Adding test

changedetectionio/__init__.py

@@ -2,7 +2,7 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 # Semver means never use .01, or 00. Should be .1.
-__version__ = '0.51.1'
+__version__ = '0.51.2'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError

changedetectionio/content_fetchers/requests.py

@@ -1,6 +1,7 @@
 from loguru import logger
 import hashlib
 import os
+import re
 import asyncio
 from changedetectionio import strtobool
 from changedetectionio.content_fetchers.exceptions import BrowserStepsInUnsupportedFetcher, EmptyReply, Non200ErrorCodeReceived
@@ -76,9 +77,22 @@ class fetcher(Fetcher):
         if not is_binary:
             # Don't run this for PDF (and requests identified as binary) takes a _long_ time
             if not r.headers.get('content-type') or not 'charset=' in r.headers.get('content-type'):
-                encoding = chardet.detect(r.content)['encoding']
-                if encoding:
-                    r.encoding = encoding
+                # For XML/RSS feeds, check the XML declaration for encoding attribute
+                # This is more reliable than chardet which can misdetect UTF-8 as MacRoman
+                content_type = r.headers.get('content-type', '').lower()
+                if 'xml' in content_type or 'rss' in content_type:
+                    # Look for <?xml version="1.0" encoding="UTF-8"?>
+                    xml_encoding_match = re.search(rb'<\?xml[^>]+encoding=["\']([^"\']+)["\']', r.content[:200])
+                    if xml_encoding_match:
+                        r.encoding = xml_encoding_match.group(1).decode('ascii')
+                    else:
+                        # Default to UTF-8 for XML if no encoding found
+                        r.encoding = 'utf-8'
+                else:
+                    # For other content types, use chardet
+                    encoding = chardet.detect(r.content)['encoding']
+                    if encoding:
+                        r.encoding = encoding
 
         self.headers = r.headers
 

changedetectionio/rss_tools.py

@@ -29,16 +29,135 @@ def cdata_in_document_to_text(html_content: str, render_anchor_tag_content=False
     return re.sub(pattern, repl, html_content)
 
 
+# Jinja2 template for formatting RSS/Atom feed entries
+# Covers all common feedparser entry fields including namespaced elements
+# Outputs HTML that will be converted to text via html_to_text
+# @todo - This could be a UI setting in the future
+RSS_ENTRY_TEMPLATE = """<article class="rss-item" id="{{ entry.id|replace('"', '')|replace(' ', '-') }}">{%- if entry.title -%}Title: {{ entry.title }}<br>{%- endif -%}
+{%- if entry.link -%}<strong>Link:</strong> <a href="{{ entry.link }}">{{ entry.link }}</a><br>
+{%- endif -%}
+{%- if entry.id -%}
+<strong>Guid:</strong> {{ entry.id }}<br>
+{%- endif -%}
+{%- if entry.published -%}
+<strong>PubDate:</strong> {{ entry.published }}<br>
+{%- endif -%}
+{%- if entry.updated and entry.updated != entry.published -%}
+<strong>Updated:</strong> {{ entry.updated }}<br>
+{%- endif -%}
+{%- if entry.author -%}
+<strong>Author:</strong> {{ entry.author }}<br>
+{%- elif entry.author_detail and entry.author_detail.name -%}
+<strong>Author:</strong> {{ entry.author_detail.name }}
+{%- if entry.author_detail.email %} ({{ entry.author_detail.email }}){% endif -%}
+<br>
+{%- endif -%}
+{%- if entry.contributors -%}
+<strong>Contributors:</strong> {% for contributor in entry.contributors -%}
+{{ contributor.name if contributor.name else contributor }}
+{%- if not loop.last %}, {% endif -%}
+{%- endfor %}<br>
+{%- endif -%}
+{%- if entry.publisher -%}
+<strong>Publisher:</strong> {{ entry.publisher }}<br>
+{%- endif -%}
+{%- if entry.rights -%}
+<strong>Rights:</strong> {{ entry.rights }}<br>
+{%- endif -%}
+{%- if entry.license -%}
+<strong>License:</strong> {{ entry.license }}<br>
+{%- endif -%}
+{%- if entry.language -%}
+<strong>Language:</strong> {{ entry.language }}<br>
+{%- endif -%}
+{%- if entry.tags -%}
+<strong>Tags:</strong> {% for tag in entry.tags -%}
+{{ tag.term if tag.term else tag }}
+{%- if not loop.last %}, {% endif -%}
+{%- endfor %}<br>
+{%- endif -%}
+{%- if entry.category -%}
+<strong>Category:</strong> {{ entry.category }}<br>
+{%- endif -%}
+{%- if entry.comments -%}
+<strong>Comments:</strong> <a href="{{ entry.comments }}">{{ entry.comments }}</a><br>
+{%- endif -%}
+{%- if entry.slash_comments -%}
+<strong>Comment Count:</strong> {{ entry.slash_comments }}<br>
+{%- endif -%}
+{%- if entry.enclosures -%}
+<strong>Enclosures:</strong><br>
+{%- for enclosure in entry.enclosures %}
+- <a href="{{ enclosure.href }}">{{ enclosure.href }}</a> ({{ enclosure.type if enclosure.type else 'unknown type' }}
+{%- if enclosure.length %}, {{ enclosure.length }} bytes{% endif -%}
+)<br>
+{%- endfor -%}
+{%- endif -%}
+{%- if entry.media_content -%}
+<strong>Media:</strong><br>
+{%- for media in entry.media_content %}
+- <a href="{{ media.url }}">{{ media.url }}</a>
+{%- if media.type %} ({{ media.type }}){% endif -%}
+{%- if media.width and media.height %} {{ media.width }}x{{ media.height }}{% endif -%}
+<br>
+{%- endfor -%}
+{%- endif -%}
+{%- if entry.media_thumbnail -%}
+<strong>Thumbnail:</strong> <a href="{{ entry.media_thumbnail[0].url if entry.media_thumbnail[0].url else entry.media_thumbnail[0] }}">{{ entry.media_thumbnail[0].url if entry.media_thumbnail[0].url else entry.media_thumbnail[0] }}</a><br>
+{%- endif -%}
+{%- if entry.media_description -%}
+<strong>Media Description:</strong> {{ entry.media_description }}<br>
+{%- endif -%}
+{%- if entry.itunes_duration -%}
+<strong>Duration:</strong> {{ entry.itunes_duration }}<br>
+{%- endif -%}
+{%- if entry.itunes_author -%}
+<strong>Podcast Author:</strong> {{ entry.itunes_author }}<br>
+{%- endif -%}
+{%- if entry.dc_identifier -%}
+<strong>Identifier:</strong> {{ entry.dc_identifier }}<br>
+{%- endif -%}
+{%- if entry.dc_source -%}
+<strong>DC Source:</strong> {{ entry.dc_source }}<br>
+{%- endif -%}
+{%- if entry.dc_type -%}
+<strong>Type:</strong> {{ entry.dc_type }}<br>
+{%- endif -%}
+{%- if entry.dc_format -%}
+<strong>Format:</strong> {{ entry.dc_format }}<br>
+{%- endif -%}
+{%- if entry.dc_relation -%}
+<strong>Related:</strong> {{ entry.dc_relation }}<br>
+{%- endif -%}
+{%- if entry.dc_coverage -%}
+<strong>Coverage:</strong> {{ entry.dc_coverage }}<br>
+{%- endif -%}
+{%- if entry.source and entry.source.title -%}
+<strong>Source:</strong> {{ entry.source.title }}
+{%- if entry.source.link %} (<a href="{{ entry.source.link }}">{{ entry.source.link }}</a>){% endif -%}
+<br>
+{%- endif -%}
+{%- if entry.dc_content -%}
+<strong>Content:</strong> {{ entry.dc_content | safe }}
+{%- elif entry.content and entry.content[0].value -%}
+<strong>Content:</strong> {{ entry.content[0].value | safe }}
+{%- elif entry.summary -%}
+<strong>Summary:</strong> {{ entry.summary | safe }}
+{%- endif -%}</article>
+"""
+
+
 def format_rss_items(rss_content: str, render_anchor_tag_content=False) -> str:
     """
-    Format RSS/Atom feed items in a readable text format using feedparser.
+    Format RSS/Atom feed items in a readable text format using feedparser and Jinja2.
 
-    Converts RSS <item> or Atom <entry> elements to formatted text with:
-    - <title> → <h1>Title</h1>
-    - <link> → Link: [url]
-    - <guid> → Guid: [id]
-    - <pubDate> → PubDate: [date]
-    - <description> or <content> → Raw HTML content (CDATA and entities automatically handled)
+    Converts RSS <item> or Atom <entry> elements to formatted text with all available fields:
+    - Basic fields: title, link, id/guid, published date, updated date
+    - Author fields: author, author_detail, contributors, publisher
+    - Content fields: content, summary, description
+    - Metadata: tags, category, rights, license
+    - Media: enclosures, media_content, media_thumbnail
+    - Dublin Core elements: dc:creator, dc:date, dc:publisher, etc. (mapped by feedparser)
 
     Args:
         rss_content: The RSS/Atom feed content
@@ -49,65 +168,19 @@ def format_rss_items(rss_content: str, render_anchor_tag_content=False) -> str:
     """
     try:
         import feedparser
-        from xml.sax.saxutils import escape as xml_escape
+        from changedetectionio.jinja2_custom import safe_jinja
 
         # Parse the feed - feedparser handles all RSS/Atom variants, CDATA, entity unescaping, etc.
         feed = feedparser.parse(rss_content)
 
-        formatted_items = []
-
-        # Determine feed type for appropriate labels when fields are missing
-        # feedparser sets feed.version to things like 'rss20', 'atom10', etc.
+        # Determine feed type for appropriate labels
         is_atom = feed.version and 'atom' in feed.version
 
+        formatted_items = []
         for entry in feed.entries:
-            item_parts = []
-
-            # Title - feedparser handles CDATA and entity unescaping automatically
-            if hasattr(entry, 'title') and entry.title:
-                item_parts.append(f'<h1>{xml_escape(entry.title)}</h1>')
-
-            # Link
-            if hasattr(entry, 'link') and entry.link:
-                item_parts.append(f'Link: {xml_escape(entry.link)}<br>')
-
-            # GUID/ID
-            if hasattr(entry, 'id') and entry.id:
-                item_parts.append(f'Guid: {xml_escape(entry.id)}<br>')
-
-            # Date - feedparser normalizes all date field names to 'published'
-            if hasattr(entry, 'published') and entry.published:
-                item_parts.append(f'PubDate: {xml_escape(entry.published)}<br>')
-
-            # Description/Content - feedparser handles CDATA and entity unescaping automatically
-            # Only add "Summary:" label for Atom <summary> tags
-            content = None
-            add_label = False
-
-            if hasattr(entry, 'content') and entry.content:
-                # Atom <content> - no label, just content
-                content = entry.content[0].value if entry.content[0].value else None
-            elif hasattr(entry, 'summary'):
-                # Could be RSS <description> or Atom <summary>
-                # feedparser maps both to entry.summary
-                content = entry.summary if entry.summary else None
-                # Only add "Summary:" label for Atom feeds (which use <summary> tag)
-                if is_atom:
-                    add_label = True
-
-            # Add content with or without label
-            if content:
-                if add_label:
-                    item_parts.append(f'Summary:<br>{content}')
-                else:
-                    item_parts.append(content)
-            else:
-                # No content - just show <none>
-                item_parts.append('&lt;none&gt;')
-
-            # Join all parts of this item
-            if item_parts:
-                formatted_items.append('\n'.join(item_parts))
+            # Render the entry using Jinja2 template
+            rendered = safe_jinja.render(RSS_ENTRY_TEMPLATE, entry=entry, is_atom=is_atom)
+            formatted_items.append(rendered.strip())
 
         # Wrap each item in a div with classes (first, last, item-N)
         items_html = []
@@ -122,7 +195,8 @@ def format_rss_items(rss_content: str, render_anchor_tag_content=False) -> str:
 
             class_str = ' '.join(classes)
             items_html.append(f'<div class="{class_str}">{item}</div>')
-        return '<html><body>\n'+"\n<br><br>".join(items_html)+'\n</body></html>'
+
+        return '<html><body>\n' + "\n<br>".join(items_html) + '\n</body></html>'
 
     except Exception as e:
         logger.warning(f"Error formatting RSS items: {str(e)}")

changedetectionio/tests/test_rss_reader_mode.py

@@ -7,6 +7,61 @@ from flask import url_for
 from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, extract_rss_token_from_UI, \
     extract_UUID_from_client, delete_all_watches
 
+def set_xmlns_purl_content(datastore_path, extra=""):
+    data=f"""<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="https://purl.org/dc/elements/1.1/" xmlns:media="http://search.yahoo.com/mrss/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
+<channel>
+<atom:link href="https://www.xxxxxxxtechxxxxx.com/feeds.xml" rel="self" type="application/rss+xml"/>
+<title>
+<![CDATA[ Latest from xxxxxxxtechxxxxx ]]>
+</title>
+<link>https://www.xxxxx.com</link>
+<description>
+<![CDATA[ All the latest content from the xxxxxxxtechxxxxx team ]]>
+</description>
+<lastBuildDate>Wed, 19 Nov 2025 15:00:00 +0000</lastBuildDate>
+<language>en</language>
+<item>
+<title>
+<![CDATA[ Sony Xperia 1 VII review: has Sony’s long-standing Xperia family lost what it takes to compete? ]]>
+</title>
+<dc:content>
+<![CDATA[  {{extra}}  a little harder, dc-content. blue often quite tough and purple usually very difficult.</p><p>On the plus side, you don't technically need to solve the final one, as you'll be able to answer that one by a process of elimination. What's more, you can make up to four mistakes, which gives you a little bit of breathing room.</p><p>It's a little more involved than something like Wordle, however, and there are plenty of opportunities for the game to trip you up with tricks. For instance, watch out for homophones and other word games that could disguise the answers.</p><p>It's playable for free via the <a href="https://www.nytimes.com/games/strands" target="_blank">NYT Games site</a> on desktop or mobile.</p></article></section> ]]>
+</dc:content>
+<link>https://www.xxxxxxx.com/gaming/nyt-connections-today-answers-hints-20-november-2025</link>
+<description>
+<![CDATA[ Looking for NYT Connections answers and hints? Here's all you need to know to solve today's game, plus my commentary on the puzzles. ]]>
+</description>
+<guid isPermaLink="false">N2C2T6DztpWdxSdKpSUx89</guid>
+<enclosure url="https://cdn.mos.cms.futurecdn.net/RCGfdf3yhQ9W3MHbTRT6yk-1280-80.jpg" type="image/jpeg" length="0"/>
+<pubDate>Wed, 19 Nov 2025 15:00:00 +0000</pubDate>
+<category>
+<![CDATA[ Gaming ]]>
+</category>
+<dc:creator>
+<![CDATA[ Johnny Dee ]]>
+</dc:creator>
+<media:content type="image/jpeg" url="https://cdn.mos.cms.futurecdn.net/RCGfdf3yhQ9W3MHbTRT6yk-1280-80.jpg">
+<media:credit>
+<![CDATA[ New York Times ]]>
+</media:credit>
+<media:text>
+<![CDATA[ NYT Connections homescreen on a phone, on a purple background ]]>
+</media:text>
+<media:title type="plain">
+<![CDATA[ NYT Connections homescreen on a phone, on a purple background ]]>
+</media:title>
+</media:content>
+<media:thumbnail url="https://cdn.mos.cms.futurecdn.net/RCGfdf3yhQ9W3MHbTRT6yk-1280-80.jpg"/>
+</item>
+    </channel>
+    </rss>
+            """
+
+    with open(os.path.join(datastore_path, "endpoint-content.txt"), "w") as f:
+        f.write(data)
+
+
+
 
 def set_original_cdata_xml(datastore_path):
     test_return_data = """<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
@@ -98,3 +153,26 @@ def test_rss_reader_mode_with_css_filters(client, live_server, measure_memory_us
     assert 'The days of Terminator and The Matrix' in snapshot_contents
     delete_all_watches(client)
 
+
+def test_xmlns_purl_content(client, live_server, measure_memory_usage, datastore_path):
+    set_xmlns_purl_content(datastore_path=datastore_path)
+
+    # Rarely do endpoints give the right header, usually just text/xml, so we check also for <rss
+    # This also triggers the automatic CDATA text parser so the RSS goes back a nice content list
+    #test_url = url_for('test_endpoint', content_type="text/xml; charset=UTF-8", _external=True)
+
+    # Because NO utf-8 was specified here, we should be able to recover it in requests or other somehow.
+    test_url = url_for('test_endpoint', content_type="text/xml;", _external=True)
+    live_server.app.config['DATASTORE'].data['settings']['application']['rss_reader_mode'] = True
+
+    # Add our URL to the import page
+    uuid = client.application.config.get('DATASTORE').add_watch(url=test_url, extras={'include_filters': [".last"]})
+    client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
+
+    wait_for_all_checks(client)
+
+    watch = live_server.app.config['DATASTORE'].data['watching'][uuid]
+    dates = list(watch.history.keys())
+    snapshot_contents = watch.get_history_snapshot(timestamp=dates[0])
+    assert "Title: Sony Xperia 1 VII review: has Sony’s long-standing Xperia family lost what it takes to compete?" in snapshot_contents
+    assert "dc-content" in snapshot_contents