用python制作词云视频详解

Package         Version
--------------- ---------
baidu-aip       2.2.18.0
jieba           0.42.1
moviepy         1.0.3
numpy           1.20.2
opencv-python   4.5.1.48
Pillow          8.2.0
requests        2.25.1
wordcloud       1.8.1
you-get         0.4.1520

    def get_cid(cls, bv):
        url = "https://api.bilibili.com/x/web-interface/view?bvid=" + str(bv)
        response = requests.get(url)
        dirt = json.loads(response.text)
        aid = dirt['data']['cid']
        return str(aid)
    def get_barrage(cls, bv, to_file_path):
        headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36",
        }
        cid = cls.get_cid(bv)
        response = requests.get("https://api.bilibili.com/x/v1/dm/list.so?oid=" + cid, headers=headers)
        html_doc = response.content.decode('utf-8')
        regex = re.compile("<d.*?>(.*?)</d>")
        DanMu = regex.findall(html_doc)
        with open(to_file_path, "w", encoding="utf_8")as f:
            for i in DanMu:
                f.write(i)
                f.write("\n")

# 获取视频信息
you-get -i https://www.bilibili.com/video/BV1f4411M7QC
# 下载视频
you-get --format=flv -o E:\Desktop\output https://www.bilibili.com/video/BV1f4411M7QC

    def cut_video(cls, origin_file_path, to_file_path, start, end):
        """
        视频剪辑
        :param origin_file_path: 原视频文件路径
        :param to_file_path: 保存路径
        :param start: 起始时间点
        :param end: 结束时间点
        """
        clip = VideoFileClip(origin_file_path).subclip(start, end)
        clip.write_videofile(to_file_path)
    def cut_audio(cls, origin_file_path, to_file_path, start, end):
        """
        音频剪辑
        :param origin_file_path: 原视频文件路径
        :param to_file_path: 保存路径
        :param start: 起始时间点
        :param end: 结束时间点
        """
        clip = AudioFileClip(origin_file_path).subclip(start, end)
        clip.write_audiofile(to_file_path)
    def get_audio_from_video(cls, video_file_path, to_file_path):
        """
        音频提取
        :param video_file_path: 视频文件路径
        :param to_file_path: 音频文件路径
        """
        video = VideoFileClip(video_file_path)
        video.audio.write_audiofile(to_file_path)

    def split(cls, from_file_path, to_folder_path, frames=0):
        """
        视频按帧读取并保存
        :param from_file_path: 视频路径
        :param to_folder_path: 保存路径
        :param frames: 保存帧数(张数)，为0则保存所有帧
        """
        vc = cv2.VideoCapture(from_file_path)    # cv2打开视频文件
        frames_count = vc.get(7)    # 获取视频总帧数
        c = 0
        if vc.isOpened():
            ret, frame = vc.read()          # 按帧读取视频
        else:
            ret = False
        while ret:
            if 0 < frames == c:
                break
            ret, frame = vc.read()  # 读取每一视频帧，并保存至图片中
            cv2.imwrite(os.path.join(to_folder_path, '{}.jpg'.format(c)), frame)
            c += 1
            if c == frames_count - 1:
                break
            print('第 {} 张图片存放成功！'.format(c))

    def binary_option_cv2(cls, from_file_path, to_file_path):
        """
        图片二值化并保存(使用cv2)
        :param from_file_path: 原图路径
        :param to_file_path: 二值化图路径
        """
        img = cv2.imread(from_file_path)
        gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
        new_gray = np.uint8((255 * (gray / 255.0) ** 1.4))
        dst = cv2.adaptiveThreshold(new_gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 15, 1)
        cv2.medianBlur(dst, 5)
        cv2.imwrite(to_file_path, dst)
    def binary_option_baidu(cls, from_file_path, to_file_path):
        """
        图片二值化并保存(使用百度人像分割)
        :param from_file_path: 原图路径
        :param to_file_path: 二值化图路径
        """
        def get_file_content(filePath):
            with open(filePath, 'rb') as fp:
                return fp.read()
        height, width, bgr = cv2.imread(from_file_path).shape
        image = get_file_content(from_file_path)
        cls.client.bodySeg(image)
        res = cls.client.bodySeg(image)
        labelmap = base64.b64decode(res['labelmap'])
        labelimg = np.frombuffer(labelmap, np.uint8)  # 转化为np数组 0-255
        labelimg = cv2.imdecode(labelimg, 1)
        labelimg = cv2.resize(labelimg, (width, height), interpolation=cv2.INTER_NEAREST)
        img_new = np.where(labelimg == 1, 255, labelimg)  # 将 1 转化为 255
        cv2.imwrite(to_file_path, img_new)

    def joint(cls, origin_folder, word_cloud_folder, to_file_path):
        """
        批量拼接图片并合成视频
        :param origin_folder: 原图文件夹
        :param word_cloud_folder: 词云图片文件夹
        :param to_file_path: 保存路径
        """
        num_list = [int(str(i).split('.')[0]) for i in os.listdir(origin_folder)]
        fps = 30  # 视频帧率，需要根据原视频帧率做调整
        height, width, _ = cv2.imread(os.path.join(origin_folder, '{}.jpg'.format(num_list[0]))).shape  # 视频高度和宽度
        width = width * 2
        # 创建一个写入操作;
        video_writer = cv2.VideoWriter(to_file_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (width, height))
        for i in sorted(num_list):
            i = '{}.jpg'.format(i)
            ori_jpg = os.path.join(origin_folder, str(i))
            word_jpg = os.path.join(word_cloud_folder, str(i))
            # com_jpg = os.path.join(Composite_path,str(i))
            ori_arr = cv2.imread(ori_jpg)
            word_arr = cv2.imread(word_jpg)
            # 利用 Numpy 进行拼接
            com_arr = np.hstack((ori_arr, word_arr))
            video_writer.write(com_arr)  # 将每一帧画面写入视频流中
            print("{}写入视频流成功".format(ori_jpg))

    def set_audio_for_video(cls, video_file_path, audio_file_path, to_file_path):
        """
        音视频合并
        :param video_file_path: 视频文件路径
        :param audio_file_path: 音频文件路径
        :param to_file_path: 保存路径
        """
        video = VideoFileClip(video_file_path)
        audio = AudioFileClip(audio_file_path)
        new_video = video.set_audio(audio)
        new_video.write_videofile(to_file_path)