forkparser 2026.1.0__py3-none-any.whl

feedparser/namespaces/itunes.py

@@ -0,0 +1,113 @@
+# Support for the iTunes format
+# Copyright 2010-2025 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:
+    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
+        ]

feedparser/namespaces/mediarss.py

@@ -0,0 +1,142 @@
+# Support for the Media RSS format
+# Copyright 2010-2025 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:
+    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

feedparser/namespaces/psc.py

@@ -0,0 +1,74 @@
+# Support for the Podlove Simple Chapters format
+# Copyright 2010-2025 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:
+    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().__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)

feedparser/parsers/json.py

@@ -0,0 +1,135 @@
+# The JSON feed parser
+# Copyright 2017 Beat Bolli
+# 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 json
+
+from ..datetimes import _parse_date
+from ..sanitizer import sanitize_html
+from ..util import FeedParserDict
+
+
+class JSONParser:
+    VERSIONS = {
+        "https://jsonfeed.org/version/1": "json1",
+        "https://jsonfeed.org/version/1.1": "json11",
+    }
+    FEED_FIELDS = (
+        ("title", "title"),
+        ("icon", "image"),
+        ("home_page_url", "link"),
+        ("description", "description"),
+    )
+    ITEM_FIELDS = (
+        ("title", "title"),
+        ("id", "guid"),
+        ("url", "link"),
+        ("summary", "summary"),
+        ("external_url", "source"),
+    )
+
+    def __init__(self, baseuri=None, baselang=None, encoding=None):
+        self.baseuri = baseuri or ""
+        self.lang = baselang or None
+        self.encoding = encoding or "utf-8"  # character encoding
+
+        self.version = None
+        self.feeddata = FeedParserDict()
+        self.namespacesInUse = []
+        self.entries = []
+
+    def feed(self, file):
+        data = json.load(file)
+
+        v = data.get("version", "")
+        try:
+            self.version = self.VERSIONS[v]
+        except KeyError:
+            raise ValueError("Unrecognized JSONFeed version '%s'" % v)
+
+        for src, dst in self.FEED_FIELDS:
+            if src in data:
+                self.feeddata[dst] = data[src]
+        if "author" in data:
+            self.parse_author(data["author"], self.feeddata)
+        # TODO: hubs; expired has no RSS equivalent
+
+        self.entries = [self.parse_entry(e) for e in data["items"]]
+
+    def parse_entry(self, e):
+        entry = FeedParserDict()
+        for src, dst in self.ITEM_FIELDS:
+            if src in e:
+                entry[dst] = e[src]
+
+        if "content_text" in e:
+            entry["content"] = c = FeedParserDict()
+            c["value"] = e["content_text"]
+            c["type"] = "text"
+        elif "content_html" in e:
+            entry["content"] = c = FeedParserDict()
+            c["value"] = sanitize_html(
+                e["content_html"], self.encoding, "application/json"
+            )
+            c["type"] = "html"
+
+        if "date_published" in e:
+            entry["published"] = e["date_published"]
+            entry["published_parsed"] = _parse_date(e["date_published"])
+        if "date_updated" in e:
+            entry["updated"] = e["date_modified"]
+            entry["updated_parsed"] = _parse_date(e["date_modified"])
+
+        if "tags" in e:
+            entry["category"] = e["tags"]
+
+        if "author" in e:
+            self.parse_author(e["author"], entry)
+
+        if "attachments" in e:
+            entry["enclosures"] = [self.parse_attachment(a) for a in e["attachments"]]
+
+        return entry
+
+    @staticmethod
+    def parse_author(parent, dest):
+        dest["author_detail"] = detail = FeedParserDict()
+        if "name" in parent:
+            dest["author"] = detail["name"] = parent["name"]
+        if "url" in parent:
+            if parent["url"].startswith("mailto:"):
+                detail["email"] = parent["url"][7:]
+            else:
+                detail["href"] = parent["url"]
+
+    @staticmethod
+    def parse_attachment(attachment):
+        enc = FeedParserDict()
+        enc["href"] = attachment["url"]
+        enc["type"] = attachment["mime_type"]
+        if "size_in_bytes" in attachment:
+            enc["length"] = attachment["size_in_bytes"]
+        return enc

feedparser/parsers/loose.py

@@ -0,0 +1,75 @@
+# The loose feed parser that interfaces with an SGML parsing library
+# Copyright 2010-2025 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.
+
+
+class LooseXMLParser:
+    contentparams = None
+
+    def __init__(self, baseuri=None, baselang=None, encoding=None, entities=None):
+        self.baseuri = baseuri or ""
+        self.lang = baselang or None
+        self.encoding = encoding or "utf-8"  # character encoding
+        self.entities = entities or {}
+        super().__init__()
+
+    @staticmethod
+    def _normalize_attributes(kv):
+        k = kv[0].lower()
+        v = k in ("rel", "type") and kv[1].lower() or kv[1]
+        # the sgml parser doesn't handle entities in attributes, nor
+        # does it pass the attribute values through as unicode, while
+        # strict xml parsers do -- account for this difference
+        v = v.replace("&amp;", "&")
+        return k, v
+
+    def decode_entities(self, element, data):
+        data = data.replace("&#60;", "&lt;")
+        data = data.replace("&#x3c;", "&lt;")
+        data = data.replace("&#x3C;", "&lt;")
+        data = data.replace("&#62;", "&gt;")
+        data = data.replace("&#x3e;", "&gt;")
+        data = data.replace("&#x3E;", "&gt;")
+        data = data.replace("&#38;", "&amp;")
+        data = data.replace("&#x26;", "&amp;")
+        data = data.replace("&#34;", "&quot;")
+        data = data.replace("&#x22;", "&quot;")
+        data = data.replace("&#39;", "&apos;")
+        data = data.replace("&#x27;", "&apos;")
+        if not self.contentparams.get("type", "xml").endswith("xml"):
+            data = data.replace("&lt;", "<")
+            data = data.replace("&gt;", ">")
+            data = data.replace("&amp;", "&")
+            data = data.replace("&quot;", '"')
+            data = data.replace("&apos;", "'")
+            data = data.replace("&#x2f;", "/")
+            data = data.replace("&#x2F;", "/")
+        return data
+
+    @staticmethod
+    def strattrs(attrs):
+        return "".join(' {}="{}"'.format(n, v.replace('"', "&quot;")) for n, v in attrs)

feedparser/parsers/strict.py

@@ -0,0 +1,141 @@
+# The strict feed parser that interfaces with an XML parsing library
+# Copyright 2010-2025 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 ..exceptions import UndeclaredNamespace
+
+
+class StrictXMLParser:
+    def __init__(self, baseuri, baselang, encoding):
+        self.bozo = 0
+        self.exc = None
+        self.decls = {}
+        self.baseuri = baseuri or ""
+        self.lang = baselang
+        self.encoding = encoding
+        super().__init__()
+
+    @staticmethod
+    def _normalize_attributes(kv):
+        k = kv[0].lower()
+        v = k in ("rel", "type") and kv[1].lower() or kv[1]
+        return k, v
+
+    def startPrefixMapping(self, prefix, uri):
+        if not uri:
+            return
+        # Jython uses '' instead of None; standardize on None
+        prefix = prefix or None
+        self.track_namespace(prefix, uri)
+        if prefix and uri == "http://www.w3.org/1999/xlink":
+            self.decls["xmlns:" + prefix] = uri
+
+    def startElementNS(self, name, qname, attrs):
+        namespace, localname = name
+        lowernamespace = str(namespace or "").lower()
+        if lowernamespace.find("backend.userland.com/rss") != -1:
+            # match any backend.userland.com namespace
+            namespace = "http://backend.userland.com/rss"
+            lowernamespace = namespace
+        if qname and qname.find(":") > 0:
+            givenprefix = qname.split(":")[0]
+        else:
+            givenprefix = None
+        prefix = self._matchnamespaces.get(lowernamespace, givenprefix)
+        if (
+            givenprefix
+            and (prefix is None or (prefix == "" and lowernamespace == ""))
+            and givenprefix not in self.namespaces_in_use
+        ):
+            raise UndeclaredNamespace(
+                "'%s' is not associated with a namespace" % givenprefix
+            )
+        localname = str(localname).lower()
+
+        # qname implementation is horribly broken in Python 2.1 (it
+        # doesn't report any), and slightly broken in Python 2.2 (it
+        # doesn't report the xml: namespace). So we match up namespaces
+        # with a known list first, and then possibly override them with
+        # the qnames the SAX parser gives us (if indeed it gives us any
+        # at all).  Thanks to MatejC for helping me test this and
+        # tirelessly telling me that it didn't work yet.
+        attrsD, self.decls = self.decls, {}
+        if localname == "math" and namespace == "http://www.w3.org/1998/Math/MathML":
+            attrsD["xmlns"] = namespace
+        if localname == "svg" and namespace == "http://www.w3.org/2000/svg":
+            attrsD["xmlns"] = namespace
+
+        if prefix:
+            localname = prefix.lower() + ":" + localname
+        elif namespace and not qname:  # Expat
+            for name, value in self.namespaces_in_use.items():
+                if name and value == namespace:
+                    localname = name + ":" + localname
+                    break
+
+        for (namespace, attrlocalname), attrvalue in attrs.items():
+            lowernamespace = (namespace or "").lower()
+            prefix = self._matchnamespaces.get(lowernamespace, "")
+            if prefix:
+                attrlocalname = prefix + ":" + attrlocalname
+            attrsD[str(attrlocalname).lower()] = attrvalue
+        for qname in attrs.getQNames():
+            attrsD[str(qname).lower()] = attrs.getValueByQName(qname)
+        localname = str(localname).lower()
+        self.unknown_starttag(localname, list(attrsD.items()))
+
+    def characters(self, text):
+        self.handle_data(text)
+
+    def endElementNS(self, name, qname):
+        namespace, localname = name
+        lowernamespace = str(namespace or "").lower()
+        if qname and qname.find(":") > 0:
+            givenprefix = qname.split(":")[0]
+        else:
+            givenprefix = ""
+        prefix = self._matchnamespaces.get(lowernamespace, givenprefix)
+        if prefix:
+            localname = prefix + ":" + localname
+        elif namespace and not qname:  # Expat
+            for name, value in self.namespaces_in_use.items():
+                if name and value == namespace:
+                    localname = name + ":" + localname
+                    break
+        localname = str(localname).lower()
+        self.unknown_endtag(localname)
+
+    def error(self, exc):
+        self.bozo = 1
+        self.exc = exc
+
+    # drv_libxml2 calls warning() in some cases
+    warning = error
+
+    def fatalError(self, exc):
+        self.error(exc)
+        raise exc