thoerup/spejdernetscraper/IMDBSeriesScraper.java

package dk.thoerup.spejdernetscraper;

import java.util.concurrent.Callable;
import java.util.concurrent.TimeUnit;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import com.google.common.cache.Cache;
import com.google.common.cache.CacheBuilder;

import dk.thoerup.genericjavautils.HttpUtil;

public class IMDBSeriesScraper {
        
        private static Cache<String,String> webCache = CacheBuilder.newBuilder()
                        .expireAfterWrite(5, TimeUnit.MINUTES)
                        .maximumSize(1000)
                        .build();
        
        private String getDoc(final String url) throws Exception {
                
                return webCache.get(url, new Callable<String>() {

                        @Override
                        public String call() throws Exception {
                                //TODO: implement something that can follow redirects
                                return HttpUtil.getContentString(url, 10000);
                        }
                });
                
        }
        
        public String fechTitle(String sid, int season, int episode) throws Exception {
                
                final String epMatch = "ep" + episode;          
                final String noTitle = "Episode #" + season + "." + episode;
                
                String url = "https://www.imdb.com/title/" + sid + "/episodes?season=" + season;
                
                String rawHtml = getDoc(url);   
                
                Document page = Jsoup.parse(rawHtml);
                
                Element episodesContent = page.getElementById("episodes_content");
                
                Elements episodesList = episodesContent.getElementsByClass("list_item");
                
                for (int i=0; i<episodesList.size(); i++) {
                        Element curEp = episodesList.get(i);
                        
                        Element image = curEp.getElementsByClass("image").first();
                        
                        Element anchor = image.child(0);
                        
                        String title = anchor.attr("title");
                        //String content = anchor.text().trim();
                        String href = anchor.attr("href");
                        
                        if ( href.endsWith(epMatch)) {
                                if (title.equalsIgnoreCase(noTitle)) {
                                        return "!Title not found!";                     
                                }
                                
                                return title;   
                        }                       
                }
                
                
                throw new Exception("Episode not found !");
        }

}
1	package dk.thoerup.spejdernetscraper;
2
3	import java.util.concurrent.Callable;
4	import java.util.concurrent.TimeUnit;
5
6	import org.jsoup.Jsoup;
7	import org.jsoup.nodes.Document;
8	import org.jsoup.nodes.Element;
9	import org.jsoup.select.Elements;
10
11	import com.google.common.cache.Cache;
12	import com.google.common.cache.CacheBuilder;
13
14	import dk.thoerup.genericjavautils.HttpUtil;
15
16	public class IMDBSeriesScraper {
17
18	private static Cache<String,String> webCache = CacheBuilder.newBuilder()
19	.expireAfterWrite(5, TimeUnit.MINUTES)
20	.maximumSize(1000)
21	.build();
22
23	private String getDoc(final String url) throws Exception {
24
25	return webCache.get(url, new Callable<String>() {
26
27	@Override
28	public String call() throws Exception {
29	//TODO: implement something that can follow redirects
30	return HttpUtil.getContentString(url, 10000);
31	}
32	});
33
34	}
35
36	public String fechTitle(String sid, int season, int episode) throws Exception {
37
38	final String epMatch = "ep" + episode;
39	final String noTitle = "Episode #" + season + "." + episode;
40
41	String url = "https://www.imdb.com/title/" + sid + "/episodes?season=" + season;
42
43	String rawHtml = getDoc(url);
44
45	Document page = Jsoup.parse(rawHtml);
46
47	Element episodesContent = page.getElementById("episodes_content");
48
49	Elements episodesList = episodesContent.getElementsByClass("list_item");
50
51	for (int i=0; i<episodesList.size(); i++) {
52	Element curEp = episodesList.get(i);
53
54	Element image = curEp.getElementsByClass("image").first();
55
56	Element anchor = image.child(0);
57
58	String title = anchor.attr("title");
59	//String content = anchor.text().trim();
60	String href = anchor.attr("href");
61
62	if ( href.endsWith(epMatch)) {
63	if (title.equalsIgnoreCase(noTitle)) {
64	return "!Title not found!";
65	}
66
67	return title;
68	}
69	}
70
71
72	throw new Exception("Episode not found !");
73	}
74
75	}