New upstream version 1.18.2.upstream/1.18.2

1 files changed, 80 insertions, 0 deletions

diff --git a/gallery_dl/extractor/bbc.py b/gallery_dl/extractor/bbc.py
new file mode 100644
index 0000000..ace8a28
--- /dev/null
+++ b/gallery_dl/extractor/bbc.py
@@ -0,0 +1,80 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2021 Mike Fährmann
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+
+"""Extractors for https://bbc.co.uk/"""
+
+from .common import GalleryExtractor, Extractor, Message
+from .. import text, util
+import json
+
+BASE_PATTERN = r"(?:https?://)?(?:www\.)?bbc\.co\.uk(/programmes/"
+
+
+class BbcGalleryExtractor(GalleryExtractor):
+    """Extractor for a programme gallery on bbc.co.uk"""
+    category = "bbc"
+    root = "https://www.bbc.co.uk"
+    directory_fmt = ("{category}", "{path[0]}", "{path[1]}", "{path[2]}",
+                     "{path[3:]:J - /}")
+    filename_fmt = "{num:>02}.{extension}"
+    archive_fmt = "{programme}_{num}"
+    pattern = BASE_PATTERN + r"[^/?#]+(?!/galleries)(?:/[^/?#]+)?)$"
+    test = (
+        ("https://www.bbc.co.uk/programmes/p084qtzs/p085g9kg", {
+            "pattern": r"https://ichef\.bbci\.co\.uk"
+                       r"/images/ic/976x549_b/\w+\.jpg",
+            "count": 37,
+            "keyword": {
+                "programme": "p084qtzs",
+                "path": ["BBC One", "Doctor Who", "The Timeless Children"],
+            },
+        }),
+        ("https://www.bbc.co.uk/programmes/p084qtzs"),
+    )
+
+    def metadata(self, page):
+        data = json.loads(text.extract(
+            page, '<script type="application/ld+json">', '</script>')[0])
+        return {
+            "programme": self.gallery_url.split("/")[4],
+            "path": list(util.unique_sequence(
+                element["name"]
+                for element in data["itemListElement"]
+            )),
+        }
+
+    def images(self, page):
+        return [
+            (imgset.rpartition(", ")[2].partition(" ")[0], None)
+            for imgset in text.extract_iter(page, 'data-image-src-sets="', '"')
+        ]
+
+
+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",
+    })
+
+    def __init__(self, match):
+        Extractor.__init__(self, match)
+        self.galleries_url = self.root + match.group(1)
+
+    def items(self):
+        page = self.request(self.galleries_url).text
+        data = {"_extractor": BbcGalleryExtractor}
+
+        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