mirror/ripme
1
0
Fork 0
mirror of https://github.com/RipMeApp/ripme.git synced 2025-09-01 18:03:55 +02:00
Code Issues Releases Wiki Activity

Fixed instagram ripper

Browse Source
This commit is contained in:
cyian-1756
2019-02-28 10:03:06 -05:00
parent 2d77fddc3b
commit e6d2be4608
1 changed files with 17 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
src/main/java/com/rarchives/ripme/ripper/rippers/InstagramRipper.java
View File

@@ -192,6 +192,9 @@ public class InstagramRipper extends AbstractJSONRipper {
Document p = resp.parse(); Document p = resp.parse();
// Get the query hash so we can download the next page // Get the query hash so we can download the next page
qHash = getQHash(p); qHash = getQHash(p);
if (qHash == null) {
throw new IOException("Unable to extract qhash from page");
}
return getJSONFromPage(p); return getJSONFromPage(p);
} }
@@ -398,7 +401,6 @@ public class InstagramRipper extends AbstractJSONRipper {
} }
private boolean pageHasImages(JSONObject json) { private boolean pageHasImages(JSONObject json) {
LOGGER.info(json);
int numberOfImages = json.getJSONObject("data").getJSONObject("user") int numberOfImages = json.getJSONObject("data").getJSONObject("user")
.getJSONObject("edge_owner_to_timeline_media").getJSONArray("edges").length(); .getJSONObject("edge_owner_to_timeline_media").getJSONArray("edges").length();
if (numberOfImages == 0) { if (numberOfImages == 0) {
@@ -426,19 +428,28 @@ public class InstagramRipper extends AbstractJSONRipper {
return new JSONObject(sb.toString()); return new JSONObject(sb.toString());
} catch (MalformedURLException e) { } catch (MalformedURLException e) {
LOGGER.info("Unable to get query_hash, " + url + " is a malformed URL"); LOGGER.info("Unable to get page, " + url + " is a malformed URL");
return null; return null;
} catch (IOException e) { } catch (IOException e) {
LOGGER.info("Unable to get query_hash"); LOGGER.info("Unable to get page");
LOGGER.info(e.getMessage()); LOGGER.info(e.getMessage());
return null; return null;
} }
} }
private String getQhashUrl(Document doc) {
for(Element el : doc.select("link[rel=preload]")) {
if (el.attr("href").contains("ProfilePageContainer")) {
return el.attr("href");
}
}
return null;
}
private String getQHash(Document doc) { private String getQHash(Document doc) {
String jsFileURL = "https://www.instagram.com" + doc.select("link[rel=preload]").attr("href"); String jsFileURL = "https://www.instagram.com" + getQhashUrl(doc);
StringBuilder sb = new StringBuilder(); StringBuilder sb = new StringBuilder();
Document jsPage; LOGGER.info(jsFileURL);
try { try {
// We can't use Jsoup here because it won't download a non-html file larger than a MB // We can't use Jsoup here because it won't download a non-html file larger than a MB
// even if you set maxBodySize to 0 // even if you set maxBodySize to 0
@@ -454,7 +465,7 @@ public class InstagramRipper extends AbstractJSONRipper {
LOGGER.info("Unable to get query_hash, " + jsFileURL + " is a malformed URL"); LOGGER.info("Unable to get query_hash, " + jsFileURL + " is a malformed URL");
return null; return null;
} catch (IOException e) { } catch (IOException e) {
LOGGER.info("Unable to get query_hash"); LOGGER.info("Unable to get query_hash from " + jsFileURL);
LOGGER.info(e.getMessage()); LOGGER.info(e.getMessage());
return null; return null;
} }