Python 解析抖音无水印视频

本文转载自查看原文 2021-08-03 11:19 235 Django

app1/views.py

 1 from django.shortcuts import render, redirect, HttpResponse
 2 from django.http import StreamingHttpResponse, FileResponse
 3 import json
 4 import re
 5 import requests
 6 
 7 
 8 header = {
 9     'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
10     'accept-language': 'zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7',
11     'pragma': 'no-cache',
12     'upgrade-insecure-requests': '1',
13     'user-agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Mobile Safari/537.36'
14 }
15 
16 
17 def douyinurlpars(url, version=1):
18     url = re.findall('(https?://[^\s]+)', url)[0]
19 
20     print(url)
21     res = requests.get(url, headers=header, allow_redirects=True).url
22     # print(requests.headers)
23     # 视频id
24     item_id = res.split('/')[5]
25 
26     html_url = 'https://www.iesdouyin.com/web/api/v2/aweme/iteminfo/?item_ids=' + item_id
27 
28 
29     res2 = requests.get(html_url, headers=header).text
30     response_title = json.loads(res2)['item_list'][0]['desc']
31     # print(response)
32     if version == 1:
33 
34         # 无水印视频url
35         video_url = json.loads(res2)['item_list'][0]['video']['play_addr']['url_list'][0].replace('/playwm/', '/play/')
36     else:
37         # 有水印视频url
38         video_url = json.loads(res2)['item_list'][0]['video']['play_addr']['url_list'][0]
39     return video_url, response_title
40 
41 
42 def douyin(request):
43     if request.method == 'POST':
44         url = request.POST.get('url')
45         if not url:
46             return render(request, 'index.html', {'msg': '输入的链接地址不能为空!!!'})
47         res_url, title = douyinurlpars(url)
48         # res_url = 'https://aweme.snssdk.com/aweme/v1/play/?video_id=v0200fg10000c3ourrbc77uf4e6l8s8g&ratio=720p&line=0'
49         # title = '很多事是科学无法解释的%诡异 %经典港剧'
50         
51         # 将url 进行编码，这里是为了res.html中给后端get传参，因为url中有特殊字符&  （最开始想用来着，后来download函数没用，所以这一步其实也用不到了）
52         date = res_url.replace('&', 'renew')
53         
54         return render(request, 'res.html', {'url': res_url, 'title': title, 'quote_url': date})
55     return render(request, 'index.html')
56 
57 # 备注下，download func 暂时没用，如果有想用的自己研究下也行。小事儿。。。
58 def download(request):
59 
60     head = {
61         'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
62         'Accept-Encoding': 'gzip, deflate',
63         'Accept-Language': 'zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7',
64         'Cache-Control': 'max-age=0',
65         'Connection': 'keep-alive',
66         'Upgrade-Insecure-Requests': '1',
67         'User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.164 Mobile Safari/537.36',
68     }
69 
70     quote_url = request.GET.get('quote_url')
71     # print(type(quote_url), str(quote_url))
72 
73     url = quote_url.replace('renew', '&')
74     file_name = request.GET.get('title') + '1.mp4'
75     # file_name = 'a.mp4'
76     print(quote_url)
77     print(url)
78     print(file_name)
79     # url = 'https://aweme.snssdk.com/aweme/v1/play/?video_id=v0200fg10000c3ourrbc77uf4e6l8s8g&ratio=720p&line=0'
80 
81     # 文件迭代，减少内存压力
82     def generate(url):
83         r = requests.get(url, headers=head, stream=True)
84         for chunk in r.iter_content(chunk_size=512):
85             if chunk:
86                 yield chunk
87 
88     response = StreamingHttpResponse(generate(url))
89     response['content_type'] = "application/octet-stream"
90     response['Content-Disposition'] = 'attachment; filename="{}"'.format(file_name)
91     return response

index.html

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>抖音解析</title>
    <meta name="viewport" content="width=device-width, initial-scale=1"/>

    <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/3.4.1/css/bootstrap.min.css"
          integrity="sha384-HSMxcRTRxnN+Bdg0JdbxYKrThecOKuH5zCYotlSAcp1+c8xmyTe9GYg1l9a69psu" crossorigin="anonymous">
</head>
<body>

<h1 class="text-center">抖音无水印视频解析</h1>

<form class="form-horizontal" action="{% url 'app1:douyin' %}" method="post">
    {% csrf_token %}
<br>
    <div class="form-group form-group-lg">
        <div>
            <input name="url" class="form-control input-lg text-center" type="text" id="formGroupInputLarge"
                   placeholder="放入复制的链接，不用去除链接中的文字和符号">
            <br>
            <button class="form-control btn btn-primary btn-lg">提交</button>
        </div>
    </div>

    {% if msg %}
        <div class="text-center alert alert-danger alert-dismissible " role="alert">
            <strong>{{ msg }}</strong>
        </div>
    {% endif %}


</form>


<!-- jQuery (Bootstrap 的所有 JavaScript 插件都依赖 jQuery，所以必须放在前边) -->
<script src="https://cdn.jsdelivr.net/npm/jquery@1.12.4/dist/jquery.min.js"
        integrity="sha384-nvAa0+6Qg9clwYCGGPpDQLVpLNn0fRaROjHqs13t4Ggj3Ez50XnGQqc/r8MhnRDZ"
        crossorigin="anonymous"></script>
<!-- 加载 Bootstrap 的所有 JavaScript 插件。你也可以根据需要只加载单个插件。 -->
<script src="https://stackpath.bootstrapcdn.com/bootstrap/3.4.1/js/bootstrap.min.js"
        integrity="sha384-aJ21OjlMXNL5UyIl/XNwTMqvzeRMZH2w8c5cRVpzpU8Y5bApTppSuUkhZXN0VxHd"
        crossorigin="anonymous"></script>
</body>
</html>

res.html

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1" />
    <meta name="referrer" content="no-referrer" />
    <title>视频页</title>
    <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/3.4.1/css/bootstrap.min.css" integrity="sha384-HSMxcRTRxnN+Bdg0JdbxYKrThecOKuH5zCYotlSAcp1+c8xmyTe9GYg1l9a69psu" crossorigin="anonymous">
    <style>

    html, body {
        background: #393D49;
        height: 100%;
    }
</style>
</head>
<body>
<div class="text-center">
    <h3><a name="title">{{ title }}</a></h3>

    <!--<p class="lead"><a href="{{ url }}">查看视频</a></p>-->

</div>

<div class=" text-center">
    <video width="240" height="420" controls="controls">
        <source src="{{ url }}" type="video/mp4"/>
    </video>
</div>



<!-- jQuery (Bootstrap 的所有 JavaScript 插件都依赖 jQuery，所以必须放在前边) -->
    <script src="https://cdn.jsdelivr.net/npm/jquery@1.12.4/dist/jquery.min.js" integrity="sha384-nvAa0+6Qg9clwYCGGPpDQLVpLNn0fRaROjHqs13t4Ggj3Ez50XnGQqc/r8MhnRDZ" crossorigin="anonymous"></script>
    <!-- 加载 Bootstrap 的所有 JavaScript 插件。你也可以根据需要只加载单个插件。 -->
    <script src="https://stackpath.bootstrapcdn.com/bootstrap/3.4.1/js/bootstrap.min.js" integrity="sha384-aJ21OjlMXNL5UyIl/XNwTMqvzeRMZH2w8c5cRVpzpU8Y5bApTppSuUkhZXN0VxHd" crossorigin="anonymous"></script>
</body>
</html>

备注

注意，用django写好后，自己部署完毕。这台机器尽量不要用固定的外网ip地址，抖音对固定的IP地址有做反扒。至于怎么每次运行时更换外网IP地址，有需要的可以留言，我们交流交流。

免责声明！

本站转载的文章为个人学习借鉴使用，本站对版权不负任何法律责任。如果侵犯了您的隐私权益，请联系本站邮箱yoyou2525@163.com删除。

猜您在找 抖音无水印视频解析思路抖音无水印视频解析php源码【python】抖音无水印短视频批量爬虫抖音无水印视频抓取原理抖音无水印在线解析下载抖音无水印解析PHP源码 PHP抖音无水印解析api 抖音无水印接口 php抖音无水印视频获取代码一篇文章教会你使用Python下载抖音无水印视频