[zzup] support 'up.zzup.com' galleries (#6181)

gallery_dl/extractor/zzup.py

@@ -4,6 +4,8 @@
 # it under the terms of the GNU General Public License version 2 as
 # published by the Free Software Foundation.
 
+"""Extractors for https://zzup.com/"""
+
 from .common import GalleryExtractor
 from .. import text
 
@@ -11,17 +13,20 @@ from .. import text
 class ZzupGalleryExtractor(GalleryExtractor):
     category = "zzup"
     directory_fmt = ("{category}", "{title}")
-    filename_fmt = "{slug}_{num:>03}.{extension}"
+    filename_fmt = "{num:>03}.{extension}"
     archive_fmt = "{slug}_{num}"
     root = "https://zzup.com"
-    pattern = (r"(?:https?://)?(?:www\.)?zzup\.com(/content"
+    pattern = (r"(?:https?://)?(up\.|www\.)?zzup\.com(/(?:viewalbum|content)"
                r"/[\w=]+/([^/?#]+)/[\w=]+)/(?:index|page-\d+)\.html")
     example = "https://zzup.com/content/xyz=/12345_TITLE/123=/index.html"
 
     def __init__(self, match):
-        url = "{}/{}/index.html".format(self.root, match.group(1))
+        subdomain, path, self.slug = match.groups()
+        if subdomain == "up.":
+            self.root = "https://up.zzup.com"
+            self.images = self.images_v2
+        url = "{}{}/index.html".format(self.root, path)
         GalleryExtractor.__init__(self, match, url)
-        self.slug = match.group(2)
 
     def metadata(self, page):
         return {
@@ -38,3 +43,20 @@ class ZzupGalleryExtractor(GalleryExtractor):
         p1, _, p2 = url.partition("/image0")
         ufmt = p1 + "/image{:>05}" + p2[4:]
         return [(ufmt.format(num), None) for num in range(1, count + 1)]
+
+    def images_v2(self, page):
+        results = []
+
+        while True:
+            for path in text.extract_iter(
+                    page, ' class="picbox"><a target="_blank" href="', '"'):
+                results.append(("{}/showimage/{}/zzup.com.jpg".format(
+                    self.root, "/".join(path.split("/")[2:-2])), None))
+
+            pos = page.find("glyphicon-arrow-right")
+            if pos < 0:
+                break
+            path = text.rextract(page, ' href="', '"', pos)[0]
+            page = self.request(text.urljoin(self.gallery_url, path)).text
+
+        return results

test/results/zzup.py

@@ -27,4 +27,10 @@ __tests__ = (
     "#pattern" : r"https://zzup.com/MjAxNjc3OTIyMjE5Nzk=/showimage/zzup-8769086487/image000\d\d-5896498214-40-9689595623/Courtesan/9879560327/zzup.com.jpg",
 },
 
+{
+    "#url"     : "https://up.zzup.com/viewalbum/TE9MQUxVWlogLSBMYWxsaSAtIFdhcm0gYW5kIENvenk=/NTM0MTk=/OTgz/index.html",
+    "#category": ("", "zzup", "gallery"),
+    "#class"   : zzup.ZzupGalleryExtractor,
+},
+
 )