[chevereto:album] extract 'album_…' metadata (#8604)

gallery_dl/extractor/chevereto.py

@@ -21,10 +21,12 @@ class CheveretoExtractor(BaseExtractor):
     def _init(self):
         self.path = self.groups[-1]
 
-    def _pagination(self, url):
+    def _pagination(self, url, callback=None):
-        while True:
+        page = self.request(url).text
-            page = self.request(url).text
+        if callback is not None:
+            callback(page)
 
+        while True:
             for item in text.extract_iter(
                     page, '<div class="list-item-image ', 'image-container'):
                 yield text.urljoin(self.root, text.extr(
@@ -35,6 +37,7 @@ class CheveretoExtractor(BaseExtractor):
                 return
             if url[0] == "/":
                 url = self.root + url
+            page = self.request(url).text
 
 
 BASE_PATTERN = CheveretoExtractor.update({
@@ -155,10 +158,21 @@ class CheveretoAlbumExtractor(CheveretoExtractor):
             albums = (url,)
 
         for album in albums:
-            for item_url in self._pagination(album):
+            for item_url in self._pagination(
+                    album, self._extract_metadata_album):
                 data = data_video if "/video/" in item_url else data_image
                 yield Message.Queue, item_url, data
 
+    def _extract_metadata_album(self, page):
+        url, pos = text.extract(
+            page, 'property="og:url" content="', '"')
+
+        kwdict = self.kwdict
+        kwdict["album_slug"], _, kwdict["album_id"] = \
+            url[url.rfind("/")+1:].rpartition(".")
+        kwdict["album"] = text.unescape(text.extract(
+            page, 'property="og:title" content="', '"', pos)[0])
+
 
 class CheveretoCategoryExtractor(CheveretoExtractor):
     """Extractor for chevereto galleries"""

test/results/jpgfish.py

@@ -118,6 +118,10 @@ __tests__ = (
     "#category": ("chevereto", "jpgfish", "album"),
     "#class"   : chevereto.CheveretoAlbumExtractor,
     "#count"   : 2,
+
+    "album"     : "funny meme album",
+    "album_id"  : "CDilP",
+    "album_slug": "funny-meme-album",
 },
 
 {
@@ -125,6 +129,10 @@ __tests__ = (
     "#category": ("chevereto", "jpgfish", "album"),
     "#class"   : chevereto.CheveretoAlbumExtractor,
     "#count"   : 114,
+
+    "album"     : "Gunggingnsk OF",
+    "album_id"  : "N9OOI",
+    "album_slug": "gunggingnsk",
 },
 
 {
@@ -132,6 +140,10 @@ __tests__ = (
     "#category": ("chevereto", "jpgfish", "album"),
     "#class"   : chevereto.CheveretoAlbumExtractor,
     "#count"   : 100,
+
+    "album"     : "101-200",
+    "album_id"  : "aNJ6A",
+    "album_slug": "101-200",
 },
 
 {
@@ -139,6 +151,10 @@ __tests__ = (
     "#category": ("chevereto", "jpgfish", "album"),
     "#class"   : chevereto.CheveretoAlbumExtractor,
     "#count"   : 606,
+
+    "album"     : "re:([12345]0)?1-[123456]00",
+    "album_id"  : str,
+    "album_slug": str,
 },
 
 {