需要ffmpeg、该路径

    1. # -*- coding:utf-8 -*-
    2. # author: LIUWENYU
    3. # datetime: 2020/11/2 15:39
    4. # describe:
    5. import requests
    6. from fake_useragent import UserAgent
    7. from lxml import etree
    8. import re
    9. import time
    10. import os
    11. import subprocess
    13. class Bilib():
    14.     def __init__(self,search_name=None):
    15.         """
    16.         :param search_name: 查询关键词
    17.         其他参数说明：
    18.         keyword：关键词 例如：西游记
    19.         order: totalrank 综合排序，click 最多点击，pubdate 最新发布，dm 最多弹幕，stow 最多收藏
    20.         duration：0 全部时长，1 10分钟以下，2 10-30分钟，3 30-60分钟，4 60分钟以上
    21.         tids_1: 0 全部分区，1 动画，13 番剧，167 国创，3 音乐，129 舞蹈。。等等 这个选项有点多
    22.         page：1 第一页，2 第二页
    23.         eg：https://search.bilibili.com/video?keyword=西游记&order=totalrank&duration=1&tids_1=0&page=1
    24.         """
    25.         # 关键字
    26.         self.search_name = search_name
    27.         # 请求头
    28.         self.headers = {"User-Agent": UserAgent().random}
    29.         # 下载视频请求头
    30.         self.downloadVideoHeaders = {
    31.             'referer': 'https://www.bilibili.com/video/BV1WJ411e76L?from=search',
    32.             'sec-ch-ua': '"\\Not;A\"Brand";v="99", "Google Chrome";v="85", "Chromium";v="85"',
    33.             'sec-ch-ua-mobile': '?0',
    34.             'sec-fetch-dest': 'empty',
    35.             'sec-fetch-mode': 'cors',
    36.             'sec-fetch-site': 'cross-site',
    37.             'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.83 Safari/537.36'
    38.         }
    39.         self.link_list = []
    41.     # 获取网页源码
    42.     def get_html(self,url):
    43.         result_url = requests.get(url=url,headers=self.headers)
    44.         if result_url.status_code == 200:
    45.             return result_url.text
    46.         else:
    47.             print('Get Html Code is False:%s,没有查询到相关视频' % result_url.status_code)
    48.             return
    50.     # 获取视频页数
    51.     def get_page_count(self,html):
    52.         # 对网页数据进行解析，提取需要的视频链接
    53.         result_etree = etree.HTML(html)
    54.         page_num = result_etree.xpath('//li[contains(@class,"page-item last")]/button/text()')
    55.         page_num = re.findall(r'\d+',page_num[0])[0]
    56.         return page_num
    58.     # 获取视频地址
    59.     def get_link(self,html):
    60.         if not html: return
    61.         # 对网页数据进行解析，提取需要的视频链接
    62.         result_etree = etree.HTML(html)
    63.         link_list_result = result_etree.xpath('//*[@id="video-list"]/ul/li/a/@href')
    64.         for item in link_list_result:
    65.             self.link_list.append(item)
    66.         return self.link_list
    68.     # 根据视频地址，获取视频
    69.     def get_video(self,video_count,page_num_t):
    70.         # 存放路径
    71.         path = os.path.split(os.path.realpath(__file__))[0] + os.sep + 'video'
    72.         if not os.path.exists(path):
    73.             os.makedirs(path)
    75.         # 合并后的视频位置
    76.         path_new = os.path.split(os.path.realpath(__file__))[0] + os.sep + 'videoNew'
    77.         if not os.path.exists(path_new):
    78.             os.makedirs(path_new)
    80.         # 下载数量
    81.         if 0 < video_count < page_num_t * 20:
    82.             for i in range(len(self.link_list))[:video_count]:
    83.                 result_video = requests.get(url='http:' + self.link_list[i], headers=self.headers).text
    84.                 video_url = re.findall(r'"base_url":"(.*?)"', result_video)  # 匹配视频，音频地址
    85.                 video_name = etree.HTML(result_video).xpath('//*[@id="viewbox_report"]/h1/span/text()')
    86.                 video_name = '-'.join(re.findall(r'[\w]+', video_name[0]))  # 视频名称
    87.                 print(f'{video_name}---下载中...')
    88.                 # 存视频
    89.                 info_s = requests.get(url=video_url[0], headers=self.downloadVideoHeaders).content
    90.                 with open(f'{path}{os.sep}{video_name}1.mp4', 'wb') as f:
    91.                     f.write(info_s)
    92.                 # 存音频
    93.                 info_y = requests.get(url=video_url[-1], headers=self.downloadVideoHeaders).content
    94.                 with open(f'{path}{os.sep}{video_name}2.mp4', 'wb') as f:
    95.                     f.write(info_y)
    96.                 time.sleep(1)
    97.                 filename = f'{path_new}{os.sep}{video_name}.mp4'
    98.                 yin_video = f'{path}{os.sep}{video_name}1.mp4'
    99.                 shi_video = f'{path}{os.sep}{video_name}2.mp4'
    100.                 # 合并音视频
    101.                 self.video_add_mp4(filename,yin_video,shi_video)
    102.                 print(f'{video_name}---下载完成...')
    104.         # 下载全部视频
    105.         if video_count == 0:
    106.             for i in self.link_list:
    107.                 result_video = requests.get(url='http:' + self.link_list[i],headers=self.headers).text
    108.                 video_url = re.findall(r'"base_url":"(.*?)"',result_video)  # 匹配视频，音频地址
    109.                 video_name = etree.HTML(result_video).xpath('//*[@id="viewbox_report"]/h1/span/text()')
    110.                 video_name = '-'.join(re.findall(r'[\w]+', video_name[0]))  # 视频名称
    111.                 print(video_name)
    112.                 # 存视频
    113.                 info_s = requests.get(url=video_url[0], headers=self.downloadVideoHeaders).content
    114.                 with open(f'{path}{os.sep}{video_name}1.mp4', 'wb') as f:
    115.                     f.write(info_s)
    116.                 # 存音频
    117.                 info_y = requests.get(url=video_url[-1], headers=self.downloadVideoHeaders).content
    118.                 with open(f'{path}{os.sep}{video_name}2.mp4', 'wb') as f:
    119.                     f.write(info_y)
    121.     # 视频 + 音频 合并
    122.     def video_add_mp4(self,filename,yin_video,shi_videop):
    123.         cmd = f'X:\\bili\\video\\FFmpeg\\ffmpeg -i {yin_video} -i {shi_videop} -acodec copy -vcodec copy {filename}'
    124.         print(cmd)
    125.         subprocess.call(cmd, shell=True)
    127.     def main(self):
    128.         while True:
    129.             search_name = input('请输入查询视频关键字：')
    130.             # search_name = '西游记'
    131.             if not search_name:
    132.                 continue
    133.             break
    135.         # 页数
    136.         url = f"https://search.bilibili.com/video?keyword={search_name}&order=totalrank&duration=1&tids_1=0"
    137.         html = self.get_html(url=url)
    138.         page_num = self.get_page_count(html)
    139.         print(f'相关视频有{page_num}页,每页视频大概20个')
    140.         while True:
    141.             page_num_t = int(input('请选择下载几页：'))
    142.             if page_num_t > int(page_num):
    143.                 print('输入页码有误，请重新输入')
    144.                 continue
    145.             break
    147.         # 视频数量
    148.         while True:
    149.             print('数量规则：0<数量<20*页数，0表示选择页数的全部视频')
    150.             video_count = int(input('请输入下载视频数量：'))
    151.             if video_count < 0 or video_count > page_num_t *20 :
    152.                 print('输入数量有误，请重新输入')
    153.                 continue
    154.             break
    156.         # 地址
    157.         links = ''
    158.         for i in range(1,page_num_t+1):
    159.             url_t = f"https://search.bilibili.com/video?keyword={search_name}&order=totalrank&duration=1&tids_1=0&page={i}"
    160.             print(url_t)
    161.             html = self.get_html(url=url_t)
    162.             links = self.get_link(html)
    163.             print(f'第{i}页,视频地址获取完成')
    164.             time.sleep(2)   # 睡眠一会，访问频率过快，会被认为网络爬虫，将IP地址关进小黑屋
    165.         print(f'总共获取视频地址数量{len(links)}')
    167.         # 下载视频
    168.         self.get_video(video_count,page_num_t)
    170. if __name__ == '__main__':
    171.     b = Bilib()
    172.     b.main()