import requests
from lxml import etree
import os
import re
from urllib.parse import quote

# 请求地址转义
def url_quote(url):
    _ = url.replace("https://xiaojiejie.me","")
    __ = quote(_)
    return "https://xiaojiejie.me" + __

# 将列表中的所有元素转化为字符串
def list_to_str(lst):
    return ''.join(lst)

# 使用正则表达式替换掉标点符号
def remove_punctuation(text):
    result = re.sub(r'[^\u4e00-\u9fa5]', '', text)
    return result

headers = {
    'User-Agent': 'Apifox/1.0.0 (https://apifox.com)'
    }

# 下载单张图片(单组图)
def download_single_img(url,classify=None,name=None,index=None):
    response = requests.get(url,headers=headers)
    root = etree.HTML(response.text)
    # with open("two.html", "w",encoding='utf-8') as f:
    #     f.write(response.text)
    # 保存目录
    local_img = root.xpath('//div[@id="image_div"]//img/@src')
    # print(local_img)
    for img in local_img:
        print(img)
        if "webp" in img and "logo" not in img:
            print("ok:",img)
            _save = os.path.join(save_dir,classify,name)
            if not os.path.exists(_save):
                os.makedirs(_save)
            res = requests.get(url_quote(img))
            print(res.status_code,"write")
            with open(os.path.join(_save,str(index)+".jpg"), "wb") as f:
                f.write(res.content)
                
# 获取单页的内容
def get_single_page_content(url,classify=None):
    print(url)
    r = requests.get(url,headers=headers)
    root = etree.HTML(r.text)
    item_info = root.xpath('//ul[@id="index_ajax_list"]/li') # li
    for item in item_info:
        source_url = list_to_str(item.xpath('a/@href'))
        page_number = list_to_str(item.xpath('a/div/span/text()'))
        _name = remove_punctuation(list_to_str(item.xpath('div/a/text()')))
        try:
            download_single_img(url,classify=classify,name=_name,index="1")
        except:
            print("error:",source_url)
        for _index in range(2,int(page_number)+1):
            _url = source_url + str(_index) + "/"
            print(_url,classify)
            try:
                download_single_img(_url,classify=classify,name=_name,index=_index)
            except:
                print("error:",_url)

u = [
    {"https://xiaojiejie.me/coser/ucoser":83},   # 83
    {"https://xiaojiejie.me/life/yygirls":235},   # 235
    {"https://xiaojiejie.me/aigirls":1}    # 1
]

save_dir = "/root/info/xiao/img"
for sub in u:
    for k,v in sub.items():
        print(k,v)
        for i in range(1,v+1):
            _ = k + "/page/" + str(i) + "/"
            get_single_page_content(_,classify=k.split("/")[-1])

# youku_downloader.py
import os
import re
import subprocess
import requests
from bs4 import BeautifulSoup
from playwright.sync_api import sync_playwright


class YoukuVideoDownloader:
    def __init__(self):
        pass

    def extract_id_from_url(self, url):
        """从优酷URL中提取视频ID"""
        pattern = r'id_([^\.]+)\.html'
        match = re.search(pattern, url)
        if match:
            return match.group(1)
        else:
            return None

    def merge_videos(self, video_files, output_filename):
        """合并视频文件"""
        # 将视频文件路径写入到一个文本文件中
        with open('input_files.txt', 'w') as f:
            for file in video_files:
                f.write("file '{}'\n".format(file))

        print(output_filename)
        # 构建 ffmpeg 命令
        ffmpeg_command = [
            'ffmpeg.exe',  # ffmpeg 可执行文件的路径（假设在当前目录下）
            '-y',  # 覆盖输出文件而不询问
            '-f', 'concat',  # 指定输入文件格式为 concat（连接多个文件）
            '-safe', '0',  # 禁用安全模式，允许使用任意文件名
            '-i', 'input_files.txt',  # 指定包含输入文件列表的文件（每行一个文件名）
            '-c', 'copy',  # 使用 copy 编解码器，快速拷贝视频和音频流而不重新编码
            output_filename  # 输出文件名
        ]

        # 执行ffmpeg命令
        result = subprocess.run(ffmpeg_command, shell=True)

        # 删除临时文本文件
        os.remove('input_files.txt')

        # 删除原始视频文件
        for file in video_files:
            os.remove(file)

    def download_and_merge(self, url, title):
        # 获取视频 ID
        video_id = self.extract_id_from_url(url)
        if not video_id:
            print("无法获取视频ID，请检查URL是否正确")
            # progress_callback("无法获取视频ID，请检查URL是否正确", "error")
            return

        # 创建下载目录
        download_dir = "download"
        if not os.path.exists(download_dir):
            os.makedirs(download_dir)

        # 自定义浏览器位置
        firefox_executable_path = "firefox-1440"

        # 创建 Playwright 的浏览器实例
        with sync_playwright() as p:
            # 设置浏览器启动参数
            browser = p.firefox.launch(headless=True)  # 设置 headless 参数为 True，无头模式
            page = browser.new_page()

            # 打开网页
            page.goto('https://player.youku.com/embed/' + video_id)

            # 等待一段时间，以确保动态内容加载完成
            page.wait_for_timeout(5000)

            # 获取页面的 HTML 内容
            html_content = page.content().encode('utf-8')

            # 使用 BeautifulSoup 解析 HTML
            soup = BeautifulSoup(html_content, 'lxml')

            # 从页面源码中提取mp4链接
            video_divs = soup.find_all('video')
            if video_divs:
                video_files = []
                # 遍历视频标签
                for index, video_div in enumerate(video_divs):
                    mp4_url = video_div.get('src') or video_div.get('data-orginal-src')  # 获取视频链接
                    if mp4_url:
                        response = requests.get(mp4_url, stream=True)
                        total_length = int(response.headers.get('content-length'))
                        filename = os.path.join(download_dir, f"video_{video_id}_{index}.mp4")
                        with open(filename, 'wb') as f:
                            downloaded = 0
                            for chunk in response.iter_content(chunk_size=4096):  # 限制块的大小
                                if chunk:
                                    f.write(chunk)
                                    downloaded += len(chunk)
                                    # progress_callback(downloaded, total_length)
                                    print("Download", downloaded, total_length)

                        video_files.append(filename)

                if video_files:
                    # 合并视频
                    output_filename = os.path.join(download_dir, f"video_{title}_merged.mp4")
                    self.merge_videos(video_files, output_filename)
                    # progress_callback(f"合并后的视频已保存为 {output_filename}", "success")
                    print(f"合并后的视频已保存为 {output_filename}", "success")
                else:
                    # progress_callback("没有可用的视频链接，无法合并视频", "error")
                    print("没有可用的视频链接，无法合并视频", "error")
            else:
                # progress_callback("未找到可用的视频标签或此视频需要VIP", "error")
                print("未找到可用的视频标签或此视频需要VIP", "error")

            # 关闭浏览器
            browser.close()


youku = YoukuVideoDownloader()
info = "甜心格格"
with open("1.txt", "r", encoding="utf-8") as f:
    for index,line in enumerate(f.readlines()):
        line = line.strip()
        if line:
            youku.download_and_merge(line, info+"_"+str(index))