diff --git a/mypy.ini b/mypy.ini
index c84a7e7..8aab2fa 100644
--- a/mypy.ini
+++ b/mypy.ini
@@ -1,41 +1,38 @@
 [mypy]
 namespace_packages = True
 warn_unused_ignores = True
 
 # 3rd party libraries without stubs (yet)
 
 [mypy-bs4.*]
 ignore_missing_imports = True
 
 [mypy-celery.*]
 ignore_missing_imports = True
 
 [mypy-debian.*]
 ignore_missing_imports = True
 
 [mypy-iso8601.*]
 ignore_missing_imports = True
 
 [mypy-launchpadlib.*]
 ignore_missing_imports = True
 
 [mypy-lazr.*]
 ignore_missing_imports = True
 
 [mypy-pkg_resources.*]
 ignore_missing_imports = True
 
 [mypy-pytest.*]
 ignore_missing_imports = True
 
 [mypy-pytest_postgresql.*]
 ignore_missing_imports = True
 
 [mypy-requests_mock.*]
 ignore_missing_imports = True
 
 [mypy-urllib3.util.*]
 ignore_missing_imports = True
-
-[mypy-xmltodict.*]
-ignore_missing_imports = True
diff --git a/requirements.txt b/requirements.txt
index 34bf339..4f6c24e 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,8 +1,7 @@
 python_debian
 requests
 setuptools
-xmltodict
 iso8601
 beautifulsoup4
 launchpadlib
 tenacity
diff --git a/swh/lister/pypi/lister.py b/swh/lister/pypi/lister.py
index ae9874b..ad52e22 100644
--- a/swh/lister/pypi/lister.py
+++ b/swh/lister/pypi/lister.py
@@ -1,76 +1,77 @@
 # Copyright (C) 2018-2021 The Software Heritage developers
 # See the AUTHORS file at the top-level directory of this distribution
 # License: GNU General Public License version 3, or any later version
 # See top-level LICENSE file for more information
 
 import logging
 from typing import Iterator, List, Optional
 
+from bs4 import BeautifulSoup
 import requests
-import xmltodict
 
 from swh.scheduler.interface import SchedulerInterface
 from swh.scheduler.model import ListedOrigin
 
 from .. import USER_AGENT
 from ..pattern import CredentialsType, StatelessLister
 
 logger = logging.getLogger(__name__)
 
 PackageListPage = List[str]
 
 
 class PyPILister(StatelessLister[PackageListPage]):
     """List origins from PyPI.
 
     """
 
     LISTER_NAME = "pypi"
     INSTANCE = "pypi"  # As of today only the main pypi.org is used
 
     PACKAGE_LIST_URL = "https://pypi.org/simple/"
     PACKAGE_URL = "https://pypi.org/project/{package_name}/"
 
     def __init__(
         self,
         scheduler: SchedulerInterface,
         credentials: Optional[CredentialsType] = None,
     ):
         super().__init__(
             scheduler=scheduler,
             url=self.PACKAGE_LIST_URL,
             instance=self.INSTANCE,
             credentials=credentials,
         )
 
         self.session = requests.Session()
         self.session.headers.update(
             {"Accept": "application/html", "User-Agent": USER_AGENT}
         )
 
     def get_pages(self) -> Iterator[PackageListPage]:
 
         response = self.session.get(self.PACKAGE_LIST_URL)
 
         response.raise_for_status()
 
-        page_xmldict = xmltodict.parse(response.content)
-        page_results = [p["#text"] for p in page_xmldict["html"]["body"]["a"]]
+        page = BeautifulSoup(response.content, features="html.parser")
+
+        page_results = [p.text for p in page.find_all("a")]
 
         yield page_results
 
     def get_origins_from_page(
         self, packages_name: PackageListPage
     ) -> Iterator[ListedOrigin]:
         """Convert a page of PyPI repositories into a list of ListedOrigins."""
         assert self.lister_obj.id is not None
 
         for package_name in packages_name:
             package_url = self.PACKAGE_URL.format(package_name=package_name)
 
             yield ListedOrigin(
                 lister_id=self.lister_obj.id,
                 url=package_url,
                 visit_type="pypi",
                 last_update=None,  # available on PyPI JSON API
             )