Python爬虫获取html文件中js变量，下载视频

原网页关键内容如下：

<div class="container">
<div class="row">
    <div class="col-12 col-sm-12 col-md-8 col-lg-8 py-2">
        <div>
            
            
            
            
            <video id="video" poster="/image/c9/2e/fe52c35ba98444b6bcd63c7c6b4ec92e.jpg1" width="100%" height="auto" preload="none" controls playsinline webkit-playsinline></video>
            
                ;(function(){
                    var src = "https:\/\/******\/stream\/full\/asia\/1700\/G0622.cut.ff.m3u81";
                    var video = document.getElementById("video");
					video.volume = 0.1;
                    if (!Hls.isSupported()) {
                        video.src = src;
                        return;
                    }
                    
                    
                    
                    
                    
                    
                    var hls = {};
                    if (p2pml.core.HybridLoader.isSupported()) {
                        var engine = new p2pml.hlsjs.Engine({
                            segments: {
                                swarmId: src['\x72\x65\x70\x6c\x61\x63\x65']("\x63\x63\x2e\x73\x73\x73\x73\x70\x70\x70\x70\x2e\x63\x6f\x6d","\x62\x70\x31\x2e\x64\x6b\x6b\x6f\x6d\x6f\x2e\x63\x6f\x6dfdd"),
                            },
                            loader: {
                                trackerAnnounce: ["wss://tracker.openwebtorrent.com1/", "wss://tracker.btorrent.xyz1/"],
                                cachedSegmentExpiration: 86400000,
                                cachedSegmentsCount: 1000,
                                requiredSegmentsPriority: 3,
                                httpDownloadMaxPriority: 9,
                                httpDownloadProbability: 0.06,
                                httpDownloadProbabilityInterval: 1000,
                                httpDownloadProbabilitySkipIfNoPeers: true,
                                p2pDownloadMaxPriority: 50,
                                httpFailedSegmentTimeout: 1000,
                                simultaneousP2PDownloads: 20,
                                simultaneousHttpDownloads: 3,
                                httpDownloadInitialTimeout: 120000,
                                httpDownloadInitialTimeoutPerSegment: 5000,
                                httpUseRanges: true,
                            }
                        });
                        
                        
                        
						
                        hls = new Hls({ loader: engine.createLoaderClass() });
                        p2pml.hlsjs.initHlsJsPlayer(hls);
                    } else {
                        hls = new Hls();
                    }
                    hls.loadSource(src);
                    hls.attachMedia(video);
                    
                })();
            
            
        </div>
    </div>
        <div class="col-12 col-sm-12 col-md-4 col-lg-4 py-2">
            <div>
                <a target="_blank" href="https://tzainolxp.50gdainolxp.com/0167/475/index1.html"><img class="img-fluid" src="/static/assets/img/8484af615821.gif"></a><a target="_blank" href="https://tzbqdjwdr.50gdbqdjwdr.com/6966/9725/index1.html"><img class="img-fluid" src="/static/assets/img/632711ca1f31.gif"></a>
            </div>
        </div>
    </div>
</div>

##可以看到$var src $是关键的内容

在使用soup.find_all("script")获取到script的list后， 使用正则即可解决

post_list = soup.find_all("script")
for post in post_list:
    js_code = post.string
    # 使用正则表达式提取变量名和赋值部分
    pattern = r'var\s+(\w+)\s*=\s*(.*?);'
    matches = re.findall(pattern, js_code, re.DOTALL)
    for var in matches:
        if(var[0] == "src"):
            print(title,"var[1]",var[1])

注意：本文归作者所有，未经作者允许，不得转载