爬取猫眼电影数据

时间：2020-06-19 10:30:52 阅读：179 评论：0 收藏：0 [点我收藏+]

标签：err thread sele intro inf readline png chrome cti

最近做了一个新项目，因为项目需要大量电影数据，猫眼电影又恰好有足够的数据，就上猫眼爬数据了。

1、先分析一下网页地址，发现电影都是被排好序号了，这就很简单了。

2、在分析页面，这次主要爬取黄色框中的内容。在浏览器中按F12检查元素，只要把Div获取出来就算完成了。

技术图片

下面贴代码：

技术图片

主函数

 1 static void Main(string[] args)
 2         {
 3             int errorCount = 0;//计算爬取失败的次数
 4             int count = 450;//结束范围
 5             for (int i = 401; i <= count; i++)
 6             {
 7                 Thread.Sleep(2000);//每隔两秒爬取一次，不要给服务器压力
 8                 try
 9                 {
10                     HtmlWeb web = new HtmlWeb();
11                     //https://maoyan.com/films/1
12                     web.OverrideEncoding = Encoding.UTF8;
13                     HtmlDocument doc = web.Load($"https://maoyan.com/films/{i}");//把url中的1替换为i
14 
15                     HtmlDocument htmlDoc = new HtmlDocument();
16                     string url = $"https://maoyan.com/films/{i}";
17                     
18                     //获取电影名
19                     HtmlNode MovieTitle = doc.DocumentNode.SelectSingleNode("//div[@class=‘movie-brief-container‘]/h1[@class=‘name‘]");//分析页面结构后得到的div
20                     if (MovieTitle == null)//如果是null，那么表明进入验证页面了，执行第二种方法
21                     {
22                         string urlResponse = URLRequest(url);
23                         htmlDoc.LoadHtml(urlResponse);
24                         MovieTitle = htmlDoc.DocumentNode.SelectSingleNode("//div[@class=‘movie-brief-container‘]/h1[@class=‘name‘]");
25                         if (MovieTitle == null)//如果是null，那么表明进入验证页面了。（第二种方法也失效）
26                         {
27 　　　　　　　　　　　　　　　　　　//此处需要进入浏览器手动完成验证 或者 自行分析验证页面实现自动验证
28                         }
29                     }
30                     string title = MovieTitle.InnerText;
31                     //Console.WriteLine(MovieTitle.InnerText);
32 
33                     //获取电影海报
34                     HtmlNode MovieImgSrc = doc.DocumentNode.SelectSingleNode("//div[@class=‘celeInfo-left‘]/div[@class=‘avatar-shadow‘]/img[@class=‘avatar‘]");
35                     if (MovieImgSrc == null)
36                     {
37                         
38                         MovieImgSrc = htmlDoc.DocumentNode.SelectSingleNode("//div[@class=‘celeInfo-left‘]/div[@class=‘avatar-shadow‘]/img[@class=‘avatar‘]");
39                     }
40                     //Console.WriteLine(MovieImgSrc.GetAttributeValue("src", ""));
41                     string imgurl = MovieImgSrc.GetAttributeValue("src", "");
42 
43                     //电影类型
44                     HtmlNodeCollection MovieTypes = doc.DocumentNode.SelectNodes("//div[@class=‘movie-brief-container‘]/ul/li[@class=‘ellipsis‘]");
45                     if (MovieTypes == null)
46                     {
47                         MovieTypes = htmlDoc.DocumentNode.SelectNodes("//div[@class=‘movie-brief-container‘]/ul/li[@class=‘ellipsis‘]");
48                     }
49                     string types = "", artime = "", releasetime = "";
50 
51                     foreach (var item in MovieTypes[0].ChildNodes)
52                     {
53                         if (item.InnerText.Trim() != "")
54                         {
55                             //Console.WriteLine(item.InnerText.Trim());
56                             types += item.InnerText.Trim() + "-";
57                         }
58                     }
59                     artime = MovieTypes[1].InnerText;
60                     releasetime = MovieTypes[2].InnerText;
61                     //Console.WriteLine(MovieTypes[i].InnerText);
62 
63                     //剧情简介
64                     string intro = "";
65                     HtmlNode introduction = doc.DocumentNode.SelectSingleNode("//div[@class=‘mod-content‘]/span[@class=‘dra‘]");
66                     if (introduction == null)
67                     {
68                         introduction = htmlDoc.DocumentNode.SelectSingleNode("//div[@class=‘mod-content‘]/span[@class=‘dra‘]");
69                     }
70                     //Console.WriteLine(introduction.InnerText);
71                     intro = introduction.InnerText;
72                     //Console.WriteLine(i);
73 
74                     using (FileStream fs = new FileStream(@"d:\Sql.txt", FileMode.Append, FileAccess.Write))
75                     {
76                         fs.Lock(0, fs.Length);
77                         StreamWriter sw = new StreamWriter(fs);
78                         sw.WriteLine($"INSERT INTO Movies VALUES(‘{title}‘,‘{imgurl}‘,‘{types}‘,‘{artime}‘,‘{releasetime}‘,‘{intro.Trim()}‘);");
79                         fs.Unlock(0, fs.Length);//一定要用在Flush()方法以前，否则抛出异常。
80                         sw.Flush();
81                     }
82 
83                 }
84                 catch (Exception ex)
85                 {
86                     errorCount++;
87                     Console.WriteLine(ex);
88                 }
89             }
90             Console.WriteLine($"结束 成功:{count - errorCount}条,失败：{errorCount}条");
91             Console.ReadLine();
92 
93         }

URLRequest方法

 1 static string URLRequest(string url)
 2         {
 3             // 准备请求
 4             HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url);
 5 
 6             // 设置GET方法
 7             request.Method = "GET";
 8             request.Timeout = 6000; //60 second timeout
 9             request.UserAgent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.106 Safari/537.36";
10 
11             string responseContent = null;
12 
13             // 获取 Response
14             using (WebResponse response = request.GetResponse())
15             {
17                 using (Stream stream = response.GetResponseStream())
18                 {
19                     // 读取流
20                     using (StreamReader streamreader = new StreamReader(stream))
21                     {
23                         responseContent = streamreader.ReadToEnd();
24                     }
25                 }
26             }
27 
28             return (responseContent);
29         }