fastfeedparser 0.5.9__tar.gz → 0.6.0__tar.gz

{fastfeedparser-0.5.9/src/fastfeedparser.egg-info → fastfeedparser-0.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: fastfeedparser
-Version: 0.5.9
+Version: 0.6.0
 Summary: High performance RSS, Atom, JSON and RDF feed parser in Python
 Home-page: https://github.com/kagisearch/fastfeedparser
 Author: Vladimir Prelovac

{fastfeedparser-0.5.9 → fastfeedparser-0.6.0}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = fastfeedparser
-version = 0.5.9
+version = 0.6.0
 author = Vladimir Prelovac
 author_email = vlad@kagi.com
 description = High performance RSS, Atom, JSON and RDF feed parser in Python

{fastfeedparser-0.5.9 → fastfeedparser-0.6.0}/src/fastfeedparser/__init__.py

@@ -1,4 +1,4 @@
 from .main import parse, FastFeedParserDict
 
-__version__ = "0.5.1"
+__version__ = "0.6.0"
 __all__ = ["parse", "FastFeedParserDict"]

{fastfeedparser-0.5.9 → fastfeedparser-0.6.0}/src/fastfeedparser/main.py

@@ -635,6 +635,7 @@ def _raise_for_non_feed_root(
 
 
 _RE_META_REFRESH_URL = re.compile(r'url\s*=\s*["\']?\s*([^"\'>\s]+)', re.IGNORECASE)
+_MAX_META_REDIRECTS = 3
 
 
 def _extract_meta_refresh_url(content: str | bytes, base_url: str) -> str | None:
@@ -866,31 +867,32 @@ def parse(
     else:
         content = source
 
-    try:
-        return _parse_content(
-            content,
-            include_content=include_content,
-            include_tags=include_tags,
-            include_media=include_media,
-            include_enclosures=include_enclosures,
-        )
-    except ValueError as e:
-        if not is_url:
-            raise
-        assert isinstance(source, str)
-        err_msg = str(e)
-        if "HTML" not in err_msg and "not a valid RSS/Atom feed" not in err_msg:
-            raise
-        redirect_url = _extract_meta_refresh_url(content, source)
-        if redirect_url is None:
-            raise
-        return parse(
-            redirect_url,
-            include_content=include_content,
-            include_tags=include_tags,
-            include_media=include_media,
-            include_enclosures=include_enclosures,
-        )
+    parse_kwargs = dict(
+        include_content=include_content,
+        include_tags=include_tags,
+        include_media=include_media,
+        include_enclosures=include_enclosures,
+    )
+
+    redirects_left = _MAX_META_REDIRECTS
+    while True:
+        try:
+            return _parse_content(content, **parse_kwargs)
+        except ValueError as e:
+            if not is_url:
+                raise
+            assert isinstance(source, str)
+            err_msg = str(e)
+            if "HTML" not in err_msg and "not a valid RSS/Atom feed" not in err_msg:
+                raise
+            if redirects_left <= 0:
+                raise ValueError("too many meta-refresh redirects") from e
+            redirect_url = _extract_meta_refresh_url(content, source)
+            if redirect_url is None:
+                raise
+            content = _fetch_url_content(redirect_url)
+            source = redirect_url
+            redirects_left -= 1
 
 
 def _parse_feed_info(
@@ -1051,6 +1053,35 @@ def _parse_feed_info(
         if managing_editor:
             feed["author"] = managing_editor
 
+    # Parse feed-level image/icon/logo
+    if feed_type == "atom":
+        icon_el = channel.find(f"{{{atom_ns}}}icon")
+        if icon_el is not None and icon_el.text:
+            feed["icon"] = icon_el.text.strip()
+        logo_el = channel.find(f"{{{atom_ns}}}logo")
+        if logo_el is not None and logo_el.text:
+            feed["logo"] = logo_el.text.strip()
+    elif feed_type == "rss":
+        image_el = channel.find("image")
+        if image_el is not None:
+            image: dict[str, Optional[str]] = {}
+            for sub_tag in ("url", "title", "link"):
+                sub_el = image_el.find(sub_tag)
+                if sub_el is not None and sub_el.text:
+                    image[sub_tag] = sub_el.text.strip()
+            if image.get("url"):
+                feed["image"] = image
+    elif feed_type == "rdf":
+        rdf_image_el = channel.find("{http://purl.org/rss/1.0/}image")
+        if rdf_image_el is not None:
+            image = {}
+            for sub_tag in ("title", "link", "url"):
+                sub_el = rdf_image_el.find(f"{{http://purl.org/rss/1.0/}}{sub_tag}")
+                if sub_el is not None and sub_el.text:
+                    image[sub_tag] = sub_el.text.strip()
+            if image.get("url"):
+                feed["image"] = image
+
     # Parse feed-level tags/categories
     if include_tags:
         tags = _parse_tags(channel, feed_type, atom_ns)

{fastfeedparser-0.5.9 → fastfeedparser-0.6.0/src/fastfeedparser.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: fastfeedparser
-Version: 0.5.9
+Version: 0.6.0
 Summary: High performance RSS, Atom, JSON and RDF feed parser in Python
 Home-page: https://github.com/kagisearch/fastfeedparser
 Author: Vladimir Prelovac

{fastfeedparser-0.5.9 → fastfeedparser-0.6.0}/src/fastfeedparser.egg-info/SOURCES.txt

@@ -10,4 +10,5 @@ src/fastfeedparser.egg-info/dependency_links.txt
 src/fastfeedparser.egg-info/requires.txt
 src/fastfeedparser.egg-info/top_level.txt
 tests/test_encoding.py
+tests/test_feed_image.py
 tests/test_integration.py

fastfeedparser-0.6.0/tests/test_feed_image.py

@@ -0,0 +1,136 @@
+"""Tests for feed-level image/icon/logo extraction."""
+
+from fastfeedparser import parse
+
+
+def test_rss_feed_image():
+    xml = b"""<?xml version="1.0" encoding="UTF-8"?>
+    <rss version="2.0">
+    <channel>
+        <title>Test Feed</title>
+        <link>https://example.com</link>
+        <image>
+            <url>https://example.com/logo.png</url>
+            <title>Test Feed</title>
+            <link>https://example.com</link>
+        </image>
+        <item>
+            <title>Entry 1</title>
+        </item>
+    </channel>
+    </rss>"""
+    result = parse(xml)
+    assert result["feed"]["image"] == {
+        "url": "https://example.com/logo.png",
+        "title": "Test Feed",
+        "link": "https://example.com",
+    }
+
+
+def test_rss_feed_image_url_only():
+    xml = b"""<?xml version="1.0" encoding="UTF-8"?>
+    <rss version="2.0">
+    <channel>
+        <title>Test</title>
+        <image>
+            <url>https://example.com/icon.png</url>
+        </image>
+        <item><title>Entry</title></item>
+    </channel>
+    </rss>"""
+    result = parse(xml)
+    assert result["feed"]["image"]["url"] == "https://example.com/icon.png"
+    assert "title" not in result["feed"]["image"]
+
+
+def test_rss_feed_no_image():
+    xml = b"""<?xml version="1.0" encoding="UTF-8"?>
+    <rss version="2.0">
+    <channel>
+        <title>Test</title>
+        <item><title>Entry</title></item>
+    </channel>
+    </rss>"""
+    result = parse(xml)
+    assert "image" not in result["feed"]
+
+
+def test_rss_feed_image_empty_url():
+    xml = b"""<?xml version="1.0" encoding="UTF-8"?>
+    <rss version="2.0">
+    <channel>
+        <title>Test</title>
+        <image>
+            <url></url>
+            <title>Test</title>
+        </image>
+        <item><title>Entry</title></item>
+    </channel>
+    </rss>"""
+    result = parse(xml)
+    assert "image" not in result["feed"]
+
+
+def test_atom_feed_icon_and_logo():
+    xml = b"""<?xml version="1.0" encoding="UTF-8"?>
+    <feed xmlns="http://www.w3.org/2005/Atom">
+        <title>Test Feed</title>
+        <icon>https://example.com/favicon.ico</icon>
+        <logo>https://example.com/banner.png</logo>
+        <entry>
+            <title>Entry 1</title>
+            <id>urn:entry:1</id>
+        </entry>
+    </feed>"""
+    result = parse(xml)
+    assert result["feed"]["icon"] == "https://example.com/favicon.ico"
+    assert result["feed"]["logo"] == "https://example.com/banner.png"
+
+
+def test_atom_feed_icon_only():
+    xml = b"""<?xml version="1.0" encoding="UTF-8"?>
+    <feed xmlns="http://www.w3.org/2005/Atom">
+        <title>Test</title>
+        <icon>https://example.com/favicon.ico</icon>
+        <entry><title>E</title><id>urn:1</id></entry>
+    </feed>"""
+    result = parse(xml)
+    assert result["feed"]["icon"] == "https://example.com/favicon.ico"
+    assert "logo" not in result["feed"]
+
+
+def test_atom_feed_no_icon():
+    xml = b"""<?xml version="1.0" encoding="UTF-8"?>
+    <feed xmlns="http://www.w3.org/2005/Atom">
+        <title>Test</title>
+        <entry><title>E</title><id>urn:1</id></entry>
+    </feed>"""
+    result = parse(xml)
+    assert "icon" not in result["feed"]
+    assert "logo" not in result["feed"]
+
+
+def test_rdf_feed_image():
+    xml = b"""<?xml version="1.0" encoding="UTF-8"?>
+    <rdf:RDF
+        xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+        xmlns="http://purl.org/rss/1.0/">
+        <channel>
+            <title>Test RDF Feed</title>
+            <link>https://example.com</link>
+        </channel>
+        <image>
+            <url>https://example.com/rdf-logo.png</url>
+            <title>RDF Feed</title>
+            <link>https://example.com</link>
+        </image>
+        <item>
+            <title>Entry 1</title>
+        </item>
+    </rdf:RDF>"""
+    result = parse(xml)
+    assert result["feed"]["image"] == {
+        "url": "https://example.com/rdf-logo.png",
+        "title": "RDF Feed",
+        "link": "https://example.com",
+    }