mirror/ripme
1
0
Fork 0
mirror of https://github.com/RipMeApp/ripme.git synced 2025-08-18 11:41:21 +02:00
Code Issues Releases Wiki Activity

Merge pull request #1362 from kittenparry/meituri-update

Browse Source 
Functional regex for getting image url list (MeituriRipper)
This commit is contained in:
cyian-1756
2019-09-09 15:19:19 -05:00
committed by GitHub
parent 524068b82f a296ad4831
commit 6c9fb45d84
1 changed files with 10 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
src/main/java/com/rarchives/ripme/ripper/rippers/MeituriRipper.java
View File

@@ -35,11 +35,11 @@ public class MeituriRipper extends AbstractHTMLRipper {
@Override
public String getGID(URL url) throws MalformedURLException {
// without escape
// ^https?://[w.]*meituri\.com/a/([0-9]+)/([0-9\.html]+)*$
// ^https?://[w.]*meituri\.com/a/([0-9]+)/([0-9]+\.html)*$
// https://www.meituri.com/a/14449/
// also matches https://www.meituri.com/a/14449/3.html etc.
// group 1 is 14449
Pattern p = Pattern.compile("^https?://[w.]*meituri\\.com/a/([0-9]+)/([0-9\\.html]+)*$");
Pattern p = Pattern.compile("^https?://[w.]*meituri\\.com/a/([0-9]+)/([0-9]+\\.html)*$");
Matcher m = p.matcher(url.toExternalForm());
if (m.matches()) {
albumID = m.group(1);
@@ -59,27 +59,22 @@ public class MeituriRipper extends AbstractHTMLRipper {
List<String> imageURLs = new ArrayList<>();
// Get number of images from the page
// Then generate links according to that
String numOfImages = "";
// A very ugly way of getting "图片数量： 55P" from paragraphs
// 3rd p in div.tuji
int n = 0;
int numOfImages = 1;
Pattern p = Pattern.compile("^<p>图片数量： ([0-9]+)P</p>$");
for (Element para : doc.select("div.tuji > p")) {
// 图片数量： 55P
if (n == 2) {
numOfImages = para.toString();
// <p>图片数量： 55P</p>
Matcher m = p.matcher(para.toString());
if (m.matches()) {
// 55
numOfImages = Integer.parseInt(m.group(1));
}
n++;
}
// ["<p>图片数量：", "55P</p>"]
String[] splitNumOfImages = numOfImages.split(" ");
// "55P</p>" -> "55" -> 55
int actualNumOfImages = Integer.parseInt(splitNumOfImages[1].replace("P</p>", ""));
// Base URL: http://ii.hywly.com/a/1/albumid/imgnum.jpg
String baseURL = "http://ii.hywly.com/a/1/" + albumID + "/";
// Loop through and add images to the URL list
for (int i = 1; i <= actualNumOfImages; i++) {
for (int i = 1; i <= numOfImages; i++) {
imageURLs.add(baseURL + i + ".jpg");
}
return imageURLs;