-
Notifications
You must be signed in to change notification settings - Fork 631
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
4 changed files
with
86 additions
and
3 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
83 changes: 83 additions & 0 deletions
83
src/main/java/com/rarchives/ripme/ripper/rippers/BcfakesRipper.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,83 @@ | ||
package com.rarchives.ripme.ripper.rippers; | ||
|
||
import java.io.IOException; | ||
import java.net.MalformedURLException; | ||
import java.net.URL; | ||
import java.util.ArrayList; | ||
import java.util.List; | ||
import java.util.regex.Matcher; | ||
import java.util.regex.Pattern; | ||
|
||
import org.jsoup.nodes.Document; | ||
import org.jsoup.nodes.Element; | ||
import org.jsoup.select.Elements; | ||
|
||
import com.rarchives.ripme.ripper.AbstractHTMLRipper; | ||
import com.rarchives.ripme.utils.Http; | ||
|
||
public class BcfakesRipper extends AbstractHTMLRipper { | ||
|
||
public BcfakesRipper(URL url) throws IOException { | ||
super(url); | ||
} | ||
|
||
@Override | ||
public String getHost() { | ||
return "bcfakes"; | ||
} | ||
@Override | ||
public String getDomain() { | ||
return "bcfakes.com"; | ||
} | ||
|
||
@Override | ||
public String getGID(URL url) throws MalformedURLException { | ||
Pattern p; | ||
Matcher m; | ||
|
||
p = Pattern.compile("^https?://[wm.]*bcfakes.com/celebritylist/([a-zA-Z0-9\\-_]+).*$"); | ||
m = p.matcher(url.toExternalForm()); | ||
if (m.matches()) { | ||
return m.group(1); | ||
} | ||
|
||
throw new MalformedURLException( | ||
"Expected bcfakes gallery format: " | ||
+ "http://www.bcfakes.com/celebritylist/name" | ||
+ " Got: " + url); | ||
} | ||
|
||
@Override | ||
public Document getFirstPage() throws IOException { | ||
return Http.url(url).get(); | ||
} | ||
|
||
@Override | ||
public Document getNextPage(Document doc) throws IOException { | ||
// Find next page | ||
Elements hrefs = doc.select("a.next"); | ||
if (hrefs.size() == 0) { | ||
throw new IOException("No more pages"); | ||
} | ||
String nextUrl = "http://www.bcfakes.com" + hrefs.first().attr("href"); | ||
sleep(500); | ||
return Http.url(nextUrl).get(); | ||
} | ||
|
||
@Override | ||
public List<String> getURLsFromPage(Document doc) { | ||
List<String> imageURLs = new ArrayList<String>(); | ||
for (Element thumb : doc.select("div.ngg-gallery-thumbnail > a > img")) { | ||
String imageURL = thumb.attr("src"); | ||
imageURL = imageURL.replace("thumbs/thumbs_", ""); | ||
imageURLs.add(imageURL); | ||
} | ||
return imageURLs; | ||
} | ||
|
||
@Override | ||
public void downloadURL(URL url, int index) { | ||
addURLToDownload(url, getPrefix(index)); | ||
} | ||
|
||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters