                "text": "",
+            },
+            "AllPartGet": False,  # 是否提前获取分P或互动视频(建议update_size大于5时使用, 如果该变量不存在时, 默认update_size大于5时开启)
+        },
+    },
+}
+# 如果InmainRSS为False或频道有更新则无视DisplayRSSaddress的状态, 都会变为True。
+
+
+# 全局变量
+class Application_gVar:
+    def __init__(self):
+        self.config = {}  # 配置文件字典
+        self.channelid_youtube = {}  # YouTube频道字典
+        self.channelid_bilibili = {}  # 哔哩哔哩频道字典
+        self.channelid_youtube_ids = {}  # YouTube频道ID字典
+        self.channelid_youtube_ids_original = {}  # 原始YouTube频道ID字典
+        self.channelid_bilibili_ids = {}  # 哔哩哔哩频道ID字典
+        self.channelid_bilibili_ids_original = {}  # 原始哔哩哔哩频道ID字典
+
+        self.server_process_print_flag = ["keep"]  # httpserver进程打印标志列表
+        self.update_generate_rss = True  # 更新并生成rss布朗值
+        self.displayed_QRcode = []  # 已显示二维码列表
+
+        self.bilibili_data = {}  # 哔哩哔哩data字典
+        self.youtube_cookie = {}  # YouTube cookie字典
+        self.channelid_youtube_ids_update = {}  # 需更新的YouTube频道字典
+        self.youtube_content_ytid_update = {}  # 需下载YouTube视频字典
+        self.youtube_content_ytid_backward_update = {}  # 向后更新需下载YouTube视频字典
+        self.channelid_youtube_rss = {}  # YouTube频道最新Rss Response字典
+        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.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
+        self.xmls_original = {}  # 原始xml信息字典
+        self.xmls_original_fail = []  # 未获取原始xml频道列表
+        self.youtube_xml_get_tree = {}  # YouTube频道简介和图标字典
+        self.all_youtube_content_ytid = {}  # 所有YouTube视频id字典
+        self.all_bilibili_content_bvid = {}  # 所有哔哩哔哩视频id字典
+        self.all_items = []  # 更新后所有item明细列表
+        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.shortcuts_url = {}  # 输出至shortcut的url字典
+
+
+# 参数变量
+class Application_parse:
+    def __init__(self):
+        self.shortcuts_url_original = []
+        self.argument = ""
+        self.update_num = -1
+        self.time_delay = 0
+        self.config = ""
+        self.period = 1
+        self.file = ""
+        self.httpfs = False
+
+
+# 创建 Application 类的实例
+gVar = Application_gVar()
+parse = Application_parse()

Podflow/basic/__init__.py

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

Podflow/basic/file_save.py

@@ -0,0 +1,21 @@
+# Podflow/basic/file_save.py
+# coding: utf-8
+
+import os
+import json
+
+
+# 文件保存模块
+def file_save(content, file_name, folder=None):
+    # 如果指定了文件夹则将文件保存到指定的文件夹中
+    if folder:
+        file_path = os.path.join(os.getcwd(), folder, file_name)
+    else:
+        # 如果没有指定文件夹则将文件保存在当前工作目录中
+        file_path = os.path.join(os.getcwd(), file_name)
+    # 保存文件
+    with open(file_path, "w", encoding="utf-8") as file:
+        if "." in file_name and file_name.split(".")[-1] == "json":
+            json.dump(content, file, ensure_ascii=False, indent=4)
+        else:
+            file.write(content)

Podflow/basic/folder_build.py

@@ -0,0 +1,16 @@
+# Podflow/basic/folder_build.py
+# coding: utf-8
+
+import os
+from Podflow.basic.write_log import write_log
+
+
+# 构建文件夹模块
+def folder_build(folder_name, parent_folder_name=None):
+    if parent_folder_name:
+        folder_path = os.path.join(os.getcwd(), parent_folder_name, folder_name)
+    else:
+        folder_path = os.path.join(os.getcwd(), folder_name)
+    if not os.path.exists(folder_path):  # 判断文件夹是否存在
+        os.makedirs(folder_path)  # 创建文件夹
+        write_log(f"文件夹{folder_name}创建成功")

Podflow/basic/get_duration.py

@@ -0,0 +1,18 @@
+# Podflow/basic/get_duration.py
+# coding: utf-8
+
+import math
+import ffmpeg
+from Podflow.basic.write_log import write_log
+
+
+# 获取已下载视频时长模块
+def get_duration(file_path):
+    try:
+        # 调用ffmpeg获取视频文件的时长信息
+        probe = ffmpeg.probe(file_path)
+        duration = float(probe['format']['duration'])
+        return math.ceil(duration)
+    except ffmpeg.Error as e:
+        error_note = e.stderr.decode('utf-8').splitlines()[-1]
+        write_log(f"\033[31mError:\033[0m {error_note}")

Podflow/basic/get_file_list.py

@@ -0,0 +1,57 @@
+# Podflow/basic/get_file_list.py
+# coding: utf-8
+
+import os
+import re
+from Podflow.basic.list_merge_tidy import list_merge_tidy
+
+
+# 获取文件列表和分P列表
+def get_file_list(video_key, video_media="m4a", length=12):
+    media = ("m4a", "mp4", "part") if video_media == "m4a" else ("mp4", "part")
+    try:
+        content_id = [
+            file  # 获取文件名（包括扩展名）
+            for file in os.listdir(
+                f"channel_audiovisual/{video_key}"
+            )  # 遍历指定目录下的所有文件
+            if file.endswith(media)  # 筛选出以 media 结尾的文件
+        ]
+        content_id_items = []
+        items_counts = {}
+        for id_num in content_id:
+            if len(id_num) > length + 4:
+                content_id_items.append(id_num)
+            if ".part" in id_num:
+                items_counts[id_num[:length]] = 0
+        content_id_items = [id_num[:length] for id_num in content_id_items]
+        for id_num in content_id_items:
+            if id_num not in items_counts:
+                qtys = content_id_items.count(id_num)
+                if video_media == "m4a":
+                    pattern = re.compile(rf"{id_num}_[0-9]*\.(m4a|mp4)")
+                else:
+                    pattern = re.compile(rf"{id_num}_[0-9]*\.(mp4)")
+                if len([item for item in content_id if pattern.search(item)]) == qtys:
+                    items_counts[id_num] = qtys
+                else:
+                    fail = False
+                    for qty in range(qtys):
+                        if video_media == "m4a":
+                            if (
+                                f"{id_num}_p{qty + 1}.m4a" not in content_id
+                                and f"{id_num}_p{qty + 1}.mp4" not in content_id
+                            ):
+                                fail = True
+                        elif f"{id_num}_p{qty + 1}.mp4" not in content_id:
+                            fail = True
+                    items_counts[id_num] = 0 if fail else qtys
+        content_id = list_merge_tidy(content_id, [], length)
+        for id_num, num in items_counts.copy().items():
+            if num in [1, 0] and id_num in content_id:
+                content_id.remove(id_num)
+                del items_counts[id_num]
+    except Exception:
+        content_id = []
+        items_counts = {}
+    return content_id, items_counts

Podflow/basic/get_html_dict.py

@@ -0,0 +1,30 @@
+# Podflow/basic/get_html_dict.py
+# coding: utf-8
+
+import re
+import json
+from bs4 import BeautifulSoup
+from Podflow.basic.http_client import http_client
+
+
+# 通过bs4获取html中字典模块
+def get_html_dict(url, name, script_label):
+    if not (response := http_client(url, name)):
+        return None
+    html_content = response.text
+    # 使用Beautiful Soup解析HTML
+    soup = BeautifulSoup(html_content, 'html.parser')
+    if not (
+        data_script := soup.find(
+            'script', string=lambda t: t and script_label in t
+        )
+    ):
+        return None
+    try:
+        # 使用正则表达式提取 JSON 数据
+        pattern = re.compile(r'\{.*\}', re.DOTALL)
+        if match := pattern.search(data_script.text):
+            data_str = match.group()
+            return json.loads(data_str)
+    except json.JSONDecodeError:
+        return None

Podflow/basic/http_client.py

@@ -0,0 +1,75 @@
+# Podflow/basic/http_client.py
+# coding: utf-8
+
+import time
+from datetime import datetime
+import requests
+
+
+# HTTP 请求重试模块
+def http_client(
+    url,
+    name="",
+    max_retries=10,
+    retry_delay=4,
+    headers_possess=False,
+    cookies=None,
+    data=None,
+    mode="get",
+):
+    user_agent = {
+        "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"
+    }
+    if "bilibili" in url:
+        user_agent["Referer"] = "https://www.bilibili.com/"
+    elif "youtube" in url:
+        user_agent["Referer"] = "https://www.youtube.com/"
+    elif "douyin" in url:
+        headers_douyin = {
+            "authority": "sso.douyin.com",
+            "accept": "application/json, text/plain, */*",
+            "accept-language": "zh-CN,zh;q=0.9",
+            "origin": "https://www.douyin.com",
+            "referer": "https://www.douyin.com/",
+            "sec-ch-ua": '"Google Chrome";v="117", "Not;A=Brand";v="8", "Chromium";v="117"',
+            "sec-ch-ua-mobile": "?0",
+            "sec-ch-ua-platform": '"Windows"',
+            "sec-fetch-dest": "empty",
+            "sec-fetch-mode": "cors",
+            "sec-fetch-site": "same-site",
+            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
+        }
+        user_agent |= headers_douyin
+    err = None  # 初始化 err 变量
+    response = None  # 初始化 response 变量
+    # 创建一个Session对象
+    session = requests.Session()
+    if headers_possess:
+        session.headers.update(user_agent)
+    if cookies:
+        session.cookies.update(cookies)
+    if data:
+        session.params.update(data)
+    for num in range(max_retries):
+        try:
+            if mode != "post":
+                response = session.get(url, timeout=8)
+            else:
+                response = session.post(url, timeout=8)
+            response.raise_for_status()
+        except Exception as http_get_error:
+            if response is not None and response.status_code in {404}:
+                return response
+            if name:
+                print(
+                    f"{datetime.now().strftime('%H:%M:%S')}|{name}|\033[31m连接异常重试中...\033[97m{num + 1}\033[0m"
+                )
+            err = f":\n{str(http_get_error)}" if err else ""
+        else:
+            return response
+        time.sleep(retry_delay)
+    if name:
+        print(
+            f"{datetime.now().strftime('%H:%M:%S')}|{name}|\033[31m达到最大重试次数\033[97m{max_retries}\033[0m{err}"
+        )
+    return response

Podflow/basic/list_merge_tidy.py

@@ -0,0 +1,15 @@
+# Podflow/basic/list_merge_tidy.py
+# coding: utf-8
+
+
+# 合并整形列表模块
+def list_merge_tidy(list1, list2=None, length=None):
+    if list2 is None:
+        list2 = []
+    final_list = []
+    for item in list1 + list2:
+        if item:
+            item = item[:length]
+        if item not in final_list:
+            final_list.append(item)
+    return final_list

Podflow/basic/qr_code.py

@@ -0,0 +1,55 @@
+# Podflow/basic/qr_code.py
+# coding: utf-8
+
+import math
+import qrcode
+
+
+# 网址二维码模块
+def qr_code(data):
+    # 创建一个QRCode对象
+    qr = qrcode.QRCode(
+        version=1,
+        error_correction=qrcode.constants.ERROR_CORRECT_L,
+        box_size=1,
+        border=0,
+    )
+    # 设置二维码的数据
+    qr.add_data(data)
+    # 获取QR Code矩阵
+    qr.make(fit=True)
+    matrix = qr.make_image(fill_color="black", back_color="white").modules
+    # 获取图像的宽度和高度
+    width, height = len(matrix), len(matrix)
+    height_double = math.ceil(height / 2)
+    # 转换图像为ASCII字符
+    fonts = ["▀", "▄", "█", " "]
+    ascii_art = ""
+    for y in range(height_double):
+        if (y + 1) * 2 - 1 >= height:
+            for x in range(width):
+                ascii_art += (
+                    fonts[0] if matrix[(y + 1) * 2 - 2][x] is True else fonts[3]
+                )
+        else:
+            for x in range(width):
+                if (
+                    matrix[(y + 1) * 2 - 2][x] is True
+                    and matrix[(y + 1) * 2 - 1][x] is True
+                ):
+                    ascii_art += fonts[2]
+                elif (
+                    matrix[(y + 1) * 2 - 2][x] is True
+                    and matrix[(y + 1) * 2 - 1][x] is False
+                ):
+                    ascii_art += fonts[0]
+                elif (
+                    matrix[(y + 1) * 2 - 2][x] is False
+                    and matrix[(y + 1) * 2 - 1][x] is True
+                ):
+                    ascii_art += fonts[1]
+                else:
+                    ascii_art += fonts[3]
+            ascii_art += "\n"
+    print(ascii_art)
+    return height_double

Podflow/basic/split_dict.py

@@ -0,0 +1,14 @@
+# Podflow/basic/split_dict.py
+# coding: utf-8
+
+
+# 字典拆分模块
+def split_dict(data, chunk_size=100, firse_item_only=False):
+    if chunk_size == 0:
+        return [{}]
+    end_value = chunk_size if firse_item_only else len(data)
+    chunks = []
+    for i in range(0, end_value, chunk_size):
+        chunk = dict(list(data.items())[i:i+chunk_size])
+        chunks.append(chunk)
+    return chunks

Podflow/basic/time_format.py

@@ -0,0 +1,16 @@
+# Podflow/basic/time_format.py
+# coding: utf-8
+
+
+# 格式化时间模块
+def time_format(duration):
+    if duration is None:
+        return "Unknown"
+    duration = int(duration)
+    hours, remaining_seconds = divmod(duration, 3600)
+    minutes = remaining_seconds // 60
+    remaining_seconds = remaining_seconds % 60
+    if hours > 0:
+        return "{:02}:{:02}:{:02}".format(hours, minutes, remaining_seconds)
+    else:
+        return "{:02}:{:02}".format(minutes, remaining_seconds)

Podflow/basic/time_stamp.py

@@ -0,0 +1,61 @@
+# Podflow/basic/time_stamp.py
+# coding: utf-8
+
+import time
+import threading
+import contextlib
+from datetime import datetime
+from Podflow.basic.http_client import http_client
+
+
+# 时间戳模块
+def time_stamp():
+    time_stamps = []
+
+    # 获取时间戳淘宝
+    def time_stamp_taobao():
+        if response := http_client(
+            "http://api.m.taobao.com/rest/api3.do?api=mtop.common.getTimestamp",
+            "",
+            1,
+            0,
+        ):
+            response_json = response.json()
+            with contextlib.suppress(KeyError):
+                time_stamps.append(int(response_json["data"]["t"]))
+
+    # 获取时间戳美团
+    def time_stamp_meituan():
+        if response := http_client(
+            "https://cube.meituan.com/ipromotion/cube/toc/component/base/getServerCurrentTime",
+            "",
+            1,
+            0,
+        ):
+            response_json = response.json()
+            with contextlib.suppress(KeyError):
+                time_stamps.append(int(response_json["data"]))
+
+    # 获取时间戳苏宁
+    def time_stamp_suning():
+        if response := http_client("https://f.m.suning.com/api/ct.do", "", 1, 0):
+            response_json = response.json()
+            with contextlib.suppress(KeyError):
+                time_stamps.append(int(response_json["currentTime"]))
+
+    # 创建线程
+    thread1 = threading.Thread(target=time_stamp_taobao)
+    thread2 = threading.Thread(target=time_stamp_meituan)
+    thread3 = threading.Thread(target=time_stamp_suning)
+    # 启动线程
+    thread1.start()
+    thread2.start()
+    thread3.start()
+    # 等待线程结束
+    thread1.join()
+    thread2.join()
+    thread3.join()
+    if time_stamps:
+        return int(sum(time_stamps) / len(time_stamps))
+    print(f"{datetime.now().strftime('%H:%M:%S')}|\033[31m获取时间戳api失败\033[0m")
+    return round(time.time() * 1000)

Podflow/basic/vary_replace.py

@@ -0,0 +1,11 @@
+# Podflow/basic/vary_replace.py
+# coding: utf-8
+
+import re
+
+
+# 批量正则表达式替换删除模块
+def vary_replace(varys, text):
+    for vary in varys:
+        text = re.sub(vary, "", text)
+    return text

Podflow/basic/write_log.py

@@ -0,0 +1,43 @@
+# Podflow/basic/write_log.py
+# coding: utf-8
+
+import re
+from datetime import datetime
+from Podflow.basic.file_save import file_save
+
+
+# 日志模块
+def write_log(
+    log,
+    suffix=None,
+    display=True,
+    time_display=True,
+    only_log="",
+    file_name="Podflow.log",
+):
+    # 获取当前的具体时间
+    current_time = datetime.now()
+    # 格式化输出, 只保留年月日时分秒
+    formatted_time = current_time.strftime("%Y-%m-%d %H:%M:%S")
+    # 打开文件, 并读取原有内容
+    try:
+        with open(file_name, "r", encoding="utf-8") as file:
+            contents = file.read()
+    except FileNotFoundError:
+        contents = ""
+    # 将新的日志内容添加在原有内容之前
+    log_in = re.sub(r"\033\[[0-9;]+m", "", log)
+    log_in = re.sub(r"\n", "", log_in)
+    only_log = re.sub(r"\033\[[0-9;]+m", "", only_log)
+    new_contents = (
+        f"{formatted_time} {log_in}{only_log}\n{contents}"
+        if only_log
+        else f"{formatted_time} {log_in}\n{contents}"
+    )
+    # 将新的日志内容写入文件
+    file_save(new_contents, file_name)
+    if display:
+        formatted_time_mini = current_time.strftime("%H:%M:%S")
+        log_print = f"{formatted_time_mini}|{log}" if time_display else f"{log}"
+        log_print = f"{log_print}|{suffix}" if suffix else f"{log_print}"
+        print(log_print)

Podflow/bilibili/__init__.py

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