New upstream version 1.18.3.upstream/1.18.3

1 files changed, 39 insertions, 14 deletions

diff --git a/gallery_dl/extractor/bbc.py b/gallery_dl/extractor/bbc.py
index ace8a28..17b5f52 100644
--- a/gallery_dl/extractor/bbc.py
+++ b/gallery_dl/extractor/bbc.py
@@ -27,7 +27,7 @@ class BbcGalleryExtractor(GalleryExtractor):
     test = (
         ("https://www.bbc.co.uk/programmes/p084qtzs/p085g9kg", {
             "pattern": r"https://ichef\.bbci\.co\.uk"
-                       r"/images/ic/976x549_b/\w+\.jpg",
+                       r"/images/ic/1920xn/\w+\.jpg",
             "count": 37,
             "keyword": {
                 "programme": "p084qtzs",
@@ -49,32 +49,57 @@ class BbcGalleryExtractor(GalleryExtractor):
         }
 
     def images(self, page):
+        width = self.config("width")
+        width = width - width % 16 if width else 1920
+        dimensions = "/{}xn/".format(width)
+
         return [
-            (imgset.rpartition(", ")[2].partition(" ")[0], None)
-            for imgset in text.extract_iter(page, 'data-image-src-sets="', '"')
+            (src.replace("/320x180_b/", dimensions),
+             {"_fallback": self._fallback_urls(src, width)})
+            for src in text.extract_iter(page, 'data-image-src="', '"')
         ]
 
+    @staticmethod
+    def _fallback_urls(src, max_width):
+        front, _, back = src.partition("/320x180_b/")
+        for width in (1920, 1600, 1280, 976):
+            if width < max_width:
+                yield "{}/{}xn/{}".format(front, width, back)
+
 
 class BbcProgrammeExtractor(Extractor):
     """Extractor for all galleries of a bbc programme"""
     category = "bbc"
     subcategory = "programme"
     root = "https://www.bbc.co.uk"
-    pattern = BASE_PATTERN + r"[^/?#]+/galleries)"
-    test = ("https://www.bbc.co.uk/programmes/b006q2x0/galleries", {
-        "pattern": BbcGalleryExtractor.pattern,
-        "count": ">= 24",
-    })
+    pattern = BASE_PATTERN + r"[^/?#]+/galleries)(?:/?\?page=(\d+))?"
+    test = (
+        ("https://www.bbc.co.uk/programmes/b006q2x0/galleries", {
+            "pattern": BbcGalleryExtractor.pattern,
+            "range": "1-50",
+            "count": ">= 50",
+        }),
+        ("https://www.bbc.co.uk/programmes/b006q2x0/galleries?page=40", {
+            "pattern": BbcGalleryExtractor.pattern,
+            "count": ">= 100",
+        }),
+    )
 
     def __init__(self, match):
         Extractor.__init__(self, match)
-        self.galleries_url = self.root + match.group(1)
+        self.path, self.page = match.groups()
 
     def items(self):
-        page = self.request(self.galleries_url).text
         data = {"_extractor": BbcGalleryExtractor}
+        params = {"page": text.parse_int(self.page, 1)}
+        galleries_url = self.root + self.path
 
-        for programme_id in text.extract_iter(
-                page, '<a href="https://www.bbc.co.uk/programmes/', '"'):
-            url = "https://www.bbc.co.uk/programmes/" + programme_id
-            yield Message.Queue, url, data
+        while True:
+            page = self.request(galleries_url, params=params).text
+            for programme_id in text.extract_iter(
+                    page, '<a href="https://www.bbc.co.uk/programmes/', '"'):
+                url = "https://www.bbc.co.uk/programmes/" + programme_id
+                yield Message.Queue, url, data
+            if 'rel="next"' not in page:
+                return
+            params["page"] += 1