Python爬虫学习，批量爬取下载抖音视频

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

项目源码展示

'''
注：如果你对python感兴趣，我这有个学习Python基地，里面有很多学习资料，感兴趣的+Q群:895 797 751
# -*- 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UIDReturns: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 = 0has_more = 1i = 0share_user_url = 'https://www.douyin.com/share/user/%s' % user_idshare_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 + 1sys.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:passi = 0for 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 % uriexcept:continueshare_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, nicknamedef 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_urldef 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 = 0video_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 = 1024content_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:NoneReturns: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:NoneReturns: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()

总结
以上所述是小编给大家介绍的python3下载抖音视频的完整代码,希望对大家有所帮助。

Python爬虫学习，批量爬取下载抖音视频相关推荐

Python爬虫学习教程，批量爬取下载抖音视频
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qu ...
python自动搜索爬取下载文件-python批量爬取下载抖音视频
本文实例为大家分享了python批量爬取下载抖音视频的具体代码,供大家参考,具体内容如下 import os import requests import re import sys import a ...
python爬取抖音用户数据_python批量爬取下载抖音视频
本文实例为大家分享了python批量爬取下载抖音视频的具体代码,供大家参考,具体内容如下 import os import requests import re import sys import a ...
Python爬虫学习之爬取淘宝搜索图片
Python爬虫学习之爬取淘宝搜索图片准备工作因为淘宝的反爬机制导致Scrapy不能使用,所以我这里是使用selenium来获取网页信息,并且通过lxml框架来提取信息. selenium.lxm ...
Python爬虫学习笔记 -- 爬取糗事百科
Python爬虫学习笔记 -- 爬取糗事百科代码存放地址: https://github.com/xyls2011/python/tree/master/qiushibaike 爬取网址:https ...
为了部落来自艾泽拉斯勇士的python爬虫学习心得爬取大众点评上的各种美食数据并进行数据分析
为了希尔瓦娜斯第一个爬虫程序 csgo枪械数据先上代码基本思想问题1 问题2 爬取大众点评 URL分析第一个难题生成csv文件以及pandas库 matplotlib.pyplot库 K- ...
Python爬虫：批量爬取变形金刚图片，下载保存到本地。
本文的文字及图片来源于网络,仅供学习.交流使用,不具有任何商业用途,版权归原作者所有,如有问题请及时联系我们以作处理本文文章来自:CSDN 作者:Guapifang 其实和爬取普通数据本质一样,不过 ...
python爬虫学习之爬取超清唯美壁纸
简介壁纸的选择其实很大程度上能看出电脑主人的内心世界,有的人喜欢风景,有的人喜欢星空,有的人喜欢美女,有的人喜欢动物.然而,终究有一天你已经产生审美疲劳了,但你下定决定要换壁纸的时候,又发现网上的壁 ...
python爬虫学习一--爬取网络小说实例
最近疫情猖獗,长假憋在家里实在无聊,早上突然看了一篇python爬虫文章,当场决定试验一下,参照了一下别人的案例,自己各种踩坑捣鼓了好几个小时,终于成功最后把具体步骤和注意点分享给大家: 1.Pyth ...

Python爬虫学习，批量爬取下载抖音视频

Python爬虫学习，批量爬取下载抖音视频相关推荐

最新文章

热门文章