[bbc] extract more metadata (#6582)

https://github.com/mikf/gallery-dl/issues/6582#issuecomment-2745905375

- title
- title_image
- description
- synopsis

gallery_dl/extractor/bbc.py

@@ -27,7 +27,12 @@ class BbcGalleryExtractor(GalleryExtractor):
 
     def metadata(self, page):
         data = self._extract_jsonld(page)
+
         return {
+            "title": text.unescape(text.extr(
+                page, "<h1>", "</h1>").rpartition("</span>")[2]),
+            "description": text.unescape(text.extr(
+                page, 'property="og:description" content="', '"')),
             "programme": self.gallery_url.split("/")[4],
             "path": list(util.unique_sequence(
                 element["name"]
@@ -40,11 +45,20 @@ class BbcGalleryExtractor(GalleryExtractor):
         width = width - width % 16 if width else 1920
         dimensions = "/{}xn/".format(width)
 
-        return [
-            (src.replace("/320x180_b/", dimensions),
-             {"_fallback": self._fallback_urls(src, width)})
-            for src in text.extract_iter(page, 'data-image-src="', '"')
-        ]
+        results = []
+        for img in text.extract_iter(page, 'class="gallery__thumbnail', ">"):
+            src = text.extr(img, 'data-image-src="', '"')
+            results.append((
+                src.replace("/320x180_b/", dimensions),
+                {
+                    "title_image": text.unescape(text.extr(
+                        img, 'data-gallery-title="', '"')),
+                    "synopsis": text.unescape(text.extr(
+                        img, 'data-gallery-synopsis="', '"')),
+                    "_fallback": self._fallback_urls(src, width),
+                },
+            ))
+        return results
 
     @staticmethod
     def _fallback_urls(src, max_width):
@@ -62,14 +76,11 @@ class BbcProgrammeExtractor(Extractor):
     pattern = BASE_PATTERN + r"[^/?#]+/galleries)(?:/?\?page=(\d+))?"
     example = "https://www.bbc.co.uk/programmes/ID/galleries"
 
-    def __init__(self, match):
-        Extractor.__init__(self, match)
-        self.path, self.page = match.groups()
-
     def items(self):
+        path, pnum = self.groups
         data = {"_extractor": BbcGalleryExtractor}
-        params = {"page": text.parse_int(self.page, 1)}
-        galleries_url = self.root + self.path
+        params = {"page": text.parse_int(pnum, 1)}
+        galleries_url = self.root + path
 
         while True:
             page = self.request(galleries_url, params=params).text

test/results/bbc.py

@@ -15,14 +15,52 @@ __tests__ = (
     "#pattern" : r"https://ichef\.bbci\.co\.uk/images/ic/1920xn/\w+\.jpg",
     "#count"   : 37,
 
-    "programme": "p084qtzs",
-    "path"     : [
+    "count"      : 37,
+    "num"        : range(1, 37),
+    "description": "The Cybermen attack. And for the Doctor, nothing will ever be the same.",
+    "programme"  : "p084qtzs",
+    "synopsis"   : "The Cybermen attack. And for the Doctor, nothing will ever be the same.",
+    "title"      : "The Timeless Children",
+    "title_image": {"The Timeless Children", ": The Timeless Children"},
+    "path"       : [
         "BBC One",
         "Doctor Who (2005–2022)",
         "The Timeless Children",
     ],
 },
 
+{
+    "#url"     : "https://www.bbc.co.uk/programmes/p086f8yf/p086f8j6",
+    "#category": ("", "bbc", "gallery"),
+    "#class"   : bbc.BbcGalleryExtractor,
+    "#pattern" : r"https://ichef\.bbci\.co\.uk/images/ic/1920xn/\w+\.jpg",
+    "#range"   : "1-2",
+    "#count"   : 2,
+
+    "count"      : 9,
+    "num"        : {1, 2},
+    "description": "Continuing his journey, Colin gives unique insights into the unique animals he finds.",
+    "extension"  : "jpg",
+    "filename"   : {"p086f7yn", "p086f80n"},
+    "programme"  : "p086f8yf",
+    "title"      : "Wild Cuba: A Caribbean Journey - Part 2",
+    "title_image": {
+        "Cuba is home to many unique birds",
+        "A Cuban pygmy owl looks out of its tree hole",
+    },
+    "synopsis"   : {
+        "This vibrant Cuban tody is just one of more than 300 species of bird found in Cuba.",
+        "Cuban pygmy owls nest in abandoned holes carved out by woodpeckers.",
+    },
+    "path"       : [
+        "BBC Two",
+        "Natural World",
+        "2019-2020",
+        "Wild Cuba: A Caribbean Journey - Part 2",
+        "Wildlife camera operator Colin Stafford-Johnson has loved Cuba since he was a little boy"
+    ],
+},
+
 {
     "#url"     : "https://www.bbc.co.uk/programmes/p084qtzs",
     "#category": ("", "bbc", "gallery"),