Primer commit del proyecto RSS

venv/lib/python3.12/site-packages/feedparser/namespaces/_base.py

@@ -0,0 +1,506 @@
+# Support for the Atom, RSS, RDF, and CDF feed formats
+# Copyright 2010-2023 Kurt McKee <contactme@kurtmckee.org>
+# Copyright 2002-2008 Mark Pilgrim
+# All rights reserved.
+#
+# This file is a part of feedparser.
+#
+# Redistribution and use in source and binary forms, with or without modification,
+# are permitted provided that the following conditions are met:
+#
+# * Redistributions of source code must retain the above copyright notice,
+#   this list of conditions and the following disclaimer.
+# * Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+import copy
+
+from ..datetimes import _parse_date
+from ..urls import make_safe_absolute_uri
+from ..util import FeedParserDict
+
+
+class Namespace(object):
+    """Support for the Atom, RSS, RDF, and CDF feed formats.
+
+    The feed formats all share common elements, some of which have conflicting
+    interpretations. For simplicity, all of the base feed format support is
+    collected here.
+    """
+
+    supported_namespaces = {
+        '': '',
+        'http://backend.userland.com/rss': '',
+        'http://blogs.law.harvard.edu/tech/rss': '',
+        'http://purl.org/rss/1.0/': '',
+        'http://my.netscape.com/rdf/simple/0.9/': '',
+        'http://example.com/newformat#': '',
+        'http://example.com/necho': '',
+        'http://purl.org/echo/': '',
+        'uri/of/echo/namespace#': '',
+        'http://purl.org/pie/': '',
+        'http://purl.org/atom/ns#': '',
+        'http://www.w3.org/2005/Atom': '',
+        'http://purl.org/rss/1.0/modules/rss091#': '',
+    }
+
+    def _start_rss(self, attrs_d):
+        versionmap = {
+            '0.91': 'rss091u',
+            '0.92': 'rss092',
+            '0.93': 'rss093',
+            '0.94': 'rss094',
+        }
+
+        # If we're here then this is an RSS feed.
+        # If we don't have a version or have a version that starts with something
+        # other than RSS then there's been a mistake. Correct it.
+        if not self.version or not self.version.startswith('rss'):
+            attr_version = attrs_d.get('version', '')
+            version = versionmap.get(attr_version)
+            if version:
+                self.version = version
+            elif attr_version.startswith('2.'):
+                self.version = 'rss20'
+            else:
+                self.version = 'rss'
+
+    def _start_channel(self, attrs_d):
+        self.infeed = 1
+        self._cdf_common(attrs_d)
+
+    def _cdf_common(self, attrs_d):
+        if 'lastmod' in attrs_d:
+            self._start_modified({})
+            self.elementstack[-1][-1] = attrs_d['lastmod']
+            self._end_modified()
+        if 'href' in attrs_d:
+            self._start_link({})
+            self.elementstack[-1][-1] = attrs_d['href']
+            self._end_link()
+
+    def _start_feed(self, attrs_d):
+        self.infeed = 1
+        versionmap = {'0.1': 'atom01',
+                      '0.2': 'atom02',
+                      '0.3': 'atom03'}
+        if not self.version:
+            attr_version = attrs_d.get('version')
+            version = versionmap.get(attr_version)
+            if version:
+                self.version = version
+            else:
+                self.version = 'atom'
+
+    def _end_channel(self):
+        self.infeed = 0
+    _end_feed = _end_channel
+
+    def _start_image(self, attrs_d):
+        context = self._get_context()
+        if not self.inentry:
+            context.setdefault('image', FeedParserDict())
+        self.inimage = 1
+        self.title_depth = -1
+        self.push('image', 0)
+
+    def _end_image(self):
+        self.pop('image')
+        self.inimage = 0
+
+    def _start_textinput(self, attrs_d):
+        context = self._get_context()
+        context.setdefault('textinput', FeedParserDict())
+        self.intextinput = 1
+        self.title_depth = -1
+        self.push('textinput', 0)
+    _start_textInput = _start_textinput
+
+    def _end_textinput(self):
+        self.pop('textinput')
+        self.intextinput = 0
+    _end_textInput = _end_textinput
+
+    def _start_author(self, attrs_d):
+        self.inauthor = 1
+        self.push('author', 1)
+        # Append a new FeedParserDict when expecting an author
+        context = self._get_context()
+        context.setdefault('authors', [])
+        context['authors'].append(FeedParserDict())
+    _start_managingeditor = _start_author
+
+    def _end_author(self):
+        self.pop('author')
+        self.inauthor = 0
+        self._sync_author_detail()
+    _end_managingeditor = _end_author
+
+    def _start_contributor(self, attrs_d):
+        self.incontributor = 1
+        context = self._get_context()
+        context.setdefault('contributors', [])
+        context['contributors'].append(FeedParserDict())
+        self.push('contributor', 0)
+
+    def _end_contributor(self):
+        self.pop('contributor')
+        self.incontributor = 0
+
+    def _start_name(self, attrs_d):
+        self.push('name', 0)
+
+    def _end_name(self):
+        value = self.pop('name')
+        if self.inpublisher:
+            self._save_author('name', value, 'publisher')
+        elif self.inauthor:
+            self._save_author('name', value)
+        elif self.incontributor:
+            self._save_contributor('name', value)
+        elif self.intextinput:
+            context = self._get_context()
+            context['name'] = value
+
+    def _start_width(self, attrs_d):
+        self.push('width', 0)
+
+    def _end_width(self):
+        value = self.pop('width')
+        try:
+            value = int(value)
+        except ValueError:
+            value = 0
+        if self.inimage:
+            context = self._get_context()
+            context['width'] = value
+
+    def _start_height(self, attrs_d):
+        self.push('height', 0)
+
+    def _end_height(self):
+        value = self.pop('height')
+        try:
+            value = int(value)
+        except ValueError:
+            value = 0
+        if self.inimage:
+            context = self._get_context()
+            context['height'] = value
+
+    def _start_url(self, attrs_d):
+        self.push('href', 1)
+    _start_homepage = _start_url
+    _start_uri = _start_url
+
+    def _end_url(self):
+        value = self.pop('href')
+        if self.inauthor:
+            self._save_author('href', value)
+        elif self.incontributor:
+            self._save_contributor('href', value)
+    _end_homepage = _end_url
+    _end_uri = _end_url
+
+    def _start_email(self, attrs_d):
+        self.push('email', 0)
+
+    def _end_email(self):
+        value = self.pop('email')
+        if self.inpublisher:
+            self._save_author('email', value, 'publisher')
+        elif self.inauthor:
+            self._save_author('email', value)
+        elif self.incontributor:
+            self._save_contributor('email', value)
+
+    def _start_subtitle(self, attrs_d):
+        self.push_content('subtitle', attrs_d, 'text/plain', 1)
+    _start_tagline = _start_subtitle
+
+    def _end_subtitle(self):
+        self.pop_content('subtitle')
+    _end_tagline = _end_subtitle
+
+    def _start_rights(self, attrs_d):
+        self.push_content('rights', attrs_d, 'text/plain', 1)
+    _start_copyright = _start_rights
+
+    def _end_rights(self):
+        self.pop_content('rights')
+    _end_copyright = _end_rights
+
+    def _start_item(self, attrs_d):
+        self.entries.append(FeedParserDict())
+        self.push('item', 0)
+        self.inentry = 1
+        self.guidislink = 0
+        self.title_depth = -1
+        id = self._get_attribute(attrs_d, 'rdf:about')
+        if id:
+            context = self._get_context()
+            context['id'] = id
+        self._cdf_common(attrs_d)
+    _start_entry = _start_item
+
+    def _end_item(self):
+        self.pop('item')
+        self.inentry = 0
+        self.hasContent = 0
+    _end_entry = _end_item
+
+    def _start_language(self, attrs_d):
+        self.push('language', 1)
+
+    def _end_language(self):
+        self.lang = self.pop('language')
+
+    def _start_webmaster(self, attrs_d):
+        self.push('publisher', 1)
+
+    def _end_webmaster(self):
+        self.pop('publisher')
+        self._sync_author_detail('publisher')
+
+    def _start_published(self, attrs_d):
+        self.push('published', 1)
+    _start_issued = _start_published
+    _start_pubdate = _start_published
+
+    def _end_published(self):
+        value = self.pop('published')
+        self._save('published_parsed', _parse_date(value), overwrite=True)
+    _end_issued = _end_published
+    _end_pubdate = _end_published
+
+    def _start_updated(self, attrs_d):
+        self.push('updated', 1)
+    _start_modified = _start_updated
+    _start_lastbuilddate = _start_updated
+
+    def _end_updated(self):
+        value = self.pop('updated')
+        parsed_value = _parse_date(value)
+        self._save('updated_parsed', parsed_value, overwrite=True)
+    _end_modified = _end_updated
+    _end_lastbuilddate = _end_updated
+
+    def _start_created(self, attrs_d):
+        self.push('created', 1)
+
+    def _end_created(self):
+        value = self.pop('created')
+        self._save('created_parsed', _parse_date(value), overwrite=True)
+
+    def _start_expirationdate(self, attrs_d):
+        self.push('expired', 1)
+
+    def _end_expirationdate(self):
+        self._save('expired_parsed', _parse_date(self.pop('expired')), overwrite=True)
+
+    def _start_category(self, attrs_d):
+        term = attrs_d.get('term')
+        scheme = attrs_d.get('scheme', attrs_d.get('domain'))
+        label = attrs_d.get('label')
+        self._add_tag(term, scheme, label)
+        self.push('category', 1)
+    _start_keywords = _start_category
+
+    def _end_category(self):
+        value = self.pop('category')
+        if not value:
+            return
+        context = self._get_context()
+        tags = context['tags']
+        if value and len(tags) and not tags[-1]['term']:
+            tags[-1]['term'] = value
+        else:
+            self._add_tag(value, None, None)
+    _end_keywords = _end_category
+
+    def _start_cloud(self, attrs_d):
+        self._get_context()['cloud'] = FeedParserDict(attrs_d)
+
+    def _start_link(self, attrs_d):
+        attrs_d.setdefault('rel', 'alternate')
+        if attrs_d['rel'] == 'self':
+            attrs_d.setdefault('type', 'application/atom+xml')
+        else:
+            attrs_d.setdefault('type', 'text/html')
+        context = self._get_context()
+        attrs_d = self._enforce_href(attrs_d)
+        if 'href' in attrs_d:
+            attrs_d['href'] = self.resolve_uri(attrs_d['href'])
+        expecting_text = self.infeed or self.inentry or self.insource
+        context.setdefault('links', [])
+        if not (self.inentry and self.inimage):
+            context['links'].append(FeedParserDict(attrs_d))
+        if 'href' in attrs_d:
+            if (
+                    attrs_d.get('rel') == 'alternate'
+                    and self.map_content_type(attrs_d.get('type')) in self.html_types
+            ):
+                context['link'] = attrs_d['href']
+        else:
+            self.push('link', expecting_text)
+
+    def _end_link(self):
+        self.pop('link')
+
+    def _start_guid(self, attrs_d):
+        self.guidislink = (attrs_d.get('ispermalink', 'true') == 'true')
+        self.push('id', 1)
+    _start_id = _start_guid
+
+    def _end_guid(self):
+        value = self.pop('id')
+        self._save('guidislink', self.guidislink and 'link' not in self._get_context())
+        if self.guidislink:
+            # guid acts as link, but only if 'ispermalink' is not present or is 'true',
+            # and only if the item doesn't already have a link element
+            self._save('link', value)
+    _end_id = _end_guid
+
+    def _start_title(self, attrs_d):
+        if self.svgOK:
+            return self.unknown_starttag('title', list(attrs_d.items()))
+        self.push_content('title', attrs_d, 'text/plain', self.infeed or self.inentry or self.insource)
+
+    def _end_title(self):
+        if self.svgOK:
+            return
+        value = self.pop_content('title')
+        if not value:
+            return
+        self.title_depth = self.depth
+
+    def _start_description(self, attrs_d):
+        context = self._get_context()
+        if 'summary' in context and not self.hasContent:
+            self._summaryKey = 'content'
+            self._start_content(attrs_d)
+        else:
+            self.push_content('description', attrs_d, 'text/html', self.infeed or self.inentry or self.insource)
+
+    def _start_abstract(self, attrs_d):
+        self.push_content('description', attrs_d, 'text/plain', self.infeed or self.inentry or self.insource)
+
+    def _end_description(self):
+        if self._summaryKey == 'content':
+            self._end_content()
+        else:
+            self.pop_content('description')
+        self._summaryKey = None
+    _end_abstract = _end_description
+
+    def _start_info(self, attrs_d):
+        self.push_content('info', attrs_d, 'text/plain', 1)
+    _start_feedburner_browserfriendly = _start_info
+
+    def _end_info(self):
+        self.pop_content('info')
+    _end_feedburner_browserfriendly = _end_info
+
+    def _start_generator(self, attrs_d):
+        if attrs_d:
+            attrs_d = self._enforce_href(attrs_d)
+            if 'href' in attrs_d:
+                attrs_d['href'] = self.resolve_uri(attrs_d['href'])
+        self._get_context()['generator_detail'] = FeedParserDict(attrs_d)
+        self.push('generator', 1)
+
+    def _end_generator(self):
+        value = self.pop('generator')
+        context = self._get_context()
+        if 'generator_detail' in context:
+            context['generator_detail']['name'] = value
+
+    def _start_summary(self, attrs_d):
+        context = self._get_context()
+        if 'summary' in context and not self.hasContent:
+            self._summaryKey = 'content'
+            self._start_content(attrs_d)
+        else:
+            self._summaryKey = 'summary'
+            self.push_content(self._summaryKey, attrs_d, 'text/plain', 1)
+
+    def _end_summary(self):
+        if self._summaryKey == 'content':
+            self._end_content()
+        else:
+            self.pop_content(self._summaryKey or 'summary')
+        self._summaryKey = None
+
+    def _start_enclosure(self, attrs_d):
+        attrs_d = self._enforce_href(attrs_d)
+        context = self._get_context()
+        attrs_d['rel'] = 'enclosure'
+        context.setdefault('links', []).append(FeedParserDict(attrs_d))
+
+    def _start_source(self, attrs_d):
+        if 'url' in attrs_d:
+            # This means that we're processing a source element from an RSS 2.0 feed
+            self.sourcedata['href'] = attrs_d['url']
+        self.push('source', 1)
+        self.insource = 1
+        self.title_depth = -1
+
+    def _end_source(self):
+        self.insource = 0
+        value = self.pop('source')
+        if value:
+            self.sourcedata['title'] = value
+        self._get_context()['source'] = copy.deepcopy(self.sourcedata)
+        self.sourcedata.clear()
+
+    def _start_content(self, attrs_d):
+        self.hasContent = 1
+        self.push_content('content', attrs_d, 'text/plain', 1)
+        src = attrs_d.get('src')
+        if src:
+            self.contentparams['src'] = src
+        self.push('content', 1)
+
+    def _start_body(self, attrs_d):
+        self.push_content('content', attrs_d, 'application/xhtml+xml', 1)
+    _start_xhtml_body = _start_body
+
+    def _start_content_encoded(self, attrs_d):
+        self.hasContent = 1
+        self.push_content('content', attrs_d, 'text/html', 1)
+    _start_fullitem = _start_content_encoded
+
+    def _end_content(self):
+        copyToSummary = self.map_content_type(self.contentparams.get('type')) in ({'text/plain'} | self.html_types)
+        value = self.pop_content('content')
+        if copyToSummary:
+            self._save('summary', value)
+
+    _end_body = _end_content
+    _end_xhtml_body = _end_content
+    _end_content_encoded = _end_content
+    _end_fullitem = _end_content
+
+    def _start_newlocation(self, attrs_d):
+        self.push('newlocation', 1)
+
+    def _end_newlocation(self):
+        url = self.pop('newlocation')
+        context = self._get_context()
+        # don't set newlocation if the context isn't right
+        if context is not self.feeddata:
+            return
+        context['newlocation'] = make_safe_absolute_uri(self.baseuri, url.strip())

venv/lib/python3.12/site-packages/feedparser/namespaces/admin.py

@@ -0,0 +1,53 @@
+# Support for the administrative elements extension
+# Copyright 2010-2023 Kurt McKee <contactme@kurtmckee.org>
+# Copyright 2002-2008 Mark Pilgrim
+# All rights reserved.
+#
+# This file is a part of feedparser.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# * Redistributions of source code must retain the above copyright notice,
+#   this list of conditions and the following disclaimer.
+# * Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+from ..util import FeedParserDict
+
+
+class Namespace(object):
+    # RDF Site Summary 1.0 Modules: Administrative
+    # http://web.resource.org/rss/1.0/modules/admin/
+
+    supported_namespaces = {
+        'http://webns.net/mvcb/': 'admin',
+    }
+
+    def _start_admin_generatoragent(self, attrs_d):
+        self.push('generator', 1)
+        value = self._get_attribute(attrs_d, 'rdf:resource')
+        if value:
+            self.elementstack[-1][2].append(value)
+        self.pop('generator')
+        self._get_context()['generator_detail'] = FeedParserDict({'href': value})
+
+    def _start_admin_errorreportsto(self, attrs_d):
+        self.push('errorreportsto', 1)
+        value = self._get_attribute(attrs_d, 'rdf:resource')
+        if value:
+            self.elementstack[-1][2].append(value)
+        self.pop('errorreportsto')

venv/lib/python3.12/site-packages/feedparser/namespaces/cc.py

@@ -0,0 +1,69 @@
+# Support for the Creative Commons licensing extensions
+# Copyright 2010-2023 Kurt McKee <contactme@kurtmckee.org>
+# Copyright 2002-2008 Mark Pilgrim
+# All rights reserved.
+#
+# This file is a part of feedparser.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# * Redistributions of source code must retain the above copyright notice,
+#   this list of conditions and the following disclaimer.
+# * Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+from ..util import FeedParserDict
+
+
+class Namespace(object):
+    supported_namespaces = {
+        # RDF-based namespace
+        'http://creativecommons.org/ns#license': 'cc',
+
+        # Old RDF-based namespace
+        'http://web.resource.org/cc/': 'cc',
+
+        # RSS-based namespace
+        'http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html': 'creativecommons',
+
+        # Old RSS-based namespace
+        'http://backend.userland.com/creativeCommonsRssModule': 'creativecommons',
+    }
+
+    def _start_cc_license(self, attrs_d):
+        context = self._get_context()
+        value = self._get_attribute(attrs_d, 'rdf:resource')
+        attrs_d = FeedParserDict()
+        attrs_d['rel'] = 'license'
+        if value:
+            attrs_d['href'] = value
+        context.setdefault('links', []).append(attrs_d)
+
+    def _start_creativecommons_license(self, attrs_d):
+        self.push('license', 1)
+    _start_creativeCommons_license = _start_creativecommons_license
+
+    def _end_creativecommons_license(self):
+        value = self.pop('license')
+        context = self._get_context()
+        attrs_d = FeedParserDict()
+        attrs_d['rel'] = 'license'
+        if value:
+            attrs_d['href'] = value
+        context.setdefault('links', []).append(attrs_d)
+        del context['license']
+    _end_creativeCommons_license = _end_creativecommons_license

venv/lib/python3.12/site-packages/feedparser/namespaces/dc.py

@@ -0,0 +1,134 @@
+# Support for the Dublin Core metadata extensions
+# Copyright 2010-2023 Kurt McKee <contactme@kurtmckee.org>
+# Copyright 2002-2008 Mark Pilgrim
+# All rights reserved.
+#
+# This file is a part of feedparser.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# * Redistributions of source code must retain the above copyright notice,
+#   this list of conditions and the following disclaimer.
+# * Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+from ..datetimes import _parse_date
+from ..util import FeedParserDict
+
+
+class Namespace(object):
+    supported_namespaces = {
+        'http://purl.org/dc/elements/1.1/': 'dc',
+        'http://purl.org/dc/terms/': 'dcterms',
+    }
+
+    def _end_dc_author(self):
+        self._end_author()
+
+    def _end_dc_creator(self):
+        self._end_author()
+
+    def _end_dc_date(self):
+        self._end_updated()
+
+    def _end_dc_description(self):
+        self._end_description()
+
+    def _end_dc_language(self):
+        self._end_language()
+
+    def _end_dc_publisher(self):
+        self._end_webmaster()
+
+    def _end_dc_rights(self):
+        self._end_rights()
+
+    def _end_dc_subject(self):
+        self._end_category()
+
+    def _end_dc_title(self):
+        self._end_title()
+
+    def _end_dcterms_created(self):
+        self._end_created()
+
+    def _end_dcterms_issued(self):
+        self._end_published()
+
+    def _end_dcterms_modified(self):
+        self._end_updated()
+
+    def _start_dc_author(self, attrs_d):
+        self._start_author(attrs_d)
+
+    def _start_dc_creator(self, attrs_d):
+        self._start_author(attrs_d)
+
+    def _start_dc_date(self, attrs_d):
+        self._start_updated(attrs_d)
+
+    def _start_dc_description(self, attrs_d):
+        self._start_description(attrs_d)
+
+    def _start_dc_language(self, attrs_d):
+        self._start_language(attrs_d)
+
+    def _start_dc_publisher(self, attrs_d):
+        self._start_webmaster(attrs_d)
+
+    def _start_dc_rights(self, attrs_d):
+        self._start_rights(attrs_d)
+
+    def _start_dc_subject(self, attrs_d):
+        self._start_category(attrs_d)
+
+    def _start_dc_title(self, attrs_d):
+        self._start_title(attrs_d)
+
+    def _start_dcterms_created(self, attrs_d):
+        self._start_created(attrs_d)
+
+    def _start_dcterms_issued(self, attrs_d):
+        self._start_published(attrs_d)
+
+    def _start_dcterms_modified(self, attrs_d):
+        self._start_updated(attrs_d)
+
+    def _start_dcterms_valid(self, attrs_d):
+        self.push('validity', 1)
+
+    def _end_dcterms_valid(self):
+        for validity_detail in self.pop('validity').split(';'):
+            if '=' in validity_detail:
+                key, value = validity_detail.split('=', 1)
+                if key == 'start':
+                    self._save('validity_start', value, overwrite=True)
+                    self._save('validity_start_parsed', _parse_date(value), overwrite=True)
+                elif key == 'end':
+                    self._save('validity_end', value, overwrite=True)
+                    self._save('validity_end_parsed', _parse_date(value), overwrite=True)
+
+    def _start_dc_contributor(self, attrs_d):
+        self.incontributor = 1
+        context = self._get_context()
+        context.setdefault('contributors', [])
+        context['contributors'].append(FeedParserDict())
+        self.push('name', 0)
+
+    def _end_dc_contributor(self):
+        self._end_name()
+        self.incontributor = 0

venv/lib/python3.12/site-packages/feedparser/namespaces/georss.py

@@ -0,0 +1,278 @@
+# Support for the GeoRSS format
+# Copyright 2010-2023 Kurt McKee <contactme@kurtmckee.org>
+# Copyright 2002-2008 Mark Pilgrim
+# All rights reserved.
+#
+# This file is a part of feedparser.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# * Redistributions of source code must retain the above copyright notice,
+#   this list of conditions and the following disclaimer.
+# * Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+# Required for Python 3.6 compatibility.
+from __future__ import generator_stop
+
+from ..util import FeedParserDict
+
+
+class Namespace(object):
+    supported_namespaces = {
+        'http://www.w3.org/2003/01/geo/wgs84_pos#': 'geo',
+        'http://www.georss.org/georss': 'georss',
+        'http://www.opengis.net/gml': 'gml',
+    }
+
+    def __init__(self):
+        self.ingeometry = 0
+        super(Namespace, self).__init__()
+
+    def _start_georssgeom(self, attrs_d):
+        self.push('geometry', 0)
+        context = self._get_context()
+        context['where'] = FeedParserDict()
+
+    _start_georss_point = _start_georssgeom
+    _start_georss_line = _start_georssgeom
+    _start_georss_polygon = _start_georssgeom
+    _start_georss_box = _start_georssgeom
+
+    def _save_where(self, geometry):
+        context = self._get_context()
+        context['where'].update(geometry)
+
+    def _end_georss_point(self):
+        geometry = _parse_georss_point(self.pop('geometry'))
+        if geometry:
+            self._save_where(geometry)
+
+    def _end_georss_line(self):
+        geometry = _parse_georss_line(self.pop('geometry'))
+        if geometry:
+            self._save_where(geometry)
+
+    def _end_georss_polygon(self):
+        this = self.pop('geometry')
+        geometry = _parse_georss_polygon(this)
+        if geometry:
+            self._save_where(geometry)
+
+    def _end_georss_box(self):
+        geometry = _parse_georss_box(self.pop('geometry'))
+        if geometry:
+            self._save_where(geometry)
+
+    def _start_where(self, attrs_d):
+        self.push('where', 0)
+        context = self._get_context()
+        context['where'] = FeedParserDict()
+    _start_georss_where = _start_where
+
+    def _parse_srs_attrs(self, attrs_d):
+        srs_name = attrs_d.get('srsname')
+        try:
+            srs_dimension = int(attrs_d.get('srsdimension', '2'))
+        except ValueError:
+            srs_dimension = 2
+        context = self._get_context()
+        if 'where' not in context:
+            context['where'] = {}
+        context['where']['srsName'] = srs_name
+        context['where']['srsDimension'] = srs_dimension
+
+    def _start_gml_point(self, attrs_d):
+        self._parse_srs_attrs(attrs_d)
+        self.ingeometry = 1
+        self.push('geometry', 0)
+
+    def _start_gml_linestring(self, attrs_d):
+        self._parse_srs_attrs(attrs_d)
+        self.ingeometry = 'linestring'
+        self.push('geometry', 0)
+
+    def _start_gml_polygon(self, attrs_d):
+        self._parse_srs_attrs(attrs_d)
+        self.push('geometry', 0)
+
+    def _start_gml_exterior(self, attrs_d):
+        self.push('geometry', 0)
+
+    def _start_gml_linearring(self, attrs_d):
+        self.ingeometry = 'polygon'
+        self.push('geometry', 0)
+
+    def _start_gml_pos(self, attrs_d):
+        self.push('pos', 0)
+
+    def _end_gml_pos(self):
+        this = self.pop('pos')
+        context = self._get_context()
+        srs_name = context['where'].get('srsName')
+        srs_dimension = context['where'].get('srsDimension', 2)
+        swap = True
+        if srs_name and "EPSG" in srs_name:
+            epsg = int(srs_name.split(":")[-1])
+            swap = bool(epsg in _geogCS)
+        geometry = _parse_georss_point(this, swap=swap, dims=srs_dimension)
+        if geometry:
+            self._save_where(geometry)
+
+    def _start_gml_poslist(self, attrs_d):
+        self.push('pos', 0)
+
+    def _end_gml_poslist(self):
+        this = self.pop('pos')
+        context = self._get_context()
+        srs_name = context['where'].get('srsName')
+        srs_dimension = context['where'].get('srsDimension', 2)
+        swap = True
+        if srs_name and "EPSG" in srs_name:
+            epsg = int(srs_name.split(":")[-1])
+            swap = bool(epsg in _geogCS)
+        geometry = _parse_poslist(
+            this, self.ingeometry, swap=swap, dims=srs_dimension)
+        if geometry:
+            self._save_where(geometry)
+
+    def _end_geom(self):
+        self.ingeometry = 0
+        self.pop('geometry')
+    _end_gml_point = _end_geom
+    _end_gml_linestring = _end_geom
+    _end_gml_linearring = _end_geom
+    _end_gml_exterior = _end_geom
+    _end_gml_polygon = _end_geom
+
+    def _end_where(self):
+        self.pop('where')
+    _end_georss_where = _end_where
+
+
+# GeoRSS geometry parsers. Each return a dict with 'type' and 'coordinates'
+# items, or None in the case of a parsing error.
+
+def _parse_poslist(value, geom_type, swap=True, dims=2):
+    if geom_type == 'linestring':
+        return _parse_georss_line(value, swap, dims)
+    elif geom_type == 'polygon':
+        ring = _parse_georss_line(value, swap, dims)
+        return {'type': 'Polygon', 'coordinates': (ring['coordinates'],)}
+    else:
+        return None
+
+
+def _gen_georss_coords(value, swap=True, dims=2):
+    # A generator of (lon, lat) pairs from a string of encoded GeoRSS
+    # coordinates. Converts to floats and swaps order.
+    latlons = (float(ll) for ll in value.replace(',', ' ').split())
+    while True:
+        try:
+            t = [next(latlons), next(latlons)][::swap and -1 or 1]
+            if dims == 3:
+                t.append(next(latlons))
+            yield tuple(t)
+        except StopIteration:
+            return
+
+
+def _parse_georss_point(value, swap=True, dims=2):
+    # A point contains a single latitude-longitude pair, separated by
+    # whitespace. We'll also handle comma separators.
+    try:
+        coords = list(_gen_georss_coords(value, swap, dims))
+        return {'type': 'Point', 'coordinates': coords[0]}
+    except (IndexError, ValueError):
+        return None
+
+
+def _parse_georss_line(value, swap=True, dims=2):
+    # A line contains a space separated list of latitude-longitude pairs in
+    # WGS84 coordinate reference system, with each pair separated by
+    # whitespace. There must be at least two pairs.
+    try:
+        coords = list(_gen_georss_coords(value, swap, dims))
+        return {'type': 'LineString', 'coordinates': coords}
+    except (IndexError, ValueError):
+        return None
+
+
+def _parse_georss_polygon(value, swap=True, dims=2):
+    # A polygon contains a space separated list of latitude-longitude pairs,
+    # with each pair separated by whitespace. There must be at least four
+    # pairs, with the last being identical to the first (so a polygon has a
+    # minimum of three actual points).
+    try:
+        ring = list(_gen_georss_coords(value, swap, dims))
+    except (IndexError, ValueError):
+        return None
+    if len(ring) < 4:
+        return None
+    return {'type': 'Polygon', 'coordinates': (ring,)}
+
+
+def _parse_georss_box(value, swap=True, dims=2):
+    # A bounding box is a rectangular region, often used to define the extents
+    # of a map or a rough area of interest. A box contains two space separate
+    # latitude-longitude pairs, with each pair separated by whitespace. The
+    # first pair is the lower corner, the second is the upper corner.
+    try:
+        coords = list(_gen_georss_coords(value, swap, dims))
+        return {'type': 'Box', 'coordinates': tuple(coords)}
+    except (IndexError, ValueError):
+        return None
+
+
+# The list of EPSG codes for geographic (latitude/longitude) coordinate
+# systems to support decoding of GeoRSS GML profiles.
+_geogCS = [
+    3819, 3821, 3824, 3889, 3906, 4001, 4002, 4003, 4004, 4005, 4006, 4007, 4008,
+    4009, 4010, 4011, 4012, 4013, 4014, 4015, 4016, 4018, 4019, 4020, 4021, 4022,
+    4023, 4024, 4025, 4027, 4028, 4029, 4030, 4031, 4032, 4033, 4034, 4035, 4036,
+    4041, 4042, 4043, 4044, 4045, 4046, 4047, 4052, 4053, 4054, 4055, 4075, 4081,
+    4120, 4121, 4122, 4123, 4124, 4125, 4126, 4127, 4128, 4129, 4130, 4131, 4132,
+    4133, 4134, 4135, 4136, 4137, 4138, 4139, 4140, 4141, 4142, 4143, 4144, 4145,
+    4146, 4147, 4148, 4149, 4150, 4151, 4152, 4153, 4154, 4155, 4156, 4157, 4158,
+    4159, 4160, 4161, 4162, 4163, 4164, 4165, 4166, 4167, 4168, 4169, 4170, 4171,
+    4172, 4173, 4174, 4175, 4176, 4178, 4179, 4180, 4181, 4182, 4183, 4184, 4185,
+    4188, 4189, 4190, 4191, 4192, 4193, 4194, 4195, 4196, 4197, 4198, 4199, 4200,
+    4201, 4202, 4203, 4204, 4205, 4206, 4207, 4208, 4209, 4210, 4211, 4212, 4213,
+    4214, 4215, 4216, 4218, 4219, 4220, 4221, 4222, 4223, 4224, 4225, 4226, 4227,
+    4228, 4229, 4230, 4231, 4232, 4233, 4234, 4235, 4236, 4237, 4238, 4239, 4240,
+    4241, 4242, 4243, 4244, 4245, 4246, 4247, 4248, 4249, 4250, 4251, 4252, 4253,
+    4254, 4255, 4256, 4257, 4258, 4259, 4260, 4261, 4262, 4263, 4264, 4265, 4266,
+    4267, 4268, 4269, 4270, 4271, 4272, 4273, 4274, 4275, 4276, 4277, 4278, 4279,
+    4280, 4281, 4282, 4283, 4284, 4285, 4286, 4287, 4288, 4289, 4291, 4292, 4293,
+    4294, 4295, 4296, 4297, 4298, 4299, 4300, 4301, 4302, 4303, 4304, 4306, 4307,
+    4308, 4309, 4310, 4311, 4312, 4313, 4314, 4315, 4316, 4317, 4318, 4319, 4322,
+    4324, 4326, 4463, 4470, 4475, 4483, 4490, 4555, 4558, 4600, 4601, 4602, 4603,
+    4604, 4605, 4606, 4607, 4608, 4609, 4610, 4611, 4612, 4613, 4614, 4615, 4616,
+    4617, 4618, 4619, 4620, 4621, 4622, 4623, 4624, 4625, 4626, 4627, 4628, 4629,
+    4630, 4631, 4632, 4633, 4634, 4635, 4636, 4637, 4638, 4639, 4640, 4641, 4642,
+    4643, 4644, 4645, 4646, 4657, 4658, 4659, 4660, 4661, 4662, 4663, 4664, 4665,
+    4666, 4667, 4668, 4669, 4670, 4671, 4672, 4673, 4674, 4675, 4676, 4677, 4678,
+    4679, 4680, 4681, 4682, 4683, 4684, 4685, 4686, 4687, 4688, 4689, 4690, 4691,
+    4692, 4693, 4694, 4695, 4696, 4697, 4698, 4699, 4700, 4701, 4702, 4703, 4704,
+    4705, 4706, 4707, 4708, 4709, 4710, 4711, 4712, 4713, 4714, 4715, 4716, 4717,
+    4718, 4719, 4720, 4721, 4722, 4723, 4724, 4725, 4726, 4727, 4728, 4729, 4730,
+    4731, 4732, 4733, 4734, 4735, 4736, 4737, 4738, 4739, 4740, 4741, 4742, 4743,
+    4744, 4745, 4746, 4747, 4748, 4749, 4750, 4751, 4752, 4753, 4754, 4755, 4756,
+    4757, 4758, 4759, 4760, 4761, 4762, 4763, 4764, 4765, 4801, 4802, 4803, 4804,
+    4805, 4806, 4807, 4808, 4809, 4810, 4811, 4813, 4814, 4815, 4816, 4817, 4818,
+    4819, 4820, 4821, 4823, 4824, 4901, 4902, 4903, 4904, 4979,
+]

venv/lib/python3.12/site-packages/feedparser/namespaces/itunes.py

@@ -0,0 +1,109 @@
+# Support for the iTunes format
+# Copyright 2010-2023 Kurt McKee <contactme@kurtmckee.org>
+# Copyright 2002-2008 Mark Pilgrim
+# All rights reserved.
+#
+# This file is a part of feedparser.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# * Redistributions of source code must retain the above copyright notice,
+#   this list of conditions and the following disclaimer.
+# * Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+from ..util import FeedParserDict
+
+
+class Namespace(object):
+    supported_namespaces = {
+        # Canonical namespace
+        'http://www.itunes.com/DTDs/PodCast-1.0.dtd': 'itunes',
+
+        # Extra namespace
+        'http://example.com/DTDs/PodCast-1.0.dtd': 'itunes',
+    }
+
+    def _start_itunes_author(self, attrs_d):
+        self._start_author(attrs_d)
+
+    def _end_itunes_author(self):
+        self._end_author()
+
+    def _end_itunes_category(self):
+        self._end_category()
+
+    def _start_itunes_name(self, attrs_d):
+        self._start_name(attrs_d)
+
+    def _end_itunes_name(self):
+        self._end_name()
+
+    def _start_itunes_email(self, attrs_d):
+        self._start_email(attrs_d)
+
+    def _end_itunes_email(self):
+        self._end_email()
+
+    def _start_itunes_subtitle(self, attrs_d):
+        self._start_subtitle(attrs_d)
+
+    def _end_itunes_subtitle(self):
+        self._end_subtitle()
+
+    def _start_itunes_summary(self, attrs_d):
+        self._start_summary(attrs_d)
+
+    def _end_itunes_summary(self):
+        self._end_summary()
+
+    def _start_itunes_owner(self, attrs_d):
+        self.inpublisher = 1
+        self.push('publisher', 0)
+
+    def _end_itunes_owner(self):
+        self.pop('publisher')
+        self.inpublisher = 0
+        self._sync_author_detail('publisher')
+
+    def _end_itunes_keywords(self):
+        for term in self.pop('itunes_keywords').split(','):
+            if term.strip():
+                self._add_tag(term.strip(), 'http://www.itunes.com/', None)
+
+    def _start_itunes_category(self, attrs_d):
+        self._add_tag(attrs_d.get('text'), 'http://www.itunes.com/', None)
+        self.push('category', 1)
+
+    def _start_itunes_image(self, attrs_d):
+        self.push('itunes_image', 0)
+        if attrs_d.get('href'):
+            self._get_context()['image'] = FeedParserDict({'href': attrs_d.get('href')})
+        elif attrs_d.get('url'):
+            self._get_context()['image'] = FeedParserDict({'href': attrs_d.get('url')})
+    _start_itunes_link = _start_itunes_image
+
+    def _end_itunes_block(self):
+        value = self.pop('itunes_block', 0)
+        self._get_context()['itunes_block'] = (value == 'yes' or value == 'Yes') and 1 or 0
+
+    def _end_itunes_explicit(self):
+        value = self.pop('itunes_explicit', 0)
+        # Convert 'yes' -> True, 'clean' to False, and any other value to None
+        # False and None both evaluate as False, so the difference can be ignored
+        # by applications that only need to know if the content is explicit.
+        self._get_context()['itunes_explicit'] = (None, False, True)[(value == 'yes' and 2) or value == 'clean' or 0]

venv/lib/python3.12/site-packages/feedparser/namespaces/mediarss.py

@@ -0,0 +1,141 @@
+# Support for the Media RSS format
+# Copyright 2010-2023 Kurt McKee <contactme@kurtmckee.org>
+# Copyright 2002-2008 Mark Pilgrim
+# All rights reserved.
+#
+# This file is a part of feedparser.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# * Redistributions of source code must retain the above copyright notice,
+#   this list of conditions and the following disclaimer.
+# * Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+from ..util import FeedParserDict
+
+
+class Namespace(object):
+    supported_namespaces = {
+        # Canonical namespace
+        'http://search.yahoo.com/mrss/': 'media',
+
+        # Old namespace (no trailing slash)
+        'http://search.yahoo.com/mrss': 'media',
+    }
+
+    def _start_media_category(self, attrs_d):
+        attrs_d.setdefault('scheme', 'http://search.yahoo.com/mrss/category_schema')
+        self._start_category(attrs_d)
+
+    def _end_media_category(self):
+        self._end_category()
+
+    def _end_media_keywords(self):
+        for term in self.pop('media_keywords').split(','):
+            if term.strip():
+                self._add_tag(term.strip(), None, None)
+
+    def _start_media_title(self, attrs_d):
+        self._start_title(attrs_d)
+
+    def _end_media_title(self):
+        title_depth = self.title_depth
+        self._end_title()
+        self.title_depth = title_depth
+
+    def _start_media_group(self, attrs_d):
+        # don't do anything, but don't break the enclosed tags either
+        pass
+
+    def _start_media_rating(self, attrs_d):
+        context = self._get_context()
+        context.setdefault('media_rating', attrs_d)
+        self.push('rating', 1)
+
+    def _end_media_rating(self):
+        rating = self.pop('rating')
+        if rating is not None and rating.strip():
+            context = self._get_context()
+            context['media_rating']['content'] = rating
+
+    def _start_media_credit(self, attrs_d):
+        context = self._get_context()
+        context.setdefault('media_credit', [])
+        context['media_credit'].append(attrs_d)
+        self.push('credit', 1)
+
+    def _end_media_credit(self):
+        credit = self.pop('credit')
+        if credit is not None and credit.strip():
+            context = self._get_context()
+            context['media_credit'][-1]['content'] = credit
+
+    def _start_media_description(self, attrs_d):
+        self._start_description(attrs_d)
+
+    def _end_media_description(self):
+        self._end_description()
+
+    def _start_media_restriction(self, attrs_d):
+        context = self._get_context()
+        context.setdefault('media_restriction', attrs_d)
+        self.push('restriction', 1)
+
+    def _end_media_restriction(self):
+        restriction = self.pop('restriction')
+        if restriction is not None and restriction.strip():
+            context = self._get_context()
+            context['media_restriction']['content'] = [cc.strip().lower() for cc in restriction.split(' ')]
+
+    def _start_media_license(self, attrs_d):
+        context = self._get_context()
+        context.setdefault('media_license', attrs_d)
+        self.push('license', 1)
+
+    def _end_media_license(self):
+        license_ = self.pop('license')
+        if license_ is not None and license_.strip():
+            context = self._get_context()
+            context['media_license']['content'] = license_
+
+    def _start_media_content(self, attrs_d):
+        context = self._get_context()
+        context.setdefault('media_content', [])
+        context['media_content'].append(attrs_d)
+
+    def _start_media_thumbnail(self, attrs_d):
+        context = self._get_context()
+        context.setdefault('media_thumbnail', [])
+        self.push('url', 1) # new
+        context['media_thumbnail'].append(attrs_d)
+
+    def _end_media_thumbnail(self):
+        url = self.pop('url')
+        context = self._get_context()
+        if url is not None and url.strip():
+            if 'url' not in context['media_thumbnail'][-1]:
+                context['media_thumbnail'][-1]['url'] = url
+
+    def _start_media_player(self, attrs_d):
+        self.push('media_player', 0)
+        self._get_context()['media_player'] = FeedParserDict(attrs_d)
+
+    def _end_media_player(self):
+        value = self.pop('media_player')
+        context = self._get_context()
+        context['media_player']['content'] = value

venv/lib/python3.12/site-packages/feedparser/namespaces/psc.py

@@ -0,0 +1,74 @@
+# Support for the Podlove Simple Chapters format
+# Copyright 2010-2023 Kurt McKee <contactme@kurtmckee.org>
+# Copyright 2002-2008 Mark Pilgrim
+# All rights reserved.
+#
+# This file is a part of feedparser.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# * Redistributions of source code must retain the above copyright notice,
+#   this list of conditions and the following disclaimer.
+# * Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+import datetime
+import re
+
+from .. import util
+
+
+class Namespace(object):
+    supported_namespaces = {
+        'http://podlove.org/simple-chapters': 'psc',
+    }
+
+    def __init__(self):
+        # chapters will only be captured while psc_chapters_flag is True.
+        self.psc_chapters_flag = False
+        super(Namespace, self).__init__()
+
+    def _start_psc_chapters(self, attrs_d):
+        context = self._get_context()
+        if 'psc_chapters' not in context:
+            self.psc_chapters_flag = True
+            attrs_d['chapters'] = []
+            context['psc_chapters'] = util.FeedParserDict(attrs_d)
+
+    def _end_psc_chapters(self):
+        self.psc_chapters_flag = False
+
+    def _start_psc_chapter(self, attrs_d):
+        if self.psc_chapters_flag:
+            start = self._get_attribute(attrs_d, 'start')
+            attrs_d['start_parsed'] = _parse_psc_chapter_start(start)
+
+            context = self._get_context()['psc_chapters']
+            context['chapters'].append(util.FeedParserDict(attrs_d))
+
+
+format_ = re.compile(r'^((\d{2}):)?(\d{2}):(\d{2})(\.(\d{3}))?$')
+
+
+def _parse_psc_chapter_start(start):
+    m = format_.match(start)
+    if m is None:
+        return None
+
+    _, h, m, s, _, ms = m.groups()
+    h, m, s, ms = (int(h or 0), int(m), int(s), int(ms or 0))
+    return datetime.timedelta(0, h*60*60 + m*60 + s, ms*1000)