podflow 2025.1.26__py3-none-any.whl

Podflow/message/xml_rss.py

@@ -0,0 +1,46 @@
+# Podflow/message/xml_rss.py
+# coding: utf-8
+
+import time
+
+
+# 生成XML模块
+def xml_rss(title, link, description, category, icon, items):
+    # 获取当前时间
+    current_time_now = time.time()  # 获取当前时间的秒数
+    # 获取当前时区和夏令时信息
+    time_info_now = time.localtime(current_time_now)
+    # 构造时间字符串
+    formatted_time_now = time.strftime("%a, %d %b %Y %H:%M:%S %z", time_info_now)
+    #itunes_summary = description.replace("\n", "
")
+    if title == "Podflow":
+        author = "gruel-zxz"
+        subtitle = "gruel-zxz-podflow"
+    else:
+        author = title
+        subtitle = title
+    return f"""<?xml version="1.0" encoding="UTF-8"?>
+<rss version="2.0" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd">
+    <channel>
+        <title>{title}</title>
+        <link>{link}</link>
+        <description>{description}</description>
+        <category>{category}</category>
+        <generator>Podflow (support us at https://github.com/gruel-zxz/podflow)</generator>
+        <language>en-us</language>
+        <lastBuildDate>{formatted_time_now}</lastBuildDate>
+        <pubDate>Sun, 24 Apr 2005 11:20:54 +0800</pubDate>
+        <image>
+            <url>{icon}</url>
+            <title>{title}</title>
+            <link>{link}</link>
+        </image>
+        <itunes:author>{author}</itunes:author>
+        <itunes:subtitle>{subtitle}</itunes:subtitle>
+        <itunes:summary><![CDATA[{description}]]></itunes:summary>
+        <itunes:image href="{icon}"></itunes:image>
+        <itunes:explicit>no</itunes:explicit>
+        <itunes:category text="{category}"></itunes:category>
+{items}
+    </channel>
+</rss>"""

Podflow/netscape/__init__.py

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

Podflow/netscape/bulid_netscape.py

@@ -0,0 +1,44 @@
+# Podflow/netscape/bulid_netscape.py
+# coding: utf-8
+
+from Podflow.basic.file_save import file_save
+
+
+# 生成Netscape_HTTP_Cookie模块
+def bulid_netscape(file_name, cookie=None):
+    if cookie is None:
+        cookie = {}
+    if "bilibili" in file_name:
+        cookie_jar = f'''# Netscape HTTP Cookie File
+# This file is generated by yt-dlp.  Do not edit.
+
+.bilibili.com	TRUE	/	FALSE	0	SESSDATA	{cookie.get("SESSDATA", "")}
+.bilibili.com	TRUE	/	FALSE	0	bili_jct	{cookie.get("bili_jct", "")}
+.bilibili.com	TRUE	/	FALSE	0	DedeUserID	{cookie.get("DedeUserID", "")}
+.bilibili.com	TRUE	/	FALSE	0	DedeUserID__ckMd5	{cookie.get("DedeUserID__ckMd5", "")}
+.bilibili.com	TRUE	/	FALSE	0	sid	{cookie.get("sid", "")}
+.bilibili.com	TRUE	/	FALSE	0	buvid3	{cookie.get("buvid3", "")}
+.bilibili.com	TRUE	/	FALSE	0	b_nut	{cookie.get("b_nut", "")}'''
+    elif "youtube" in file_name:
+        cookie_jar = f'''# Netscape HTTP Cookie File
+# This file is generated by yt-dlp.  Do not edit.
+
+.youtube.com	TRUE	/	TRUE	0	__Secure-3PSID	{cookie.get("__Secure-3PSID", "")}
+.youtube.com	TRUE	/	TRUE	0	__Secure-1PSIDTS	{cookie.get("__Secure-1PSIDTS", "")}
+.youtube.com	TRUE	/	TRUE	0	SAPISID	{cookie.get("SAPISID", "")}
+.youtube.com	TRUE	/	TRUE	0	__Secure-1PSIDCC	{cookie.get("__Secure-1PSIDCC", "")}
+.youtube.com	TRUE	/	TRUE	0	SSID	{cookie.get("SSID", "")}
+.youtube.com	TRUE	/	TRUE	0	__Secure-1PAPISID	{cookie.get("__Secure-1PAPISID", "")}
+.youtube.com	TRUE	/	TRUE	0	__Secure-1PSID	{cookie.get("__Secure-1PSID", "")}
+.youtube.com	TRUE	/	TRUE	0	__Secure-3PAPISID	{cookie.get("__Secure-3PAPISID", "")}
+.youtube.com	TRUE	/	TRUE	0	__Secure-3PSIDCC	{cookie.get("__Secure-3PSIDCC", "")}
+.youtube.com	TRUE	/	TRUE	0	__Secure-3PSIDTS	{cookie.get("__Secure-3PSIDTS", "")}
+.youtube.com	TRUE	/	TRUE	0	LOGIN_INFO	{cookie.get("LOGIN_INFO", "")}
+.youtube.com	TRUE	/	FALSE	0	PREF	{cookie.get("PREF", "")}
+.youtube.com	TRUE	/	TRUE	0	YSC	{cookie.get("YSC", "")}
+.youtube.com	TRUE	/	TRUE	0	VISITOR_INFO1_LIVE	{cookie.get("VISITOR_INFO1_LIVE", "")}
+.youtube.com	TRUE	/	TRUE	0	VISITOR_PRIVACY_METADATA	{cookie.get("VISITOR_PRIVACY_METADATA", "")}'''
+    else:
+        cookie_jar = '''# Netscape HTTP Cookie File
+# This file is generated by yt-dlp.  Do not edit.'''
+    file_save(cookie_jar, f"{file_name}.txt", "channel_data")

Podflow/netscape/get_cookie_dict.py

@@ -0,0 +1,21 @@
+# Podflow/Netscape/get_cookie_dict.py
+# coding: utf-8
+
+from datetime import datetime
+from http.cookiejar import LoadError, MozillaCookieJar
+
+
+# 将Netscape转Dict模块
+def get_cookie_dict(file):
+    parts = file.split("/")
+    try:
+        # 加载Netscape格式的cookie文件
+        cookie_jar = MozillaCookieJar(file)
+        cookie_jar.load(ignore_discard=True)
+        return {cookie.name: cookie.value for cookie in cookie_jar}
+    except FileNotFoundError:
+        print(f"{datetime.now().strftime('%H:%M:%S')}|{parts[-1]}文件不存在")
+        return None
+    except LoadError:
+        print(f"{datetime.now().strftime('%H:%M:%S')}|{parts[-1]}文件错误")
+        return None

Podflow/parse_arguments.py

@@ -0,0 +1,80 @@
+# Podflow/parse_arguments.py
+# coding: utf-8
+
+import argparse
+from Podflow import parse
+
+
+def positive_int(value):
+    ivalue = int(value)
+    if ivalue <= 0:
+        raise argparse.ArgumentTypeError(f"{value} is not a positive integer")
+    return ivalue
+
+
+# 获取命令行参数并判断
+def parse_arguments():
+    # 创建 ArgumentParser 对象
+    parser = argparse.ArgumentParser(
+        description="you can try: Podflow -n 24 -d 3600"
+    )
+    # 参数
+    parser.add_argument(
+        "-n",
+        "--times",
+        nargs=1,
+        type=positive_int,
+        metavar="NUM",
+        help="number of times",
+    )
+    parser.add_argument(
+        "-d",
+        "--delay",
+        type=positive_int,
+        default=1500,
+        metavar="NUM",
+        help="delay in seconds(default: 1500)",
+    )
+    parser.add_argument(
+        "-c",
+        "--config",
+        type=str,
+        default="config.json",
+        metavar="FILE_PATH",
+        help="path to the config.json file",
+    )
+    parser.add_argument(
+        "-p",
+        "--period",
+        type=positive_int,
+        metavar="NUM",
+        default=1,
+        help="Specify the update frequency (unit: times/day), default value is 1",
+    )
+    parser.add_argument(
+        "--shortcuts",
+        nargs="*",
+        type=str,
+        metavar="URL",
+        help="only shortcuts can be work",
+    )
+    parser.add_argument("--file", nargs="?", help=argparse.SUPPRESS)  # 仅运行在ipynb中
+    parser.add_argument("--httpfs", action="store_true", help=argparse.SUPPRESS)
+    # 解析参数
+    args = parser.parse_args()
+    parse.time_delay = args.delay
+    parse.config = args.config
+    parse.period = args.period
+    parse.file = args.file
+    parse.httpfs = args.httpfs
+    # 检查并处理参数的状态
+    if args.times is not None:
+        parse.update_num = int(args.times[0])
+    if args.shortcuts is not None:
+        parse.update_num = 1
+        parse.argument = "a-shell"
+        parse.shortcuts_url_original = args.shortcuts
+    if args.file is not None and ".json" in args.file:
+        parse.update_num = 1
+        parse.argument = ""
+        parse.shortcuts_url_original = []

Podflow/remove/__init__.py

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

Podflow/remove/remove_dir.py

@@ -0,0 +1,33 @@
+# Podflow/remove/remove_dir.py
+# coding: utf-8
+
+import os
+import re
+import shutil
+from Podflow import gVar
+from Podflow.basic.write_log import write_log
+
+
+# 删除已抛弃的媒体文件夹模块
+def remove_dir():
+    def remove_path(name):
+        directory_path = f"channel_audiovisual/{name}"
+        # 检查目录是否存在
+        if os.path.exists(directory_path):
+            # 删除该目录及其内容
+            shutil.rmtree(directory_path)
+        write_log(f"{name}文件夹已删除")
+
+    folder_names = [
+        folder
+        for folder in os.listdir("channel_audiovisual")
+        if os.path.isdir(f"channel_audiovisual/{folder}")
+    ]
+    folder_names_youtube = [name for name in folder_names if re.match(r"UC.{22}", name)]
+    for name in folder_names_youtube:
+        if name not in gVar.channelid_youtube_ids_original:
+            remove_path(name)
+    folder_names_bilibili = [name for name in folder_names if re.match(r"[0-9]+", name)]
+    for name in folder_names_bilibili:
+        if name not in gVar.channelid_bilibili_ids_original:
+            remove_path(name)

Podflow/remove/remove_file.py

@@ -0,0 +1,23 @@
+# Podflow/remove/remove_file.py
+# coding: utf-8
+
+import os
+from Podflow import gVar
+from Podflow.basic.write_log import write_log
+
+
+# 删除多余媒体文件模块
+def remove_file():
+    channelid_youtube_ids = gVar.channelid_youtube_ids
+    for output_dir, name in channelid_youtube_ids.items():
+        for file_name in os.listdir(f"channel_audiovisual/{output_dir}"):
+            if file_name not in gVar.all_youtube_content_ytid[output_dir]:
+                os.remove(f"channel_audiovisual/{output_dir}/{file_name}")
+                write_log(f"{name}|{file_name}已删除")
+
+    channelid_bilibili_ids = gVar.channelid_bilibili_ids
+    for output_dir, name in channelid_bilibili_ids.items():
+        for file_name in os.listdir(f"channel_audiovisual/{output_dir}"):
+            if file_name not in gVar.all_bilibili_content_bvid[output_dir]:
+                os.remove(f"channel_audiovisual/{output_dir}/{file_name}")
+                write_log(f"{name}|{file_name}已删除")

Podflow/youtube/__init__.py

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

Podflow/youtube/build.py

@@ -0,0 +1,287 @@
+# Podflow/youtube/build.py
+# coding: utf-8
+
+import re
+import html
+import threading
+import contextlib
+import xml.etree.ElementTree as ET
+from datetime import datetime, timezone
+from Podflow import gVar
+from Podflow.message.xml_rss import xml_rss
+from Podflow.basic.file_save import file_save
+from Podflow.message.xml_item import xml_item
+from Podflow.basic.http_client import http_client
+from Podflow.message.format_time import format_time
+from Podflow.basic.get_html_dict import get_html_dict
+from Podflow.message.xml_original_item import xml_original_item
+
+
+# 获取YouTube频道简介模块
+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(
+            f"https://www.youtube.com/channel/{output_dir}/about",
+            f"{gVar.channelid_youtube_ids[output_dir]} 简介",
+            2,
+            5,
+        ):
+            channel_about = channel_about.text
+            xml_tree = {
+                "icon": re.sub(
+                    r"=s(0|[1-9]\d{0,3}|1[0-9]{1,3}|20[0-3][0-9]|204[0-8])-c-k",
+                    "=s2048-c-k",
+                    re.search(
+                        r"https?://yt3.googleusercontent.com/[^\s]*(?=\">)",
+                        channel_about,
+                    ).group(),
+                )
+            }
+            xml_tree["description"] = re.search(
+                r"(?<=\<meta itemprop\=\"description\" content\=\").*?(?=\")",
+                channel_about,
+                flags=re.DOTALL,
+            ).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:
+        thread = threading.Thread(target=youtube_xml_get, args=(output_dir,))
+        youtube_xml_get_threads.append(thread)
+        thread.start()
+    # 等待所有线程完成
+    for thread in youtube_xml_get_threads:
+        thread.join()
+
+
+# 获取YouTube播放列表模块
+def get_youtube_playlist(url, channelid_title):
+    videoids = []
+    ytInitialData = get_html_dict(url, f"{channelid_title}|播放列表", "ytInitialData")
+    with contextlib.suppress(KeyError):
+        contents = ytInitialData["contents"]["twoColumnBrowseResultsRenderer"]["tabs"][
+            0
+        ]["tabRenderer"]["content"]["sectionListRenderer"]["contents"][0][
+            "itemSectionRenderer"
+        ]["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 = {}
+
+    # 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)
+    output_dir = re.search(r"(?<=<yt:channelId>).+(?=</yt:channelId>)", entry).group()
+    description = re.search(
+        r"(?<=<media:description>).+(?=</media:description>)",
+        re.sub(r"\n+", "\n", entry),
+        flags=re.DOTALL,
+    )
+    description = description.group() if description else ""
+    ytid = re.search(r"(?<=<yt:videoId>).+(?=</yt:videoId>)", entry).group()
+    return xml_item(
+        ytid,
+        output_dir,
+        f"https://youtube.com/watch?v={ytid}",
+        gVar.channelid_youtube[gVar.channelid_youtube_ids[output_dir]]["title"],
+        re.search(r"(?<=<title>).+(?=</title>)", entry).group(),
+        description,
+        pubDate,
+        re.search(r"(?<=<media:thumbnail url=\").+(?=\" width=\")", entry).group(),
+        title_change,
+    )
+
+
+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]
+        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"\?.*$", "", image)
+        pubDate = format_time(published)
+    else:
+        title = html.escape(item["title"])
+        description = html.escape(re.sub(r"\n+", "\n", item["description"]))
+        pubDate = format_time(item["pubDate"])
+        image = re.sub(r"\?.*$", "", item["image"])
+    return xml_item(
+        guid,
+        output_dir,
+        video_website,
+        channelid_title,
+        title,
+        description,
+        pubDate,
+        image,
+        title_change,
+    )
+
+
+# 生成YouTube对应channel的需更新的items模块
+def youtube_xml_items(output_dir):
+    items_list = [f"<!-- {output_dir} -->"]
+    entry_num = 0
+    original_judgment = True
+    channelid_youtube_value = gVar.channelid_youtube[
+        gVar.channelid_youtube_ids[output_dir]
+    ]
+    channelid_title = channelid_youtube_value["title"]
+    title_change = channelid_youtube_value.get("title_change", [])
+    update_size = channelid_youtube_value["update_size"]
+    if title_change:
+        for title_index, title_value in enumerate(title_change):
+            if "url" in title_value:
+                title_change[title_index]["table"] = get_youtube_playlist(
+                    title_value["url"], channelid_title
+                )
+    output_dir_value = gVar.channelid_youtube_rss[output_dir]
+    # 最新更新
+    if output_dir_value["type"] == "dict":
+        for guid in output_dir_value["content"]["list"]:
+            if guid not in gVar.video_id_failed:
+                item = output_dir_value["content"]["item"][guid]
+                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
+    else:
+        if output_dir_value["type"] == "html":  # 获取最新的rss信息
+            file_xml = output_dir_value["content"].text
+        else:
+            file_xml = output_dir_value["content"]
+        entrys = re.findall(r"<entry>.+?</entry>", file_xml, re.DOTALL)
+        for entry in entrys:
+            if (
+                re.search(r"(?<=<yt:videoId>).+(?=</yt:videoId>)", entry).group()
+                not in gVar.video_id_failed
+            ):
+                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
+            if entry_num >= update_size:
+                break
+    items_guid = re.findall(r"(?<=<guid>).+?(?=</guid>)", "".join(items_list))
+    # 存量接入
+    entry_count = channelid_youtube_value["last_size"] - len(items_guid)
+    if gVar.xmls_original and output_dir in gVar.xmls_original and entry_count > 0:
+        xml_num = 0
+        for xml in gVar.xmls_original[output_dir].split(f"<!-- {output_dir} -->"):
+            xml_guid = re.search(r"(?<=<guid>).+(?=</guid>)", xml)
+            if (
+                xml_guid
+                and xml_guid.group() not in items_guid
+                and xml_guid.group() not in gVar.video_id_failed
+            ):
+                items_list.append(
+                    f"{xml_original_item(xml, channelid_title, original_judgment, title_change)}<!-- {output_dir} -->"
+                )
+                xml_num += 1
+            if xml_num >= entry_count:
+                break
+    # 向后更新
+    with contextlib.suppress(KeyError):
+        backward = output_dir_value["backward"]
+        for backward_guid in backward["list"]:
+            if backward_guid not in gVar.video_id_failed:
+                backward_item = backward["item"][backward_guid]
+                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} -->")
+    # 生成对应xml
+    try:
+        with open(
+            f"channel_rss/{output_dir}.xml", "r", encoding="utf-8"
+        ) as file:  # 打开文件进行读取
+            root = ET.parse(file).getroot()
+            description = (root.findall(".//description")[0]).text
+            description = "" if description is None else html.escape(description)
+            icon = (root.findall(".//url")[0]).text
+    except Exception:  # 参数不存在直接更新
+        description = gVar.config["description"]
+        icon = gVar.config["icon"]
+    if (
+        output_dir in gVar.channelid_youtube_ids_update
+        and output_dir in gVar.youtube_xml_get_tree
+    ):
+        description = gVar.youtube_xml_get_tree[output_dir]["description"]
+        icon = gVar.youtube_xml_get_tree[output_dir]["icon"]
+    category = gVar.config["category"]
+    if output_dir_value["type"] == "dict":
+        title = output_dir_value["content"]["title"]
+    else:
+        title = re.search(r"(?<=<title>).+(?=</title>)", file_xml).group()
+    link = f"https://www.youtube.com/channel/{output_dir}"
+    items = "".join(items_list)
+    items = f"""<!-- {{{output_dir}}} -->
+{items}
+<!-- {{{output_dir}}} -->"""
+    file_save(
+        xml_rss(title, link, description, category, icon, items),
+        f"{output_dir}.xml",
+        "channel_rss",
+    )
+    return items