Python爬虫获取百度图片+重命名+帧差法获取关键帧

（清库存）

爬虫获取图片

# 图片在当前目录下生成

import requests
import re

num = 0
numPicture = 0
file = ''
List = []


def dowmloadPicture(html, keyword):
    global num
    # t =0
    pic_url = re.findall('"objURL":"(.*?)",', html, re.S)  # 先利用正则表达式找到图片url

    print('找到关键词:' + keyword + '的图片，即将开始下载图片...')
    for each in pic_url:
        print('正在下载第' + str(num + 1) + '张图片，图片地址:' + str(each))
        try:
            if each is not None:
                pic = requests.get(each, timeout=7)
            else:
                continue
        except BaseException:
            print('错误，当前图片无法下载')
            continue
        else:
            string = './' + keyword + '_' + str(num) + '.jpg'    # 可改成绝对地址
            fp = open(string, 'wb')
            fp.write(pic.content)
            fp.close()
            num += 1
        # if num >= numPicture:
        #     return


if __name__ == '__main__':  # 主函数入口
    header = {'content-type': 'application/json','User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:22.0) Gecko/20100101 Firefox/22.0'}
    word = input("请输入搜索关键词: ")

    num1 = 0
    while 1:
        url = 'https://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=' + word + '&pn='
        r = requests.get(url + str(num1), headers=header, allow_redirects=False)
        r.encoding = 'utf-8'
        dowmloadPicture(r.text, word)
        num1 = num1+20

文件重命名

图片在images文件夹内

# ######################最终版##################### #


import os


class BatchRename():
    '''
    批量重命名文件夹中的图片文件
    '''

    def __init__(self):
        self.path = './images/'  # 表示需要命名处理的文件夹

    def rename(self):
        filelist = os.listdir(self.path)  # 获取文件路径
        total_num = len(filelist)  # 获取文件长度（个数）
        i = 1  # 表示文件的命名是从1开始的
        for item in filelist:
            if item.endswith('.jpg'):  # 初始的图片的格式为jpg格式的（或者源文件是png格式及其
                # 他格式，后面的转换格式就可以调整为自己需要的格式即可）
                src = os.path.join(os.path.abspath(self.path), item)
                dst = os.path.join(os.path.abspath(self.path), 'pachong_' + str(i) + '.jpg')  # 处理后的格式也为jpg格式的，当然这里可以改成png格式
                # dst = os.path.join(os.path.abspath(self.path), '0000' + format(str(i), '0>3s') + '.jpg')    这种情况下的命名格式为0000000.jpg形式，可以自主定义想要的格式
                try:
                    os.rename(src, dst)
                    print('converting %s to %s ...' % (src, dst))
                    i = i + 1
                except:
                    continue
        print('total %d to rename & converted %d jpgs' % (total_num, i))


if __name__ == '__main__':
    demo = BatchRename()
    demo.rename()

帧差法获取关键帧

下载的文件夹在bilibili
帧差法 结果在bilibili_result

# -*- coding: utf-8 -*-

import cv2
import os
import time
import operator  # 内置操作符函数接口（后面排序用到）
import numpy as np
import matplotlib.pyplot as plt
from scipy.signal import argrelextrema  # 极值点


def smooth(x, window_len=13, window='hanning'):
    """使用具有所需大小的窗口使数据平滑。
    """
    print(len(x), window_len)

    s = np.r_[2 * x[0] - x[window_len:1:-1],
              x, 2 * x[-1] - x[-1:-window_len:-1]]
    # print(len(s))

    if window == 'flat':  # moving average平移
        w = np.ones(window_len, 'd')
    else:
        w = getattr(np, window)(window_len)
    y = np.convolve(w / w.sum(), s, mode='same')
    return y[window_len - 1:-window_len + 1]


class Frame:
    """用于保存有关每个帧的信息
    """

    def __init__(self, id, diff):
        self.id = id
        self.diff = diff

    def __lt__(self, other):
        if self.id == other.id:
            return self.id < other.id
        return self.id < other.id

    def __gt__(self, other):
        return other.__lt__(self)

    def __eq__(self, other):
        return self.id == other.id and self.id == other.id

    def __ne__(self, other):
        return not self.__eq__(other)


def rel_change(a, b):
    x = (b - a) / max(a, b)
    print(x)
    return x


def getEffectiveFrame(videopath, dirfile):
    # 如果文件目录不存在则创建目录
    if not os.path.exists(dirfile):
        os.makedirs(dirfile)
    (filepath, tempfilename) = os.path.split(videopath)  # 分离路径和文件名
    (filename, extension) = os.path.splitext(tempfilename)  # 区分文件的名字和后缀
    # Setting fixed threshold criteria设置固定阈值标准
    USE_THRESH = False
    # fixed threshold value固定阈值
    THRESH = 0.6
    # Setting fixed threshold criteria设置固定阈值标准
    USE_TOP_ORDER = False
    # Setting local maxima criteria设置局部最大值标准
    USE_LOCAL_MAXIMA = True
    # Number of top sorted frames排名最高的帧数
    NUM_TOP_FRAMES = 50
    # smoothing window size平滑窗口大小
    len_window = int(10) # 50

    print("target video :" + videopath)
    print("frame save directory: " + dirfile)
    # load video and compute diff between frames加载视频并计算帧之间的差异
    cap = cv2.VideoCapture(str(videopath))
    curr_frame = None
    prev_frame = None
    frame_diffs = []
    frames = []
    success, frame = cap.read()
    i = 0
    while (success):
        luv = cv2.cvtColor(frame, cv2.COLOR_BGR2LUV)
        curr_frame = luv
        if curr_frame is not None and prev_frame is not None:
            # logic here
            diff = cv2.absdiff(curr_frame, prev_frame)  # 获取差分图
            diff_sum = np.sum(diff)
            diff_sum_mean = diff_sum / (diff.shape[0] * diff.shape[1])  # 平均帧
            frame_diffs.append(diff_sum_mean)
            frame = Frame(i, diff_sum_mean)
            frames.append(frame)
        prev_frame = curr_frame
        i = i + 1
        success, frame = cap.read()
    cap.release()

    # compute keyframe
    keyframe_id_set = set()
    if USE_TOP_ORDER:
        # sort the list in descending order以降序对列表进行排序
        frames.sort(key=operator.attrgetter("diff"), reverse=True)  # 排序operator.attrgetter
        for keyframe in frames[:NUM_TOP_FRAMES]:
            keyframe_id_set.add(keyframe.id)
    if USE_THRESH:
        print("Using Threshold")  # 使用阈值
        for i in range(1, len(frames)):
            if (rel_change(np.float(frames[i - 1].diff), np.float(frames[i].diff)) >= THRESH):
                keyframe_id_set.add(frames[i].id)
    if USE_LOCAL_MAXIMA:
        print("Using Local Maxima")  # 使用局部极大值
        diff_array = np.array(frame_diffs)
        sm_diff_array = smooth(diff_array, len_window)  # 平滑
        frame_indexes = np.asarray(argrelextrema(sm_diff_array, np.greater))[0]  # 找极值
        for i in frame_indexes:
            keyframe_id_set.add(frames[i - 1].id)  # 记录极值帧数

        plt.figure(figsize=(40, 20))
        plt.locator_params("x", nbins=100)
        # stem 绘制离散函数，polt是连续函数
        plt.stem(sm_diff_array, linefmt='-', markerfmt='o', basefmt='--', label='sm_diff_array')
        plt.savefig(dirfile + filename + '_plot.png')

    # save all keyframes as image将所有关键帧另存为图像
    cap = cv2.VideoCapture(str(videopath))
    curr_frame = None
    keyframes = []
    success, frame = cap.read()
    idx = 0
    while (success):
        if idx in keyframe_id_set:
            name = filename + '_' + str(idx) + ".jpg"
            cv2.imwrite(dirfile + name, frame)
            keyframe_id_set.remove(idx)
        idx = idx + 1
        success, frame = cap.read()
    cap.release()


if __name__ == "__main__":
    print("[INFO]Effective Frame.")
    start = time.time()
    videos_path = 'bilibili/'
    outfile = 'bilibili_result/'  # 处理完的帧
    video_files = [os.path.join(videos_path, video_file) for video_file in os.listdir(videos_path)]
    #
    for video_file in video_files:
        getEffectiveFrame(video_file, outfile)
    print("[INFO]Extract Result time: ", time.time() - start)