fastfeedparser 0.5.6__tar.gz → 0.5.8__tar.gz

{fastfeedparser-0.5.6/src/fastfeedparser.egg-info → fastfeedparser-0.5.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: fastfeedparser
-Version: 0.5.6
+Version: 0.5.8
 Summary: High performance RSS, Atom, JSON and RDF feed parser in Python
 Home-page: https://github.com/kagisearch/fastfeedparser
 Author: Vladimir Prelovac

{fastfeedparser-0.5.6 → fastfeedparser-0.5.8}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = fastfeedparser
-version = 0.5.6
+version = 0.5.8
 author = Vladimir Prelovac
 author_email = vlad@kagi.com
 description = High performance RSS, Atom, JSON and RDF feed parser in Python

{fastfeedparser-0.5.6 → fastfeedparser-0.5.8}/src/fastfeedparser/main.py

@@ -411,6 +411,13 @@ def _parse_json_feed(
             if enclosures:
                 entry["enclosures"] = enclosures
 
+        # Derive feedparser-compatible author fields
+        _author = entry.get("author")
+        if _author:
+            _detail = {"name": _author}
+            entry["author_detail"] = _detail
+            entry["authors"] = [_detail]
+
         # Add links
         entry["links"] = []
         item_url = item.get("url")
@@ -455,7 +462,14 @@ def _fetch_url_content(url: str) -> str | bytes:
                 )
             content = brotli.decompress(content)
         content_charset = response.headers.get_content_charset()
-        return content.decode(content_charset) if content_charset else content
+        if content_charset:
+            try:
+                return content.decode(content_charset)
+            except (UnicodeDecodeError, LookupError):
+                # Server lied about charset; return raw bytes and let
+                # lxml detect encoding from the XML declaration/BOM.
+                return content
+        return content
 
 
 def _maybe_parse_json_feed(
@@ -805,6 +819,12 @@ def _parse_content(
         # Ensure that titles and descriptions are always present
         entry["title"] = entry.get("title", "").strip()
         entry["description"] = entry.get("description", "").strip()
+        # Derive feedparser-compatible author fields
+        _author = entry.get("author")
+        if _author:
+            _detail = {"name": _author}
+            entry["author_detail"] = _detail
+            entry["authors"] = [_detail]
         entries.append(entry)
 
     return feed
@@ -971,8 +991,19 @@ def _parse_feed_info(
     for link in channel.findall(f"{{{atom_ns}}}link"):
         rel = link.get("rel")
         href = link.get("href") or link.get("link")
-        if rel is None and href:
+        if rel == "alternate" and href and not feed_link:
             feed_link = href
+            feed_links.append(
+                {
+                    "rel": rel,
+                    "type": link.get("type"),
+                    "href": href,
+                    "title": link.get("title"),
+                }
+            )
+        elif rel is None and href:
+            if not feed_link:
+                feed_link = href
         elif rel not in {"hub", "self", "replies", "edit"}:
             feed_links.append(
                 {
@@ -1114,7 +1145,10 @@ def _populate_entry_links_from_elements(
             "title": link.get("title"),
         }
         if rel == "alternate":
-            alternate_link = link_dict
+            if alternate_link is None:
+                alternate_link = link_dict
+            else:
+                entry_links.append(link_dict)
         elif rel not in {"edit", "self"}:
             entry_links.append(link_dict)
 

{fastfeedparser-0.5.6 → fastfeedparser-0.5.8/src/fastfeedparser.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: fastfeedparser
-Version: 0.5.6
+Version: 0.5.8
 Summary: High performance RSS, Atom, JSON and RDF feed parser in Python
 Home-page: https://github.com/kagisearch/fastfeedparser
 Author: Vladimir Prelovac