宜配屋

Python爬虫 批量爬取下载抖音视频代码实例

yipeiwu_com5年前Python爬虫

这篇文章主要为大家详细介绍了python批量爬取下载抖音视频，具有一定的参考价值，感兴趣的小伙伴们可以参考一下

项目源码展示：

'''
在学习过程中有什么不懂得可以加我的
python学习交流扣扣qun，934109170
群里有不错的学习教程、开发工具与电子书籍。
与你分享python企业当下人才需求及怎么从零基础学习好python，和学习什么内容。
'''
# -*- coding:utf-8 -*-
from contextlib import closing
import requests, json, re, os, sys, random
from ipaddress import ip_address
from subprocess import Popen, PIPE
import urllib
class DouYin(object):
 def __init__(self, width = 500, height = 300):
 """
 抖音App视频下载
 """
 rip = ip_address('0.0.0.0')
 while rip.is_private:
 rip = ip_address('.'.join(map(str, (random.randint(0, 255) for _ in range(4)))))
 self.headers = {
 'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
 'accept-encoding': 'gzip, deflate, br',
 'accept-language': 'zh-CN,zh;q=0.9',
 'pragma': 'no-cache',
 'cache-control': 'no-cache',
 'upgrade-insecure-requests': '1',
 'user-agent': 'Mozilla/5.0 (Linux; U; Android 5.1.1; zh-cn; MI 4S Build/LMY47V) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/53.0.2785.146 Mobile Safari/537.36 XiaoMi/MiuiBrowser/9.1.3',
 'X-Real-IP': str(rip),
 'X-Forwarded-For': str(rip),
 }
 def get_video_urls(self, user_id, type_flag='f'):
 """
 获得视频播放地址
 Parameters:
 user_id：查询的用户UID
 Returns:
 video_names: 视频名字列表
 video_urls: 视频链接列表
 nickname: 用户昵称
 """
 video_names = []
 video_urls = []
 share_urls = []
 max_cursor = 0
 has_more = 1
 i = 0
 share_user_url = 'https://www.douyin.com/share/user/%s' % user_id
 share_user = requests.get(share_user_url, headers=self.headers)
 while share_user.status_code != 200:
 share_user = requests.get(share_user_url, headers=self.headers)
 _dytk_re = re.compile(r"dytk\s*:\s*'(.+)'")
 dytk = _dytk_re.search(share_user.text).group(1)
 _nickname_re = re.compile(r'<p class="nickname">(.+?)<\/p>')
 nickname = _nickname_re.search(share_user.text).group(1)
 urllib.request.urlretrieve('https://raw.githubusercontent.com/Jack-Cherish/python-spider/master/douyin/fuck-byted-acrawler.js', 'fuck-byted-acrawler.js')
 try:
 Popen(['node', '-v'], stdout=PIPE, stderr=PIPE).communicate()
 except (OSError, IOError) as err:
 print('请先安装 node.js: https://nodejs.org/')
 sys.exit()
 user_url_prefix = 'https://www.douyin.com/aweme/v1/aweme/favorite' if type_flag == 'f' else 'https://www.douyin.com/aweme/v1/aweme/post'
 print('解析视频链接中')
 while has_more != 0:
 process = Popen(['node', 'fuck-byted-acrawler.js', str(user_id)], stdout=PIPE, stderr=PIPE)
 _sign = process.communicate()[0].decode().strip('\n').strip('\r')
 user_url = user_url_prefix + '/?user_id=%s&max_cursor=%s&count=21&aid=1128&_signature=%s&dytk=%s' % (user_id, max_cursor, _sign, dytk)
 req = requests.get(user_url, headers=self.headers)
 while req.status_code != 200:
 req = requests.get(user_url, headers=self.headers)
 html = json.loads(req.text)
 try:
 while html['aweme_list'] == []:
  i = i + 1
  sys.stdout.write('已重新链接' + str(i) + '次 (若超过100次，请ctrl+c强制停止再重来)' + '\r')
  sys.stdout.flush()
  process = Popen(['node', 'fuck-byted-acrawler.js', str(user_id)], stdout=PIPE, stderr=PIPE)
  _sign = process.communicate()[0].decode().strip('\n').strip('\r')
  user_url = user_url_prefix + '/?user_id=%s&max_cursor=%s&count=21&aid=1128&_signature=%s&dytk=%s' % (user_id, max_cursor, _sign, dytk)
  req = requests.get(user_url, headers=self.headers)
  while req.status_code != 200:
  req = requests.get(user_url, headers=self.headers)
  html = json.loads(req.text)
 except:
 pass
 i = 0
 for each in html['aweme_list']:
 try:
  url = 'https://aweme.snssdk.com/aweme/v1/play/?video_id=%s&line=0&ratio=720p&media_type=4&vr_type=0&test_cdn=None&improve_bitrate=0'
  uri = each['video']['play_addr']['uri']
  video_url = url % uri
 except:
  continue
 share_desc = each['share_info']['share_desc']
 if os.name == 'nt':
  for c in r'\/:*?"<>|':
  nickname = nickname.replace(c, '').strip().strip('\.')
  share_desc = share_desc.replace(c, '').strip()
 share_id = each['aweme_id']
 if share_desc in ['抖音-原创音乐短视频社区', 'TikTok', '']:
  video_names.append(share_id + '.mp4')
 else:
  video_names.append(share_id + '-' + share_desc + '.mp4')
 share_urls.append(each['share_info']['share_url'])
 video_urls.append(video_url)
 max_cursor = html['max_cursor']
 has_more = html['has_more']
 return video_names, video_urls, share_urls, nickname
 def get_download_url(self, video_url, watermark_flag):
 """
 获得带水印的视频播放地址
 Parameters:
 video_url：带水印的视频播放地址
 Returns:
 download_url: 带水印的视频下载地址
 """
 # 带水印视频
 if watermark_flag == True:
 download_url = video_url.replace('/play/', '/playwm/')
 # 无水印视频
 else:
 download_url = video_url.replace('/playwm/', '/play/')
 return download_url
 def video_downloader(self, video_url, video_name, watermark_flag=False):
 """
 视频下载
 Parameters:
 video_url: 带水印的视频地址
 video_name: 视频名
 watermark_flag: 是否下载带水印的视频
 Returns:
 无
 """
 size = 0
 video_url = self.get_download_url(video_url, watermark_flag=watermark_flag)
 with closing(requests.get(video_url, headers=self.headers, stream=True)) as response:
 chunk_size = 1024
 content_size = int(response.headers['content-length'])
 if response.status_code == 200:
 sys.stdout.write(' [文件大小]:%0.2f MB\n' % (content_size / chunk_size / 1024))
 with open(video_name, 'wb') as file:
  for data in response.iter_content(chunk_size = chunk_size):
  file.write(data)
  size += len(data)
  file.flush()
  sys.stdout.write(' [下载进度]:%.2f%%' % float(size / content_size * 100) + '\r')
  sys.stdout.flush()
 def run(self):
 """
 运行函数
 Parameters:
 None
 Returns:
 None
 """
 self.hello()
 print('搜索api需要登录，暂时使用UID下载\n分享用户页面，用浏览器打开短链接，原始链接中/share/user/后的数字即是UID')
 user_id = input('请输入ID (例如95006183):')
 user_id = user_id if user_id else '95006183'
 watermark_flag = input('是否下载带水印的视频 (0-否(默认), 1-是):')
 watermark_flag = watermark_flag if watermark_flag!='' else '0'
 watermark_flag = bool(int(watermark_flag))
 type_flag = input('f-收藏的(默认), p-上传的:')
 type_flag = type_flag if type_flag!='' else 'f'
 save_dir = input('保存路径 (例如"E:/Download/", 默认"./Download/"):')
 save_dir = save_dir if save_dir else "./Download/"
 video_names, video_urls, share_urls, nickname = self.get_video_urls(user_id, type_flag)
 nickname_dir = os.path.join(save_dir, nickname)
 if not os.path.exists(save_dir):
 os.makedirs(save_dir)
 if nickname not in os.listdir(save_dir):
 os.mkdir(nickname_dir)
 if type_flag == 'f':
 if 'favorite' not in os.listdir(nickname_dir):
 os.mkdir(os.path.join(nickname_dir, 'favorite'))
 print('视频下载中:共有%d个作品!\n' % len(video_urls))
 for num in range(len(video_urls)):
 print(' 解析第%d个视频链接 [%s] 中，请稍后!\n' % (num + 1, share_urls[num]))
 if '\\' in video_names[num]:
 video_name = video_names[num].replace('\\', '')
 elif '/' in video_names[num]:
 video_name = video_names[num].replace('/', '')
 else:
 video_name = video_names[num]
 video_path = os.path.join(nickname_dir, video_name) if type_flag!='f' else os.path.join(nickname_dir, 'favorite', video_name)
 if os.path.isfile(video_path):
 print('视频已存在')
 else:
 self.video_downloader(video_urls[num], video_path, watermark_flag)
 print('\n')
 print('下载完成!')
 def hello(self):
 """
 打印欢迎界面
 Parameters:
 None
 Returns:
 None
 """
 print('*' * 100)
 print('\t\t\t\t抖音App视频下载小助手')
 print('\t\t作者:Jack Cui、steven7851')
 print('*' * 100)
if __name__ == '__main__':
 douyin = DouYin()
 douyin.run()

运行结果：

爬取结果截图

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持【听图阁-专注于Python设计】。

返回列表

上一篇：Python字符转换

下一篇：PHP生成静态页面详解

相关文章

Python打印scrapy蜘蛛抓取树结构的方法

本文实例讲述了Python打印scrapy蜘蛛抓取树结构的方法。分享给大家供大家参考。具体如下： 通过下面这段代码可以一目了然的知道scrapy的抓取页面结构，调用也非常简单 #!/...

Python基于BeautifulSoup和requests实现的爬虫功能示例

Python基于BeautifulSoup和requests实现的爬虫功能示例

本文实例讲述了Python基于BeautifulSoup和requests实现的爬虫功能。分享给大家供大家参考，具体如下： 爬取的目标网页：http://www.qianlima.com...

python爬虫URL重试机制的实现方法(python2.7以及python3.5)

应用场景： 状态不是200的URL重试多次 代码比较简单还有部分注释 python2.7实现： # -*-coding:utf-8-*- """ ayou """ import...

Python爬虫抓取手机APP的传输数据

Python爬虫抓取手机APP的传输数据

大多数APP里面返回的是json格式数据，或者一堆加密过的数据 。这里以超级课程表APP为例，抓取超级课程表里用户发的话题。 1、抓取APP数据包 方法详细可以参考这篇博文：Fiddle...

零基础写python爬虫之使用urllib2组件抓取网页内容

零基础写python爬虫之使用urllib2组件抓取网页内容

版本号：Python2.7.5，Python3改动较大，各位另寻教程。所谓网页抓取，就是把URL地址中指定的网络资源从网络流中读取出来，保存到本地。 类似于使用程序模拟IE浏览器...

© YiPeiWu.com 【宜配屋】 粤ICP备17031333号

Powered By Z-BlogPHP. Theme by TOYEAN.