From e4788fa663383d6930a526d9140af1d668aebbbc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Thu, 22 Jul 2021 20:37:05 +0200
Subject: [PATCH] [bbc] add 'gallery' and 'programme' extractors (closes #1706)

---
 docs/supportedsites.md           |  6 +++
 gallery_dl/extractor/__init__.py |  1 +
 gallery_dl/extractor/bbc.py      | 80 ++++++++++++++++++++++++++++++++
 scripts/supportedsites.py        |  1 +
 4 files changed, 88 insertions(+)
 create mode 100644 gallery_dl/extractor/bbc.py

diff --git a/docs/supportedsites.md b/docs/supportedsites.md
index 0a4febc5..2e2c4292 100644
--- a/docs/supportedsites.md
+++ b/docs/supportedsites.md
@@ -79,6 +79,12 @@ Consider all sites to be NSFW unless otherwise known.
     <td>Albums, Artwork Listings, Challenges, individual Images, Likes, Search Results, User Profiles</td>
     <td></td>
 </tr>
+<tr>
+    <td>BBC</td>
+    <td>https://bbc.co.uk/</td>
+    <td>Galleries, Programmes</td>
+    <td></td>
+</tr>
 <tr>
     <td>Behance</td>
     <td>https://www.behance.net/</td>
diff --git a/gallery_dl/extractor/__init__.py b/gallery_dl/extractor/__init__.py
index 42365884..740fb7d7 100644
--- a/gallery_dl/extractor/__init__.py
+++ b/gallery_dl/extractor/__init__.py
@@ -20,6 +20,7 @@ modules = [
     "architizer",
     "artstation",
     "aryion",
+    "bbc",
     "bcy",
     "behance",
     "blogger",
diff --git a/gallery_dl/extractor/bbc.py b/gallery_dl/extractor/bbc.py
new file mode 100644
index 00000000..ace8a285
--- /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
diff --git a/scripts/supportedsites.py b/scripts/supportedsites.py
index 03c09be8..50868fa7 100755
--- a/scripts/supportedsites.py
+++ b/scripts/supportedsites.py
@@ -22,6 +22,7 @@ CATEGORY_MAP = {
     "aryion"         : "Eka's Portal",
     "b4k"            : "arch.b4k.co",
     "baraag"         : "baraag",
+    "bbc"            : "BBC",
     "bcy"            : "半次元",
     "deviantart"     : "DeviantArt",
     "dokireader"     : "Doki Reader",