Přidat upraveny_pubcrawler/urls.py

upraveny_pubcrawler/urls.py

@@ -0,0 +1,54 @@
+import re
+from urllib.parse import urlsplit
+from ...common.urls import normalize_url
+
+
+
+ARTICLE_EXPERT = re.compile(r"^/ask-an-expert/[^/]+/[^/]+/?$", re.I)
+
+ARTICLE_FORUM = re.compile(r"^/forum/[^/]+/[^/]+/?$", re.I)
+
+
+def normalize(url, base="https://www.modrykonik.sk/"):
+    return normalize_url(url, base=base, hosts={"www.modrykonik.sk", "modrykonik.sk"},
+                         canonical_host="www.modrykonik.sk")
+
+
+def article_id(url):
+    path = urlsplit(url).path
+    m = ARTICLE_EXPERT.match(path) or ARTICLE_FORUM.match(path)
+    return m.group(0) if m else None
+
+
+def kind(url):
+    parts = urlsplit(url)
+    path = parts.path.rstrip("/") or "/"
+    segments = [s.lower() for s in path.split("/") if s]
+
+    if path == "/robots.txt":
+        return "robots"
+    if path.endswith((".xml", ".xml.gz")) and "sitemap" in path.lower():
+        return "sitemap"
+    if not segments:
+        return None
+
+    if segments[0] == "ask-an-expert":
+        if len(segments) == 1:
+            return "listing"
+        if len(segments) == 2:
+            return "listing"
+        if len(segments) == 3:
+            return "article_expert"
+        return None
+
+
+    if segments[0] == "forum":
+        if len(segments) == 1:
+            return "listing"
+        if len(segments) == 2:
+            return "listing"
+        if len(segments) == 3:
+            return "article_forum"
+        return None
+
+    return None