WordpressComicRipper: fix formatting
This commit is contained in:
MetaPrime
parent
90a8ab6f81
commit
b8294b8152
@ -16,7 +16,7 @@ import com.rarchives.ripme.ripper.AbstractHTMLRipper;
|
|||||||
import com.rarchives.ripme.utils.Http;
|
import com.rarchives.ripme.utils.Http;
|
||||||
|
|
||||||
public class WordpressComicRipper extends AbstractHTMLRipper {
|
public class WordpressComicRipper extends AbstractHTMLRipper {
|
||||||
String pageTitle ="";
|
String pageTitle = "";
|
||||||
|
|
||||||
public WordpressComicRipper(URL url) throws IOException {
|
public WordpressComicRipper(URL url) throws IOException {
|
||||||
super(url);
|
super(url);
|
||||||
@ -33,77 +33,77 @@ public class WordpressComicRipper extends AbstractHTMLRipper {
|
|||||||
// http://comics-xxx.com/republic-rendezvous-palcomix-star-wars-xxx/
|
// http://comics-xxx.com/republic-rendezvous-palcomix-star-wars-xxx/
|
||||||
|
|
||||||
public static List<String> explicit_domains = Arrays.asList("www.totempole666.com",
|
public static List<String> explicit_domains = Arrays.asList("www.totempole666.com",
|
||||||
"buttsmithy.com", "themonsterunderthebed.net", "prismblush.com", "www.konradokonski.com", "freeadultcomix.com",
|
"buttsmithy.com", "themonsterunderthebed.net", "prismblush.com", "www.konradokonski.com", "freeadultcomix.com",
|
||||||
"thisis.delvecomic.com", "comics-xxx.com");
|
"thisis.delvecomic.com", "comics-xxx.com");
|
||||||
@Override
|
|
||||||
public String getHost() {
|
|
||||||
String host = url.toExternalForm().split("/")[2];
|
|
||||||
return host;
|
|
||||||
}
|
|
||||||
|
|
||||||
@Override
|
@Override
|
||||||
public String getDomain() {
|
public String getHost() {
|
||||||
String host = url.toExternalForm().split("/")[2];
|
String host = url.toExternalForm().split("/")[2];
|
||||||
return host;
|
return host;
|
||||||
}
|
}
|
||||||
|
|
||||||
@Override
|
@Override
|
||||||
public boolean canRip(URL url) {
|
public String getDomain() {
|
||||||
String url_name = url.toExternalForm();
|
String host = url.toExternalForm().split("/")[2];
|
||||||
if (explicit_domains.contains(url_name.split("/")[2])) {
|
return host;
|
||||||
|
}
|
||||||
Pattern totempole666Pat = Pattern.compile("https?://www\\.totempole666.com/comic/([a-zA-Z0-9_-]*)/?$");
|
|
||||||
Matcher totempole666Mat = totempole666Pat.matcher(url.toExternalForm());
|
|
||||||
if (totempole666Mat.matches()) {
|
|
||||||
return true;
|
|
||||||
}
|
|
||||||
|
|
||||||
Pattern konradokonskiPat = Pattern.compile("https?://www.konradokonski.com/sawdust/comic/([a-zA-Z0-9_-]*)/?$");
|
|
||||||
Matcher konradokonskiMat = konradokonskiPat.matcher(url.toExternalForm());
|
|
||||||
if (konradokonskiMat.matches()) {
|
|
||||||
return true;
|
|
||||||
}
|
|
||||||
|
|
||||||
Pattern buttsmithyPat = Pattern.compile("https?://buttsmithy.com/archives/comic/([a-zA-Z0-9_-]*)/?$");
|
|
||||||
Matcher buttsmithyMat = buttsmithyPat.matcher(url.toExternalForm());
|
|
||||||
if (buttsmithyMat.matches()) {
|
|
||||||
return true;
|
|
||||||
}
|
|
||||||
|
|
||||||
Pattern theMonsterUnderTheBedPat = Pattern.compile("https?://themonsterunderthebed.net/\\?comic=([a-zA-Z0-9_-]*)/?$");
|
|
||||||
Matcher theMonsterUnderTheBedMat = theMonsterUnderTheBedPat.matcher(url.toExternalForm());
|
|
||||||
if (theMonsterUnderTheBedMat.matches()) {
|
|
||||||
return true;
|
|
||||||
}
|
|
||||||
|
|
||||||
Pattern prismblushPat = Pattern.compile("https?://prismblush.com/comic/([a-zA-Z0-9_-]*)/?$");
|
|
||||||
Matcher prismblushMat = prismblushPat.matcher(url.toExternalForm());
|
|
||||||
if (prismblushMat.matches()) {
|
|
||||||
return true;
|
|
||||||
}
|
|
||||||
|
|
||||||
Pattern freeadultcomixPat = Pattern.compile("https?://freeadultcomix.com/([a-zA-Z0-9_\\-]*)/?$");
|
|
||||||
Matcher freeadultcomixMat = freeadultcomixPat.matcher(url.toExternalForm());
|
|
||||||
if (freeadultcomixMat.matches()) {
|
|
||||||
return true;
|
|
||||||
}
|
|
||||||
|
|
||||||
Pattern thisisDelvecomicPat = Pattern.compile("https?://thisis.delvecomic.com/NewWP/comic/([a-zA-Z0-9_\\-]*)/?$");
|
|
||||||
Matcher thisisDelvecomicMat = thisisDelvecomicPat.matcher(url.toExternalForm());
|
|
||||||
if (thisisDelvecomicMat.matches()) {
|
|
||||||
return true;
|
|
||||||
}
|
|
||||||
|
|
||||||
Pattern comicsxxxPat = Pattern.compile("https?://comics-xxx.com/([a-zA-Z0-9_\\-]*)/?$");
|
|
||||||
Matcher comicsxxxMat = comicsxxxPat.matcher(url.toExternalForm());
|
|
||||||
if (comicsxxxMat.matches()) {
|
|
||||||
return true;
|
|
||||||
}
|
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public boolean canRip(URL url) {
|
||||||
|
String url_name = url.toExternalForm();
|
||||||
|
if (explicit_domains.contains(url_name.split("/")[2])) {
|
||||||
|
Pattern totempole666Pat = Pattern.compile("https?://www\\.totempole666.com/comic/([a-zA-Z0-9_-]*)/?$");
|
||||||
|
Matcher totempole666Mat = totempole666Pat.matcher(url.toExternalForm());
|
||||||
|
if (totempole666Mat.matches()) {
|
||||||
|
return true;
|
||||||
|
}
|
||||||
|
|
||||||
|
Pattern konradokonskiPat = Pattern.compile("https?://www.konradokonski.com/sawdust/comic/([a-zA-Z0-9_-]*)/?$");
|
||||||
|
Matcher konradokonskiMat = konradokonskiPat.matcher(url.toExternalForm());
|
||||||
|
if (konradokonskiMat.matches()) {
|
||||||
|
return true;
|
||||||
|
}
|
||||||
|
|
||||||
|
Pattern buttsmithyPat = Pattern.compile("https?://buttsmithy.com/archives/comic/([a-zA-Z0-9_-]*)/?$");
|
||||||
|
Matcher buttsmithyMat = buttsmithyPat.matcher(url.toExternalForm());
|
||||||
|
if (buttsmithyMat.matches()) {
|
||||||
|
return true;
|
||||||
|
}
|
||||||
|
|
||||||
|
Pattern theMonsterUnderTheBedPat = Pattern.compile("https?://themonsterunderthebed.net/\\?comic=([a-zA-Z0-9_-]*)/?$");
|
||||||
|
Matcher theMonsterUnderTheBedMat = theMonsterUnderTheBedPat.matcher(url.toExternalForm());
|
||||||
|
if (theMonsterUnderTheBedMat.matches()) {
|
||||||
|
return true;
|
||||||
|
}
|
||||||
|
|
||||||
|
Pattern prismblushPat = Pattern.compile("https?://prismblush.com/comic/([a-zA-Z0-9_-]*)/?$");
|
||||||
|
Matcher prismblushMat = prismblushPat.matcher(url.toExternalForm());
|
||||||
|
if (prismblushMat.matches()) {
|
||||||
|
return true;
|
||||||
|
}
|
||||||
|
|
||||||
|
Pattern freeadultcomixPat = Pattern.compile("https?://freeadultcomix.com/([a-zA-Z0-9_\\-]*)/?$");
|
||||||
|
Matcher freeadultcomixMat = freeadultcomixPat.matcher(url.toExternalForm());
|
||||||
|
if (freeadultcomixMat.matches()) {
|
||||||
|
return true;
|
||||||
|
}
|
||||||
|
|
||||||
|
Pattern thisisDelvecomicPat = Pattern.compile("https?://thisis.delvecomic.com/NewWP/comic/([a-zA-Z0-9_\\-]*)/?$");
|
||||||
|
Matcher thisisDelvecomicMat = thisisDelvecomicPat.matcher(url.toExternalForm());
|
||||||
|
if (thisisDelvecomicMat.matches()) {
|
||||||
|
return true;
|
||||||
|
}
|
||||||
|
|
||||||
|
Pattern comicsxxxPat = Pattern.compile("https?://comics-xxx.com/([a-zA-Z0-9_\\-]*)/?$");
|
||||||
|
Matcher comicsxxxMat = comicsxxxPat.matcher(url.toExternalForm());
|
||||||
|
if (comicsxxxMat.matches()) {
|
||||||
|
return true;
|
||||||
}
|
}
|
||||||
return false;
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
return false;
|
||||||
|
}
|
||||||
|
|
||||||
@Override
|
@Override
|
||||||
public String getAlbumTitle(URL url) throws MalformedURLException {
|
public String getAlbumTitle(URL url) throws MalformedURLException {
|
||||||
Pattern totempole666Pat = Pattern.compile("(?:https?://)?(?:www\\.)?totempole666.com\\/comic/([a-zA-Z0-9_-]*)/?$");
|
Pattern totempole666Pat = Pattern.compile("(?:https?://)?(?:www\\.)?totempole666.com\\/comic/([a-zA-Z0-9_-]*)/?$");
|
||||||
@ -117,6 +117,7 @@ public class WordpressComicRipper extends AbstractHTMLRipper {
|
|||||||
if (buttsmithyMat.matches()) {
|
if (buttsmithyMat.matches()) {
|
||||||
return "buttsmithy.com" + "_" + "Alfie";
|
return "buttsmithy.com" + "_" + "Alfie";
|
||||||
}
|
}
|
||||||
|
|
||||||
Pattern konradokonskiSawdustPat = Pattern.compile("http://www.konradokonski.com/sawdust/comic/([a-zA-Z0-9_-]*)/?$");
|
Pattern konradokonskiSawdustPat = Pattern.compile("http://www.konradokonski.com/sawdust/comic/([a-zA-Z0-9_-]*)/?$");
|
||||||
Matcher konradokonskiSawdustMat = konradokonskiSawdustPat.matcher(url.toExternalForm());
|
Matcher konradokonskiSawdustMat = konradokonskiSawdustPat.matcher(url.toExternalForm());
|
||||||
if (konradokonskiSawdustMat.matches()) {
|
if (konradokonskiSawdustMat.matches()) {
|
||||||
@ -154,110 +155,107 @@ public class WordpressComicRipper extends AbstractHTMLRipper {
|
|||||||
}
|
}
|
||||||
|
|
||||||
return super.getAlbumTitle(url);
|
return super.getAlbumTitle(url);
|
||||||
}
|
}
|
||||||
|
|
||||||
@Override
|
@Override
|
||||||
public String getGID(URL url) throws MalformedURLException {
|
public String getGID(URL url) throws MalformedURLException {
|
||||||
String url_name = url.toExternalForm();
|
String url_name = url.toExternalForm();
|
||||||
// We shouldn't need to return any GID
|
// We shouldn't need to return any GID
|
||||||
if (explicit_domains.contains(url_name.split("/")[2])) {
|
if (explicit_domains.contains(url_name.split("/")[2])) {
|
||||||
return "";
|
return "";
|
||||||
|
}
|
||||||
|
throw new MalformedURLException("You should never see this error message");
|
||||||
|
}
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public Document getNextPage(Document doc) throws IOException {
|
||||||
|
// Find next page
|
||||||
|
String nextPage = "";
|
||||||
|
Element elem = null;
|
||||||
|
if (getHost().contains("www.totempole666.com")
|
||||||
|
|| getHost().contains("buttsmithy.com")
|
||||||
|
|| getHost().contains("themonsterunderthebed.net")
|
||||||
|
|| getHost().contains("prismblush.com")
|
||||||
|
|| getHost().contains("www.konradokonski.com")
|
||||||
|
|| getHost().contains("thisis.delvecomic.com")) {
|
||||||
|
elem = doc.select("a.comic-nav-next").first();
|
||||||
|
if (elem == null) {
|
||||||
|
throw new IOException("No more pages");
|
||||||
}
|
}
|
||||||
throw new MalformedURLException("You should never see this error message");
|
nextPage = elem.attr("href");
|
||||||
|
}
|
||||||
|
if (nextPage == "") {
|
||||||
|
throw new IOException("No more pages");
|
||||||
|
} else {
|
||||||
|
return Http.url(nextPage).get();
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public List<String> getURLsFromPage(Document doc) {
|
||||||
|
List<String> result = new ArrayList<String>();
|
||||||
|
if (getHost().contains("www.totempole666.com")
|
||||||
|
|| getHost().contains("buttsmithy.com")
|
||||||
|
|| getHost().contains("themonsterunderthebed.net")
|
||||||
|
|| getHost().contains("prismblush.com")
|
||||||
|
|| getHost().contains("www.konradokonski.com")
|
||||||
|
|| getHost().contains("thisis.delvecomic.com")) {
|
||||||
|
Element elem = doc.select("div.comic-table > div#comic > a > img").first();
|
||||||
|
// If doc is the last page in the comic then elem.attr("src") returns null
|
||||||
|
// because there is no link <a> to the next page
|
||||||
|
if (elem == null) {
|
||||||
|
elem = doc.select("div.comic-table > div#comic > img").first();
|
||||||
|
}
|
||||||
|
// Check if this is a site where we can get the page number from the title
|
||||||
|
if (url.toExternalForm().contains("buttsmithy.com")) {
|
||||||
|
// Set the page title
|
||||||
|
pageTitle = doc.select("meta[property=og:title]").attr("content");
|
||||||
|
pageTitle = pageTitle.replace(" ", "");
|
||||||
|
pageTitle = pageTitle.replace("P", "p");
|
||||||
|
}
|
||||||
|
if (url.toExternalForm().contains("www.totempole666.com")) {
|
||||||
|
String postDate = doc.select("span.post-date").first().text().replaceAll("/", "_");
|
||||||
|
String postTitle = doc.select("h2.post-title").first().text().replaceAll("#", "");
|
||||||
|
pageTitle = postDate + "_" + postTitle;
|
||||||
|
}
|
||||||
|
if (url.toExternalForm().contains("themonsterunderthebed.net")) {
|
||||||
|
pageTitle = doc.select("title").first().text().replaceAll("#", "");
|
||||||
|
pageTitle = pageTitle.replace("“", "");
|
||||||
|
pageTitle = pageTitle.replace("”", "");
|
||||||
|
pageTitle = pageTitle.replace("The Monster Under the Bed", "");
|
||||||
|
pageTitle = pageTitle.replace("–", "");
|
||||||
|
pageTitle = pageTitle.replace(",", "");
|
||||||
|
pageTitle = pageTitle.replace(" ", "");
|
||||||
|
}
|
||||||
|
result.add(elem.attr("src"));
|
||||||
}
|
}
|
||||||
|
|
||||||
@Override
|
// freeadultcomix gets it own if because it needs to add http://freeadultcomix.com to the start of each link
|
||||||
public Document getNextPage(Document doc) throws IOException {
|
if (url.toExternalForm().contains("freeadultcomix.com")) {
|
||||||
// Find next page
|
for (Element elem : doc.select("div.single-post > p > img.aligncenter")) {
|
||||||
String nextPage = "";
|
result.add("http://freeadultcomix.com" + elem.attr("src"));
|
||||||
Element elem = null;
|
|
||||||
if (getHost().contains("www.totempole666.com")
|
|
||||||
|| getHost().contains("buttsmithy.com")
|
|
||||||
|| getHost().contains("themonsterunderthebed.net")
|
|
||||||
|| getHost().contains("prismblush.com")
|
|
||||||
|| getHost().contains("www.konradokonski.com")
|
|
||||||
|| getHost().contains("thisis.delvecomic.com")) {
|
|
||||||
elem = doc.select("a.comic-nav-next").first();
|
|
||||||
if (elem == null) {
|
|
||||||
throw new IOException("No more pages");
|
|
||||||
}
|
|
||||||
nextPage = elem.attr("href");
|
|
||||||
}
|
|
||||||
if (nextPage == "") {
|
|
||||||
throw new IOException("No more pages");
|
|
||||||
}
|
|
||||||
else {
|
|
||||||
return Http.url(nextPage).get();
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
|
}
|
||||||
|
|
||||||
@Override
|
if (url.toExternalForm().contains("comics-xxx.com")) {
|
||||||
public List<String> getURLsFromPage(Document doc) {
|
for (Element elem : doc.select("div.single-post > center > p > img")) {
|
||||||
List<String> result = new ArrayList<String>();
|
|
||||||
if (getHost().contains("www.totempole666.com")
|
|
||||||
|| getHost().contains("buttsmithy.com")
|
|
||||||
|| getHost().contains("themonsterunderthebed.net")
|
|
||||||
|| getHost().contains("prismblush.com")
|
|
||||||
|| getHost().contains("www.konradokonski.com")
|
|
||||||
|| getHost().contains("thisis.delvecomic.com")) {
|
|
||||||
Element elem = doc.select("div.comic-table > div#comic > a > img").first();
|
|
||||||
// If doc is the last page in the comic then elem.attr("src") returns null
|
|
||||||
// because there is no link <a> to the next page
|
|
||||||
if (elem == null) {
|
|
||||||
elem = doc.select("div.comic-table > div#comic > img").first();
|
|
||||||
}
|
|
||||||
// Check if this is a site where we can get the page number from the title
|
|
||||||
if (url.toExternalForm().contains("buttsmithy.com")) {
|
|
||||||
// Set the page title
|
|
||||||
pageTitle = doc.select("meta[property=og:title]").attr("content");
|
|
||||||
pageTitle = pageTitle.replace(" ", "");
|
|
||||||
pageTitle = pageTitle.replace("P", "p");
|
|
||||||
}
|
|
||||||
if (url.toExternalForm().contains("www.totempole666.com")) {
|
|
||||||
String postDate = doc.select("span.post-date").first().text().replaceAll("/", "_");
|
|
||||||
String postTitle = doc.select("h2.post-title").first().text().replaceAll("#", "");
|
|
||||||
pageTitle = postDate + "_" + postTitle;
|
|
||||||
}
|
|
||||||
if (url.toExternalForm().contains("themonsterunderthebed.net")) {
|
|
||||||
pageTitle = doc.select("title").first().text().replaceAll("#", "");
|
|
||||||
pageTitle = pageTitle.replace("“", "");
|
|
||||||
pageTitle = pageTitle.replace("”", "");
|
|
||||||
pageTitle = pageTitle.replace("The Monster Under the Bed", "");
|
|
||||||
pageTitle = pageTitle.replace("–", "");
|
|
||||||
pageTitle = pageTitle.replace(",", "");
|
|
||||||
pageTitle = pageTitle.replace(" ", "");
|
|
||||||
|
|
||||||
}
|
|
||||||
result.add(elem.attr("src"));
|
result.add(elem.attr("src"));
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
// freeadultcomix gets it own if because it needs to add http://freeadultcomix.com to the start of each link
|
|
||||||
if (url.toExternalForm().contains("freeadultcomix.com")) {
|
|
||||||
for (Element elem : doc.select("div.single-post > p > img.aligncenter")) {
|
|
||||||
result.add("http://freeadultcomix.com" + elem.attr("src"));
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if (url.toExternalForm().contains("comics-xxx.com")) {
|
|
||||||
for (Element elem : doc.select("div.single-post > center > p > img")) {
|
|
||||||
result.add(elem.attr("src"));
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return result;
|
|
||||||
}
|
}
|
||||||
|
return result;
|
||||||
|
}
|
||||||
|
|
||||||
@Override
|
@Override
|
||||||
public void downloadURL(URL url, int index) {
|
public void downloadURL(URL url, int index) {
|
||||||
// Download the url with the page title as the prefix
|
// Download the url with the page title as the prefix
|
||||||
// so we can download them in any order (And don't have to rerip the whole site to update the local copy)
|
// so we can download them in any order (And don't have to rerip the whole site to update the local copy)
|
||||||
if (getHost().contains("buttsmithy.com")
|
if (getHost().contains("buttsmithy.com")
|
||||||
|| getHost().contains("www.totempole666.com")
|
|| getHost().contains("www.totempole666.com")
|
||||||
|| getHost().contains("themonsterunderthebed.net")) {
|
|| getHost().contains("themonsterunderthebed.net")) {
|
||||||
addURLToDownload(url, pageTitle + "_");
|
addURLToDownload(url, pageTitle + "_");
|
||||||
}
|
}
|
||||||
// If we're ripping a site where we can't get the page number/title we just rip normally
|
// If we're ripping a site where we can't get the page number/title we just rip normally
|
||||||
addURLToDownload(url, getPrefix(index));
|
addURLToDownload(url, getPrefix(index));
|
||||||
}
|
}
|
||||||
|
|
||||||
@Override
|
@Override
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user