简介

抖音，是一款可以拍短视频的音乐创意短视频社交软件，该软件于2016年9月上线，是一个专注年轻人的15秒音乐短视频社区。用户可以通过这款软件选择歌曲，拍摄15秒的音乐短视频，形成自己的作品。此APP已在Android各大应用商店和APP Store均有上线。

今天咱们就用Python爬取抖音视频

想要学习Python？Python学习交流群：683380553满足你的需求，资料都已经上传群文件流，可以自行下载！

准备：

环境：Python3.6+Windows

IDE：你开行就好，喜欢用哪个就用哪个

模块：

1 from splinter.driver.webdriver.chrome import Options, Chrome
2 from splinter.browser import Browser
3 from contextlib import closing
4 import requests, json, time, re, os, sys, time
5 from bs4 import BeautifulSoup

获得视频播放地址

查询的用户ID
视频名字列表
视频链接列表
用户昵称

def get_video_urls(self, user_id):+        video_names = []
+        video_urls = []
+        unique_id = ''
+        while unique_id != user_id:
+            search_url = 'https://api.amemv.com/aweme/v1/discover/search/?cursor=0&keyword=%s&count=10&type=1&retry_type=no_retry&iid=17900846586&device_id=34692364855&ac=wifi&channel=xiaomi&aid=1128&app_name=aweme&version_code=162&version_name=1.6.2&device_platform=android&ssmix=a&device_type=MI+5&device_brand=Xiaomi&os_api=24&os_version=7.0&uuid=861945034132187&openudid=dc451556fc0eeadb&manifest_version_code=162&resolution=1080*1920&dpi=480&update_version_code=1622' % user_id
+            req = requests.get(url = search_url, verify = False)
+            html = json.loads(req.text)
+            aweme_count = html['user_list'][0]['user_info']['aweme_count']
+            uid = html['user_list'][0]['user_info']['uid']
+            nickname = html['user_list'][0]['user_info']['nickname']
+            unique_id = html['user_list'][0]['user_info']['unique_id']
+        user_url = 'https://www.douyin.com/aweme/v1/aweme/post/?user_id=%s&max_cursor=0&count=%s' % (uid, aweme_count)
+        req = requests.get(url = user_url, verify = False)
+        html = json.loads(req.text)
+        i = 1
+        for each in html['aweme_list']:
+            share_desc = each['share_info']['share_desc']
+            if '抖音-原创音乐短视频社区' == share_desc:
+                video_names.append(str(i) + '.mp4')
+                i += 1
+            else:
+                video_names.append(share_desc + '.mp4')
+            video_urls.append(each['share_info']['share_url'])
+
+        return video_names, video_urls, nickname

获得带水印的视频播放地址

video_url：带水印的视频播放地址
download_url: 带水印的视频下载地址

def get_download_url(self, video_url):+        req = requests.get(url = video_url, verify = False)
+        bf = BeautifulSoup(req.text, 'lxml')
+        script = bf.find_all('script')[-1]
+        video_url_js = re.findall('var data = \[(.+)\];', str(script))[0]
+        video_html = json.loads(video_url_js)
+        download_url = video_html['video']['play_addr']['url_list'][0]
+        return download_url

视频下载

video_url: 带水印的视频地址
video_name: 视频名
watermark_flag: 是否下载不带水印的视频

def video_downloader(self, video_url, video_name, watermark_flag=True):
+        """
+        视频下载
+        Parameters:
+            video_url: 带水印的视频地址
+            video_name: 视频名
+            watermark_flag: 是否下载不带水印的视频
+        Returns:
+            无
+        """
+        size = 0
+        if watermark_flag == True:
+            video_url = self.remove_watermark(video_url)
+        else:
+            video_url = self.get_download_url(video_url)
+        with closing(requests.get(video_url, stream=True, verify = False)) 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()

获得无水印的视频播放地址

def remove_watermark(self, video_url):
+        """
+        获得无水印的视频播放地址
+        Parameters:
+            video_url: 带水印的视频地址
+        Returns:
+            无水印的视频下载地址
+        """
+        self.driver.visit('http://douyin.iiilab.com/')
+        self.driver.find_by_tag('input').fill(video_url)
+        self.driver.find_by_xpath('//button[@class="btn btn-default"]').click()
+        html = self.driver.find_by_xpath('//div[@class="thumbnail"]/div/p')[0].html
+        bf = BeautifulSoup(html, 'lxml')
+        return bf.find('a').get('href')

下载视频

def run(self):
+        """
+        运行函数
+        Parameters:
+            None
+        Returns:
+            None
+        """
+        self.hello()
+        user_id = input('请输入ID(例如40103580):')
+        video_names, video_urls, nickname = self.get_video_urls(user_id)
+        if nickname not in os.listdir():
+            os.mkdir(nickname)
+        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, video_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]
+            self.video_downloader(video_urls[num], os.path.join(nickname, video_name))
+            print('\n')
+
+        print('下载完成!')

全部代码

+# -*- coding:utf-8 -*-想要学习Python？Python学习交流群：683380553满足你的需求，资料都已经上传群文件流，可以自行下载！
+from splinter.driver.webdriver.chrome import Options, Chrome
+from splinter.browser import Browser
+from contextlib import closing
+import requests, json, time, re, os, sys, time
+from bs4 import BeautifulSoup
+class DouYin(object):def __init__(self, width = 500, height = 300):
+        """
+        抖音App视频下载
+        """
+        # 无头浏览器
+        chrome_options = Options()
+        chrome_options.add_argument('user-agent="Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"')
+        self.driver = Browser(driver_name='chrome', executable_path='D:/chromedriver', options=chrome_options, headless=True)
+def get_video_urls(self, user_id):
+        """
+        获得视频播放地址
+        Parameters:
+            user_id：查询的用户ID
+        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 = []
+        unique_id = ''
+        while unique_id != user_id:
+            search_url = 'https://api.amemv.com/aweme/v1/discover/search/?cursor=0&keyword=%s&count=10&type=1&retry_type=no_retry&iid=17900846586&device_id=34692364855&ac=wifi&channel=xiaomi&aid=1128&app_name=aweme&version_code=162&version_name=1.6.2&device_platform=android&ssmix=a&device_type=MI+5&device_brand=Xiaomi&os_api=24&os_version=7.0&uuid=861945034132187&openudid=dc451556fc0eeadb&manifest_version_code=162&resolution=1080*1920&dpi=480&update_version_code=1622' % user_id
+            req = requests.get(url = search_url, verify = False)
+            html = json.loads(req.text)
+            aweme_count = html['user_list'][0]['user_info']['aweme_count']
+            uid = html['user_list'][0]['user_info']['uid']
+            nickname = html['user_list'][0]['user_info']['nickname']
+            unique_id = html['user_list'][0]['user_info']['unique_id']
+        user_url = 'https://www.douyin.com/aweme/v1/aweme/post/?user_id=%s&max_cursor=0&count=%s' % (uid, aweme_count)
+        req = requests.get(url = user_url, verify = False)
+        html = json.loads(req.text)
+        i = 1
+        for each in html['aweme_list']:
+            share_desc = each['share_info']['share_desc']
+            if '抖音-原创音乐短视频社区' == share_desc:
+                video_names.append(str(i) + '.mp4')
+                i += 1
+            else:
+                video_names.append(share_desc + '.mp4')
+            video_urls.append(each['share_info']['share_url'])
+
+        return video_names, video_urls, nickname
+def get_download_url(self, video_url):
+        """
+        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
+        """
+        req = requests.get(url = video_url, verify = False)
+        bf = BeautifulSoup(req.text, 'lxml')
+        script = bf.find_all('script')[-1]
+        video_url_js = re.findall('var data = \[(.+)\];', str(script))[0]
+        video_html = json.loads(video_url_js)
+        download_url = video_html['video']['play_addr']['url_list'][0]
+        return download_url
+def video_downloader(self, video_url, video_name, watermark_flag=True):
+        """
+        视频下载
+        Parameters:
+            video_url: 带水印的视频地址
+            video_name: 视频名
+            watermark_flag: 是否下载不带水印的视频
+        Returns:
+            无
+        """
+        size = 0
+        if watermark_flag == True:
+            video_url = self.remove_watermark(video_url)
+        else:
+            video_url = self.get_download_url(video_url)
+        with closing(requests.get(video_url, stream=True, verify = False)) 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 remove_watermark(self, video_url):
+        """
+        获得无水印的视频播放地址
+        Parameters:
+            video_url: 带水印的视频地址
+        Returns:
+            无水印的视频下载地址
+        """
+        self.driver.visit('http://douyin.iiilab.com/')
+        self.driver.find_by_tag('input').fill(video_url)
+        self.driver.find_by_xpath('//button[@class="btn btn-default"]').click()
+        html = self.driver.find_by_xpath('//div[@class="thumbnail"]/div/p')[0].html
+        bf = BeautifulSoup(html, 'lxml')
+        return bf.find('a').get('href')
+def run(self):
+        """
+        运行函数
+        Parameters:
+            None
+        Returns:
+            None
+        """
+        self.hello()
+        user_id = input('请输入ID(例如40103580):')
+        video_names, video_urls, nickname = self.get_video_urls(user_id)
+        if nickname not in os.listdir():
+            os.mkdir(nickname)
+        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, video_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]
+            self.video_downloader(video_urls[num], os.path.join(nickname, video_name))
+            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:Python学习交流群：125240963')
+        print('*' * 100)
+
+
+if __name__ == '__main__':
+    douyin = DouYin()
+    douyin.run()

怎么用Python爬取抖音小视频? 资深程序员都这样爬取的(附源码)相关推荐

mitmproxy+appium爬取抖音小视频
mitmproxy+appium爬取抖音小视频目标自动化爬取抖音APP小视频,随机获取用户,下载五个小视频,结果以用户ID为单位保存至video目录环境配置见: 视频下载 dy_mitmdum ...
仿抖音短视频h5单页版htnl上传即可使用源码文件
仿抖音短视频的模板项目是前后端分离,前端采用uniapp开发,后端目前是用frphp临时搭建的接口,后续为了方便管理内容,会移植到极致cms上.现在也可丢到网站里当一个单页使用,无聊时可以刷一刷短视 ...
python爬抖音短视频_python爬取抖音小视频
import os,json,requests #伪装头 headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) App ...
使用python爬取抖音app视频！谁说APP数据爬不了的！
记录一下如何用python爬取app数据,本文以爬取抖音视频app为例. 编程工具:pycharm app抓包工具:mitmproxy app自动化工具:appium 运行环境:windows10 思 ...
python3 爬虫实战：mitmproxy 对接 python 下载抖音小视频
From:https://blog.csdn.net/Fan_shui/article/details/81461253 一.前言前面我们已经用 appium 爬取了微信朋友圈,今天我们学习下 mi ...
python好用 appium fiddler_python3 爬虫实战：mitmproxy 对接 python 下载抖音小视频
一.前言前面我们已经用 appium 爬取了微信朋友圈,今天我们学习下 mitmproxy,mitmproxy 是干什么的呢,它跟 charles 和 fiddler类似,是一个抓包工具,以控制台的 ...
python批量删缩进_鬼畜小姐姐+野狼disco，十分钟教你如何用Python剪辑一个牛逼的抖音小视频？...
鬼畜小姐姐+野狼disco,十分钟教你如何用Python剪辑一个牛逼的抖音小视频? 前言半个月前,后台有个小伙伴问我,如何将视频中的音频提取出来,并且将声音转成文字写入到 word 中,正好接下来的 ...
python3爬虫实战（三）：mitmproxy对接python下载抖音小视频
一.前言前面我们已经用appium爬取了微信朋友圈,今天我们学习下mitmproxy,mitmproxy是干什么的呢,它跟charles和fiddler类似,是一个抓包工具,以控制台的形式显示,mi ...
资深程序员教你，用python入门的知识抓取抖音短视频，太厉害了
抖音短视频可以说是当下最流行的自媒体平台,而python编程同样也是目前最流行的编程语言. 今天,就让一位大厂的资深程序员,用最简单的方式,使用python抓取抖音短视频. 到时候我会把所有的源代码都 ...
爬虫项目实战三：爬取抖音短视频
爬取抖音网页版短视频目标项目准备网站分析反爬分析每一页的链接分析代码实现效果显示目标爬取抖音短视频,批量下载到本地. 项目准备软件:Pycharm 第三方库:requests,fa ...

怎么用Python爬取抖音小视频? 资深程序员都这样爬取的(附源码)

简介

准备：