diff --git a/PKG-INFO b/PKG-INFO
index 8be68c1..8d4b074 100644
--- a/PKG-INFO
+++ b/PKG-INFO
@@ -1,275 +1,275 @@
 Metadata-Version: 2.1
 Name: swh.lister
-Version: 0.6.1
+Version: 0.7.0
 Summary: Software Heritage lister
 Home-page: https://forge.softwareheritage.org/diffusion/DLSGH/
 Author: Software Heritage developers
 Author-email: swh-devel@inria.fr
 License: UNKNOWN
 Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest
 Project-URL: Funding, https://www.softwareheritage.org/donate
 Project-URL: Source, https://forge.softwareheritage.org/source/swh-lister
 Project-URL: Documentation, https://docs.softwareheritage.org/devel/swh-lister/
 Description: swh-lister
         ==========
         
         This component from the Software Heritage stack aims to produce listings
         of software origins and their urls hosted on various public developer platforms
         or package managers. As these operations are quite similar, it provides a set of
         Python modules abstracting common software origins listing behaviors.
         
         It also provides several lister implementations, contained in the
         following Python modules:
         
         - `swh.lister.bitbucket`
         - `swh.lister.cgit`
         - `swh.lister.cran`
         - `swh.lister.debian`
         - `swh.lister.gitea`
         - `swh.lister.github`
         - `swh.lister.gitlab`
         - `swh.lister.gnu`
         - `swh.lister.launchpad`
         - `swh.lister.npm`
         - `swh.lister.packagist`
         - `swh.lister.phabricator`
         - `swh.lister.pypi`
         
         Dependencies
         ------------
         
         All required dependencies can be found in the `requirements*.txt` files located
         at the root of the repository.
         
         Local deployment
         ----------------
         
         ## lister configuration
         
         Each lister implemented so far by Software Heritage (`github`, `gitlab`, `debian`, `pypi`, `npm`)
         must be configured by following the instructions below (please note that you have to replace
         `<lister_name>` by one of the lister name introduced above).
         
         ### Preparation steps
         
         1. `mkdir ~/.config/swh/ ~/.cache/swh/lister/<lister_name>/`
         2. create configuration file `~/.config/swh/lister_<lister_name>.yml`
         3. Bootstrap the db instance schema
         
         ```lang=bash
         $ createdb lister-<lister_name>
         $ python3 -m swh.lister.cli --db-url postgres:///lister-<lister_name> <lister_name>
         ```
         
         Note: This bootstraps a minimum data set needed for the lister to run.
         
         ### Configuration file sample
         
         Minimalistic configuration shared by all listers to add in file `~/.config/swh/lister_<lister_name>.yml`:
         
         ```lang=yml
         storage:
           cls: 'remote'
           args:
             url: 'http://localhost:5002/'
         
         scheduler:
           cls: 'remote'
           args:
             url: 'http://localhost:5008/'
         
         lister:
           cls: 'local'
           args:
             # see http://docs.sqlalchemy.org/en/latest/core/engines.html#database-urls
             db: 'postgresql:///lister-<lister_name>'
         
         credentials: []
         cache_responses: True
         cache_dir: /home/user/.cache/swh/lister/<lister_name>/
         ```
         
         Note: This expects storage (5002) and scheduler (5008) services to run locally
         
         ## lister-github
         
         Once configured, you can execute a GitHub lister using the following instructions in a `python3` script:
         
         ```lang=python
         import logging
         from swh.lister.github.tasks import range_github_lister
         
         logging.basicConfig(level=logging.DEBUG)
         range_github_lister(364, 365)
         ...
         ```
         
         ## lister-gitlab
         
         Once configured, you can execute a GitLab lister using the instructions detailed in the `python3` scripts below:
         
         ```lang=python
         import logging
         from swh.lister.gitlab.tasks import range_gitlab_lister
         
         logging.basicConfig(level=logging.DEBUG)
         range_gitlab_lister(1, 2, {
             'instance': 'debian',
             'api_baseurl': 'https://salsa.debian.org/api/v4',
             'sort': 'asc',
             'per_page': 20
         })
         ```
         
         ```lang=python
         import logging
         from swh.lister.gitlab.tasks import full_gitlab_relister
         
         logging.basicConfig(level=logging.DEBUG)
         full_gitlab_relister({
             'instance': '0xacab',
             'api_baseurl': 'https://0xacab.org/api/v4',
             'sort': 'asc',
             'per_page': 20
         })
         ```
         
         ```lang=python
         import logging
         from swh.lister.gitlab.tasks import incremental_gitlab_lister
         
         logging.basicConfig(level=logging.DEBUG)
         incremental_gitlab_lister({
             'instance': 'freedesktop.org',
             'api_baseurl': 'https://gitlab.freedesktop.org/api/v4',
             'sort': 'asc',
             'per_page': 20
         })
         ```
         
         ## lister-debian
         
         Once configured, you can execute a Debian lister using the following instructions in a `python3` script:
         
         ```lang=python
         import logging
         from swh.lister.debian.tasks import debian_lister
         
         logging.basicConfig(level=logging.DEBUG)
         debian_lister('Debian')
         ```
         
         ## lister-pypi
         
         Once configured, you can execute a PyPI lister using the following instructions in a `python3` script:
         
         ```lang=python
         import logging
         from swh.lister.pypi.tasks import pypi_lister
         
         logging.basicConfig(level=logging.DEBUG)
         pypi_lister()
         ```
         
         ## lister-npm
         
         Once configured, you can execute a npm lister using the following instructions in a `python3` REPL:
         
         ```lang=python
         import logging
         from swh.lister.npm.tasks import npm_lister
         
         logging.basicConfig(level=logging.DEBUG)
         npm_lister()
         ```
         
         ## lister-phabricator
         
         Once configured, you can execute a Phabricator lister using the following instructions in a `python3` script:
         
         ```lang=python
         import logging
         from swh.lister.phabricator.tasks import incremental_phabricator_lister
         
         logging.basicConfig(level=logging.DEBUG)
         incremental_phabricator_lister(forge_url='https://forge.softwareheritage.org', api_token='XXXX')
         ```
         
         ## lister-gnu
         
         Once configured, you can execute a PyPI lister using the following instructions in a `python3` script:
         
         ```lang=python
         import logging
         from swh.lister.gnu.tasks import gnu_lister
         
         logging.basicConfig(level=logging.DEBUG)
         gnu_lister()
         ```
         
         ## lister-cran
         
         Once configured, you can execute a CRAN lister using the following instructions in a `python3` script:
         
         ```lang=python
         import logging
         from swh.lister.cran.tasks import cran_lister
         
         logging.basicConfig(level=logging.DEBUG)
         cran_lister()
         ```
         
         ## lister-cgit
         
         Once configured, you can execute a cgit lister using the following instructions
         in a `python3` script:
         
         ```lang=python
         import logging
         from swh.lister.cgit.tasks import cgit_lister
         
         logging.basicConfig(level=logging.DEBUG)
         # simple cgit instance
         cgit_lister(url='https://git.kernel.org/')
         # cgit instance whose listed repositories differ from the base url
         cgit_lister(url='https://cgit.kde.org/',
                     url_prefix='https://anongit.kde.org/')
         ```
         
         ## lister-packagist
         
         Once configured, you can execute a Packagist lister using the following instructions
         in a `python3` script:
         
         ```lang=python
         import logging
         from swh.lister.packagist.tasks import packagist_lister
         
         logging.basicConfig(level=logging.DEBUG)
         packagist_lister()
         ```
         
         Licensing
         ---------
         
         This program is free software: you can redistribute it and/or modify it under
         the terms of the GNU General Public License as published by the Free Software
         Foundation, either version 3 of the License, or (at your option) any later
         version.
         
         This program is distributed in the hope that it will be useful, but WITHOUT ANY
         WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A
         PARTICULAR PURPOSE.  See the GNU General Public License for more details.
         
         See top-level LICENSE file for the full text of the GNU General Public License
         along with this program.
         
 Platform: UNKNOWN
 Classifier: Programming Language :: Python :: 3
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
 Classifier: Operating System :: OS Independent
 Classifier: Development Status :: 5 - Production/Stable
 Requires-Python: >=3.7
 Description-Content-Type: text/markdown
 Provides-Extra: testing
diff --git a/swh.lister.egg-info/PKG-INFO b/swh.lister.egg-info/PKG-INFO
index 8be68c1..8d4b074 100644
--- a/swh.lister.egg-info/PKG-INFO
+++ b/swh.lister.egg-info/PKG-INFO
@@ -1,275 +1,275 @@
 Metadata-Version: 2.1
 Name: swh.lister
-Version: 0.6.1
+Version: 0.7.0
 Summary: Software Heritage lister
 Home-page: https://forge.softwareheritage.org/diffusion/DLSGH/
 Author: Software Heritage developers
 Author-email: swh-devel@inria.fr
 License: UNKNOWN
 Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest
 Project-URL: Funding, https://www.softwareheritage.org/donate
 Project-URL: Source, https://forge.softwareheritage.org/source/swh-lister
 Project-URL: Documentation, https://docs.softwareheritage.org/devel/swh-lister/
 Description: swh-lister
         ==========
         
         This component from the Software Heritage stack aims to produce listings
         of software origins and their urls hosted on various public developer platforms
         or package managers. As these operations are quite similar, it provides a set of
         Python modules abstracting common software origins listing behaviors.
         
         It also provides several lister implementations, contained in the
         following Python modules:
         
         - `swh.lister.bitbucket`
         - `swh.lister.cgit`
         - `swh.lister.cran`
         - `swh.lister.debian`
         - `swh.lister.gitea`
         - `swh.lister.github`
         - `swh.lister.gitlab`
         - `swh.lister.gnu`
         - `swh.lister.launchpad`
         - `swh.lister.npm`
         - `swh.lister.packagist`
         - `swh.lister.phabricator`
         - `swh.lister.pypi`
         
         Dependencies
         ------------
         
         All required dependencies can be found in the `requirements*.txt` files located
         at the root of the repository.
         
         Local deployment
         ----------------
         
         ## lister configuration
         
         Each lister implemented so far by Software Heritage (`github`, `gitlab`, `debian`, `pypi`, `npm`)
         must be configured by following the instructions below (please note that you have to replace
         `<lister_name>` by one of the lister name introduced above).
         
         ### Preparation steps
         
         1. `mkdir ~/.config/swh/ ~/.cache/swh/lister/<lister_name>/`
         2. create configuration file `~/.config/swh/lister_<lister_name>.yml`
         3. Bootstrap the db instance schema
         
         ```lang=bash
         $ createdb lister-<lister_name>
         $ python3 -m swh.lister.cli --db-url postgres:///lister-<lister_name> <lister_name>
         ```
         
         Note: This bootstraps a minimum data set needed for the lister to run.
         
         ### Configuration file sample
         
         Minimalistic configuration shared by all listers to add in file `~/.config/swh/lister_<lister_name>.yml`:
         
         ```lang=yml
         storage:
           cls: 'remote'
           args:
             url: 'http://localhost:5002/'
         
         scheduler:
           cls: 'remote'
           args:
             url: 'http://localhost:5008/'
         
         lister:
           cls: 'local'
           args:
             # see http://docs.sqlalchemy.org/en/latest/core/engines.html#database-urls
             db: 'postgresql:///lister-<lister_name>'
         
         credentials: []
         cache_responses: True
         cache_dir: /home/user/.cache/swh/lister/<lister_name>/
         ```
         
         Note: This expects storage (5002) and scheduler (5008) services to run locally
         
         ## lister-github
         
         Once configured, you can execute a GitHub lister using the following instructions in a `python3` script:
         
         ```lang=python
         import logging
         from swh.lister.github.tasks import range_github_lister
         
         logging.basicConfig(level=logging.DEBUG)
         range_github_lister(364, 365)
         ...
         ```
         
         ## lister-gitlab
         
         Once configured, you can execute a GitLab lister using the instructions detailed in the `python3` scripts below:
         
         ```lang=python
         import logging
         from swh.lister.gitlab.tasks import range_gitlab_lister
         
         logging.basicConfig(level=logging.DEBUG)
         range_gitlab_lister(1, 2, {
             'instance': 'debian',
             'api_baseurl': 'https://salsa.debian.org/api/v4',
             'sort': 'asc',
             'per_page': 20
         })
         ```
         
         ```lang=python
         import logging
         from swh.lister.gitlab.tasks import full_gitlab_relister
         
         logging.basicConfig(level=logging.DEBUG)
         full_gitlab_relister({
             'instance': '0xacab',
             'api_baseurl': 'https://0xacab.org/api/v4',
             'sort': 'asc',
             'per_page': 20
         })
         ```
         
         ```lang=python
         import logging
         from swh.lister.gitlab.tasks import incremental_gitlab_lister
         
         logging.basicConfig(level=logging.DEBUG)
         incremental_gitlab_lister({
             'instance': 'freedesktop.org',
             'api_baseurl': 'https://gitlab.freedesktop.org/api/v4',
             'sort': 'asc',
             'per_page': 20
         })
         ```
         
         ## lister-debian
         
         Once configured, you can execute a Debian lister using the following instructions in a `python3` script:
         
         ```lang=python
         import logging
         from swh.lister.debian.tasks import debian_lister
         
         logging.basicConfig(level=logging.DEBUG)
         debian_lister('Debian')
         ```
         
         ## lister-pypi
         
         Once configured, you can execute a PyPI lister using the following instructions in a `python3` script:
         
         ```lang=python
         import logging
         from swh.lister.pypi.tasks import pypi_lister
         
         logging.basicConfig(level=logging.DEBUG)
         pypi_lister()
         ```
         
         ## lister-npm
         
         Once configured, you can execute a npm lister using the following instructions in a `python3` REPL:
         
         ```lang=python
         import logging
         from swh.lister.npm.tasks import npm_lister
         
         logging.basicConfig(level=logging.DEBUG)
         npm_lister()
         ```
         
         ## lister-phabricator
         
         Once configured, you can execute a Phabricator lister using the following instructions in a `python3` script:
         
         ```lang=python
         import logging
         from swh.lister.phabricator.tasks import incremental_phabricator_lister
         
         logging.basicConfig(level=logging.DEBUG)
         incremental_phabricator_lister(forge_url='https://forge.softwareheritage.org', api_token='XXXX')
         ```
         
         ## lister-gnu
         
         Once configured, you can execute a PyPI lister using the following instructions in a `python3` script:
         
         ```lang=python
         import logging
         from swh.lister.gnu.tasks import gnu_lister
         
         logging.basicConfig(level=logging.DEBUG)
         gnu_lister()
         ```
         
         ## lister-cran
         
         Once configured, you can execute a CRAN lister using the following instructions in a `python3` script:
         
         ```lang=python
         import logging
         from swh.lister.cran.tasks import cran_lister
         
         logging.basicConfig(level=logging.DEBUG)
         cran_lister()
         ```
         
         ## lister-cgit
         
         Once configured, you can execute a cgit lister using the following instructions
         in a `python3` script:
         
         ```lang=python
         import logging
         from swh.lister.cgit.tasks import cgit_lister
         
         logging.basicConfig(level=logging.DEBUG)
         # simple cgit instance
         cgit_lister(url='https://git.kernel.org/')
         # cgit instance whose listed repositories differ from the base url
         cgit_lister(url='https://cgit.kde.org/',
                     url_prefix='https://anongit.kde.org/')
         ```
         
         ## lister-packagist
         
         Once configured, you can execute a Packagist lister using the following instructions
         in a `python3` script:
         
         ```lang=python
         import logging
         from swh.lister.packagist.tasks import packagist_lister
         
         logging.basicConfig(level=logging.DEBUG)
         packagist_lister()
         ```
         
         Licensing
         ---------
         
         This program is free software: you can redistribute it and/or modify it under
         the terms of the GNU General Public License as published by the Free Software
         Foundation, either version 3 of the License, or (at your option) any later
         version.
         
         This program is distributed in the hope that it will be useful, but WITHOUT ANY
         WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A
         PARTICULAR PURPOSE.  See the GNU General Public License for more details.
         
         See top-level LICENSE file for the full text of the GNU General Public License
         along with this program.
         
 Platform: UNKNOWN
 Classifier: Programming Language :: Python :: 3
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
 Classifier: Operating System :: OS Independent
 Classifier: Development Status :: 5 - Production/Stable
 Requires-Python: >=3.7
 Description-Content-Type: text/markdown
 Provides-Extra: testing
diff --git a/swh.lister.egg-info/SOURCES.txt b/swh.lister.egg-info/SOURCES.txt
index dc907b8..9032074 100644
--- a/swh.lister.egg-info/SOURCES.txt
+++ b/swh.lister.egg-info/SOURCES.txt
@@ -1,198 +1,197 @@
 .gitignore
 .pre-commit-config.yaml
 ACKNOWLEDGEMENTS
 CODE_OF_CONDUCT.md
 CONTRIBUTORS
 LICENSE
 MANIFEST.in
 Makefile
 README.md
 conftest.py
 mypy.ini
 pyproject.toml
 pytest.ini
 requirements-swh.txt
 requirements-test.txt
 requirements.txt
 setup.cfg
 setup.py
 tox.ini
 docs/.gitignore
 docs/Makefile
 docs/cli.rst
 docs/conf.py
 docs/index.rst
 docs/run_a_new_lister.rst
 docs/tutorial.rst
 docs/_static/.placeholder
 docs/_templates/.placeholder
 docs/images/new_base.png
 docs/images/new_bitbucket_lister.png
 docs/images/new_github_lister.png
 docs/images/old_github_lister.png
 sql/crawler.sql
 sql/pimp_db.sql
 swh/__init__.py
 swh.lister.egg-info/PKG-INFO
 swh.lister.egg-info/SOURCES.txt
 swh.lister.egg-info/dependency_links.txt
 swh.lister.egg-info/entry_points.txt
 swh.lister.egg-info/requires.txt
 swh.lister.egg-info/top_level.txt
 swh/lister/__init__.py
 swh/lister/cli.py
 swh/lister/pattern.py
 swh/lister/py.typed
 swh/lister/pytest_plugin.py
 swh/lister/utils.py
 swh/lister/bitbucket/__init__.py
 swh/lister/bitbucket/lister.py
 swh/lister/bitbucket/tasks.py
 swh/lister/bitbucket/tests/__init__.py
 swh/lister/bitbucket/tests/test_lister.py
 swh/lister/bitbucket/tests/test_tasks.py
 swh/lister/bitbucket/tests/data/bb_api_repositories_page1.json
 swh/lister/bitbucket/tests/data/bb_api_repositories_page2.json
 swh/lister/cgit/__init__.py
 swh/lister/cgit/lister.py
 swh/lister/cgit/tasks.py
 swh/lister/cgit/tests/__init__.py
 swh/lister/cgit/tests/repo_list.txt
 swh/lister/cgit/tests/test_lister.py
 swh/lister/cgit/tests/test_tasks.py
+swh/lister/cgit/tests/data/https_git.baserock.org/cgit
+swh/lister/cgit/tests/data/https_git.eclipse.org/c
 swh/lister/cgit/tests/data/https_git.savannah.gnu.org/README
 swh/lister/cgit/tests/data/https_git.savannah.gnu.org/cgit
 swh/lister/cgit/tests/data/https_git.savannah.gnu.org/cgit_elisp-es.git
 swh/lister/cgit/tests/data/https_git.tizen/README
 swh/lister/cgit/tests/data/https_git.tizen/cgit
 swh/lister/cgit/tests/data/https_git.tizen/cgit,ofs=100
 swh/lister/cgit/tests/data/https_git.tizen/cgit,ofs=50
 swh/lister/cgit/tests/data/https_git.tizen/cgit_All-Projects
 swh/lister/cgit/tests/data/https_git.tizen/cgit_All-Users
 swh/lister/cgit/tests/data/https_git.tizen/cgit_Lock-Projects
 swh/lister/cgit/tests/data/https_git.tizen/cgit_adaptation_alsa-scenario-scn-data-0-base
 swh/lister/cgit/tests/data/https_git.tizen/cgit_adaptation_alsa-scenario-scn-data-0-mc1n2
 swh/lister/cgit/tests/data/https_git.tizen/cgit_adaptation_ap_samsung_audio-hal-e3250
 swh/lister/cgit/tests/data/https_git.tizen/cgit_adaptation_ap_samsung_audio-hal-e4x12
 swh/lister/cgit/tests/data/https_git.tizen/cgit_adaptation_devices_nfc-plugin-nxp
 swh/lister/cgit/tests/data/https_git.tizen/cgit_adaptation_intel_mfld_bootstub-mfld-blackbay
 swh/lister/cgit/tests/data/https_git.tizen/cgit_adaptation_mtdev
 swh/lister/cgit/tests/data/https_git.tizen/cgit_adaptation_opengl-es-virtual-drv
 swh/lister/cgit/tests/data/https_git.tizen/cgit_adaptation_panda_libdrm
 swh/lister/cgit/tests/data/https_git.tizen/cgit_adaptation_panda_libnl
 swh/lister/cgit/tests/data/https_git.tizen/cgit_adaptation_xorg_driver_xserver-xorg-misc
 swh/lister/cgit/tests/data/https_git.tizen/cgit_apps_core_preloaded_ug-setting-gallery-efl
 swh/lister/cgit/tests/data/https_git.tizen/cgit_apps_core_preloaded_ug-setting-homescreen-efl
+swh/lister/cgit/tests/data/https_jff.email/cgit
 swh/lister/core/__init__.py
 swh/lister/core/abstractattribute.py
 swh/lister/core/lister_base.py
 swh/lister/core/lister_transports.py
 swh/lister/core/models.py
 swh/lister/core/simple_lister.py
 swh/lister/core/tests/__init__.py
 swh/lister/core/tests/test_abstractattribute.py
 swh/lister/core/tests/test_lister.py
 swh/lister/core/tests/test_model.py
 swh/lister/cran/__init__.py
 swh/lister/cran/list_all_packages.R
 swh/lister/cran/lister.py
 swh/lister/cran/tasks.py
 swh/lister/cran/tests/__init__.py
 swh/lister/cran/tests/test_lister.py
 swh/lister/cran/tests/test_tasks.py
 swh/lister/cran/tests/data/list-r-packages.json
 swh/lister/debian/__init__.py
 swh/lister/debian/lister.py
 swh/lister/debian/tasks.py
 swh/lister/debian/tests/__init__.py
 swh/lister/debian/tests/test_lister.py
 swh/lister/debian/tests/test_tasks.py
 swh/lister/debian/tests/data/Sources_bullseye
 swh/lister/debian/tests/data/Sources_buster
 swh/lister/debian/tests/data/Sources_stretch
 swh/lister/gitea/__init__.py
 swh/lister/gitea/lister.py
 swh/lister/gitea/tasks.py
 swh/lister/gitea/tests/__init__.py
 swh/lister/gitea/tests/test_lister.py
 swh/lister/gitea/tests/test_tasks.py
 swh/lister/gitea/tests/data/https_try.gitea.io/repos_page1
 swh/lister/gitea/tests/data/https_try.gitea.io/repos_page2
 swh/lister/github/__init__.py
 swh/lister/github/lister.py
 swh/lister/github/tasks.py
 swh/lister/github/tests/__init__.py
 swh/lister/github/tests/test_lister.py
 swh/lister/github/tests/test_tasks.py
 swh/lister/gitlab/__init__.py
 swh/lister/gitlab/lister.py
 swh/lister/gitlab/tasks.py
 swh/lister/gitlab/tests/__init__.py
 swh/lister/gitlab/tests/test_lister.py
 swh/lister/gitlab/tests/test_tasks.py
 swh/lister/gitlab/tests/data/https_gite.lirmm.fr/api_response_page1.json
 swh/lister/gitlab/tests/data/https_gite.lirmm.fr/api_response_page2.json
 swh/lister/gitlab/tests/data/https_gite.lirmm.fr/api_response_page3.json
 swh/lister/gitlab/tests/data/https_gitlab.com/api_response_page1.json
 swh/lister/gnu/__init__.py
 swh/lister/gnu/lister.py
-swh/lister/gnu/models.py
 swh/lister/gnu/tasks.py
 swh/lister/gnu/tree.py
 swh/lister/gnu/tests/__init__.py
-swh/lister/gnu/tests/api_response.json
-swh/lister/gnu/tests/conftest.py
-swh/lister/gnu/tests/find_tarballs_output.json
 swh/lister/gnu/tests/test_lister.py
 swh/lister/gnu/tests/test_tasks.py
 swh/lister/gnu/tests/test_tree.py
 swh/lister/gnu/tests/data/tree.json
 swh/lister/gnu/tests/data/tree.min.json
 swh/lister/gnu/tests/data/https_ftp.gnu.org/tree.json.gz
 swh/lister/launchpad/__init__.py
 swh/lister/launchpad/lister.py
 swh/lister/launchpad/tasks.py
 swh/lister/launchpad/tests/__init__.py
 swh/lister/launchpad/tests/conftest.py
 swh/lister/launchpad/tests/test_lister.py
 swh/lister/launchpad/tests/test_tasks.py
 swh/lister/launchpad/tests/data/launchpad_response1.json
 swh/lister/launchpad/tests/data/launchpad_response2.json
 swh/lister/npm/__init__.py
 swh/lister/npm/lister.py
 swh/lister/npm/tasks.py
 swh/lister/npm/tests/test_lister.py
 swh/lister/npm/tests/test_tasks.py
 swh/lister/npm/tests/data/npm_full_page1.json
 swh/lister/npm/tests/data/npm_full_page2.json
 swh/lister/npm/tests/data/npm_incremental_page1.json
 swh/lister/npm/tests/data/npm_incremental_page2.json
 swh/lister/packagist/__init__.py
 swh/lister/packagist/lister.py
 swh/lister/packagist/models.py
 swh/lister/packagist/tasks.py
 swh/lister/packagist/tests/__init__.py
 swh/lister/packagist/tests/conftest.py
 swh/lister/packagist/tests/test_lister.py
 swh/lister/packagist/tests/test_tasks.py
 swh/lister/packagist/tests/data/https_packagist.org/packages_list.json
 swh/lister/phabricator/__init__.py
 swh/lister/phabricator/lister.py
 swh/lister/phabricator/tasks.py
 swh/lister/phabricator/tests/__init__.py
 swh/lister/phabricator/tests/test_lister.py
 swh/lister/phabricator/tests/test_tasks.py
 swh/lister/phabricator/tests/data/__init__.py
 swh/lister/phabricator/tests/data/phabricator_api_repositories_page1.json
 swh/lister/phabricator/tests/data/phabricator_api_repositories_page2.json
 swh/lister/pypi/__init__.py
 swh/lister/pypi/lister.py
 swh/lister/pypi/tasks.py
 swh/lister/pypi/tests/__init__.py
 swh/lister/pypi/tests/test_lister.py
 swh/lister/pypi/tests/test_tasks.py
 swh/lister/pypi/tests/data/https_pypi.org/simple
 swh/lister/tests/__init__.py
 swh/lister/tests/test_cli.py
 swh/lister/tests/test_pattern.py
 swh/lister/tests/test_utils.py
\ No newline at end of file
diff --git a/swh/lister/cgit/lister.py b/swh/lister/cgit/lister.py
index 0253a32..646efa5 100644
--- a/swh/lister/cgit/lister.py
+++ b/swh/lister/cgit/lister.py
@@ -1,187 +1,216 @@
 # Copyright (C) 2019-2021 The Software Heritage developers
 # License: GNU General Public License version 3, or any later version
 # See top-level LICENSE file for more information
 
 from datetime import datetime, timezone
 import logging
 import re
 from typing import Any, Dict, Iterator, List, Optional
 from urllib.parse import urljoin, urlparse
 
 from bs4 import BeautifulSoup
 import requests
 from requests.exceptions import HTTPError
 
 from swh.lister import USER_AGENT
 from swh.lister.pattern import CredentialsType, StatelessLister
 from swh.scheduler.interface import SchedulerInterface
 from swh.scheduler.model import ListedOrigin
 
 logger = logging.getLogger(__name__)
 
 Repositories = List[Dict[str, Any]]
 
 
 class CGitLister(StatelessLister[Repositories]):
     """Lister class for CGit repositories.
 
     This lister will retrieve the list of published git repositories by
     parsing the HTML page(s) of the index retrieved at `url`.
 
-    For each found git repository, a query is made at the given url found
-    in this index to gather published "Clone" URLs to be used as origin
-    URL for that git repo.
+    The lister currently defines 2 listing behaviors:
+
+    - If the `base_git_url` is provided, the listed origin urls are computed out of the
+      base git url link and the one listed in the main listed page (resulting in less
+      HTTP queries than the 2nd behavior below). This is expected to be the main
+      deployed behavior.
+
+    - Otherwise (with no `base_git_url`), for each found git repository listed, one
+      extra HTTP query is made at the given url found in the main listing page to gather
+      published "Clone" URLs to be used as origin URL for that git repo. If several
+      "Clone" urls are provided, prefer the http/https one, if any, otherwise fallback
+      to the first one.
 
-    If several "Clone" urls are provided, prefer the http/https one, if
-    any, otherwise fallback to the first one.
     """
 
     LISTER_NAME = "cgit"
 
     def __init__(
         self,
         scheduler: SchedulerInterface,
         url: str,
         instance: Optional[str] = None,
         credentials: Optional[CredentialsType] = None,
+        base_git_url: Optional[str] = None,
     ):
         """Lister class for CGit repositories.
 
         Args:
-            url (str): main URL of the CGit instance, i.e. url of the index
+            url: main URL of the CGit instance, i.e. url of the index
                 of published git repositories on this instance.
-            instance (str): Name of cgit instance. Defaults to url's hostname
+            instance: Name of cgit instance. Defaults to url's hostname
                 if unset.
+            base_git_url: Optional base git url which allows the origin url
+                computations.
 
         """
         if not instance:
             instance = urlparse(url).hostname
         assert instance is not None  # Make mypy happy
 
         super().__init__(
             scheduler=scheduler, url=url, instance=instance, credentials=credentials,
         )
 
         self.session = requests.Session()
         self.session.headers.update(
             {"Accept": "application/html", "User-Agent": USER_AGENT}
         )
+        self.base_git_url = base_git_url
 
     def _get_and_parse(self, url: str) -> BeautifulSoup:
         """Get the given url and parse the retrieved HTML using BeautifulSoup"""
         response = self.session.get(url)
         response.raise_for_status()
         return BeautifulSoup(response.text, features="html.parser")
 
     def get_pages(self) -> Iterator[Repositories]:
         """Generate git 'project' URLs found on the current CGit server
             The last_update date is retrieved on the list of repo page to avoid
             to compute it on the repository details which only give a date per branch
         """
         next_page: Optional[str] = self.url
         while next_page:
             bs_idx = self._get_and_parse(next_page)
 
             page_results = []
 
             for tr in bs_idx.find("div", {"class": "content"}).find_all(
                 "tr", {"class": ""}
             ):
-                url = urljoin(self.url, tr.find("a")["href"])
+                repository_link = tr.find("a")["href"]
+                repo_url = None
+                git_url = None
+
+                base_url = urljoin(self.url, repository_link)
+                if self.base_git_url:  # mapping provided
+                    # computing git url
+                    git_url = base_url.replace(self.url, self.base_git_url)
+                else:
+                    # we compute the git detailed page url from which we will retrieve
+                    # the git url (cf. self.get_origins_from_page)
+                    repo_url = base_url
+
                 span = tr.find("span", {"class": re.compile("age-")})
                 if span:
                     last_updated_date = span["title"]
                 else:
                     last_updated_date = None
 
                 page_results.append(
-                    {"url": url, "last_updated_date": last_updated_date}
+                    {
+                        "url": repo_url,
+                        "git_url": git_url,
+                        "last_updated_date": last_updated_date,
+                    }
                 )
 
             yield page_results
 
             try:
                 pager = bs_idx.find("ul", {"class": "pager"})
 
                 current_page = pager.find("a", {"class": "current"})
                 if current_page:
                     next_page = current_page.parent.next_sibling.a["href"]
                     next_page = urljoin(self.url, next_page)
             except (AttributeError, KeyError):
                 # no pager, or no next page
                 next_page = None
 
     def get_origins_from_page(
         self, repositories: Repositories
     ) -> Iterator[ListedOrigin]:
         """Convert a page of cgit repositories into a list of ListedOrigins."""
         assert self.lister_obj.id is not None
 
-        for repository in repositories:
-            origin_url = self._get_origin_from_repository_url(repository["url"])
+        for repo in repositories:
+            origin_url = repo["git_url"] or self._get_origin_from_repository_url(
+                repo["url"]
+            )
             if origin_url is None:
                 continue
 
             yield ListedOrigin(
                 lister_id=self.lister_obj.id,
                 url=origin_url,
                 visit_type="git",
-                last_update=_parse_last_updated_date(repository),
+                last_update=_parse_last_updated_date(repo),
             )
 
     def _get_origin_from_repository_url(self, repository_url: str) -> Optional[str]:
         """Extract the git url from the repository page"""
         try:
             bs = self._get_and_parse(repository_url)
         except HTTPError as e:
             logger.warning(
                 "Unexpected HTTP status code %s on %s",
                 e.response.status_code,
                 e.response.url,
             )
             return None
 
         # origin urls are listed on the repository page
         # TODO check if forcing https is better or not ?
         # <link rel='vcs-git' href='git://...' title='...'/>
         # <link rel='vcs-git' href='http://...' title='...'/>
         # <link rel='vcs-git' href='https://...' title='...'/>
         urls = [x["href"] for x in bs.find_all("a", {"rel": "vcs-git"})]
 
         if not urls:
             return None
 
         # look for the http/https url, if any, and use it as origin_url
         for url in urls:
             if urlparse(url).scheme in ("http", "https"):
                 origin_url = url
                 break
         else:
             # otherwise, choose the first one
             origin_url = urls[0]
         return origin_url
 
 
 def _parse_last_updated_date(repository: Dict[str, Any]) -> Optional[datetime]:
     """Parse the last updated date"""
     date = repository.get("last_updated_date")
     if not date:
         return None
 
     parsed_date = None
     for date_format in ("%Y-%m-%d %H:%M:%S %z", "%Y-%m-%d %H:%M:%S (%Z)"):
         try:
             parsed_date = datetime.strptime(date, date_format)
             # force UTC to avoid naive datetime
             if not parsed_date.tzinfo:
                 parsed_date = parsed_date.replace(tzinfo=timezone.utc)
             break
         except Exception:
             pass
 
     if not parsed_date:
         logger.warning(
             "Could not parse %s last_updated date: %s", repository["url"], date,
         )
 
     return parsed_date
diff --git a/swh/lister/cgit/tasks.py b/swh/lister/cgit/tasks.py
index e6ef159..9a95648 100644
--- a/swh/lister/cgit/tasks.py
+++ b/swh/lister/cgit/tasks.py
@@ -1,21 +1,25 @@
 # Copyright (C) 2019-2021 The Software Heritage developers
 # License: GNU General Public License version 3, or any later version
 # See top-level LICENSE file for more information
 
 from typing import Dict, Optional
 
 from celery import shared_task
 
 from .lister import CGitLister
 
 
 @shared_task(name=__name__ + ".CGitListerTask")
-def list_cgit(url: str, instance: Optional[str] = None,) -> Dict[str, str]:
+def list_cgit(
+    url: str, instance: Optional[str] = None, base_git_url: Optional[str] = None
+) -> Dict[str, str]:
     """Lister task for CGit instances"""
-    lister = CGitLister.from_configfile(url=url, instance=instance)
+    lister = CGitLister.from_configfile(
+        url=url, instance=instance, base_git_url=base_git_url
+    )
     return lister.run().dict()
 
 
 @shared_task(name=__name__ + ".ping")
 def _ping():
     return "OK"
diff --git a/swh/lister/cgit/tests/data/https_git.baserock.org/cgit b/swh/lister/cgit/tests/data/https_git.baserock.org/cgit
new file mode 100644
index 0000000..46fde7e
--- /dev/null
+++ b/swh/lister/cgit/tests/data/https_git.baserock.org/cgit
@@ -0,0 +1,33 @@
+<!DOCTYPE html>
+<html lang='en'>
+  <head>
+    <title>Lorry Depot</title>
+    <meta name='generator' content='cgit v1.2.1'/>
+    <meta name='robots' content='index, nofollow'/>
+    <link rel='stylesheet' type='text/css' href='/cgit-css/cgit.css'/>
+    <link rel='shortcut icon' href='/favicon.ico'/>
+  </head>
+  <body>
+    <div id='cgit'><table id='header'>
+        <tr>
+          <td class='logo' rowspan='2'><a href='/cgit/'><img src='/cgit-css/cgit.png' alt='cgit logo'/></a></td>
+          <td class='main'>Lorry Depot</td></tr>
+        <tr><td class='sub'>Mirror Repositories</td></tr></table>
+      <table class='tabs'><tr><td>
+            <a class='active' href='/cgit/'>index</a></td><td class='form'><form method='get' action='/cgit/'>
+              <input type='search' name='q' size='10' value=''/>
+              <input type='submit' value='search'/>
+      </form></td></tr></table>
+      <div class='content'>
+        <table summary='repository list' class='list nowrap'><tr class='nohover'><th class='left'><a href='/cgit/?s=name'>Name</a></th><th class='left'><a href='/cgit/?s=desc'>Description</a></th><th class='left'><a href='/cgit/?s=idle'>Idle</a></th><th class='left'>Links</th></tr>
+          <tr><td class='toplevel-repo'><a title='baserock/baserock/baserock-chroot.git' href='/cgit/baserock/baserock/baserock-chroot.git/'>baserock/baserock/baserock-chroot.git</a></td><td><a href='/cgit/baserock/baserock/baserock-chroot.git/'>Tools for working with Baserock chroots
+            </a></td><td><span class='age-years' title='2015-05-20 09:59:01 +0000'>6 years</span></td><td><a class='button' href='/cgit/baserock/baserock/baserock-chroot.git/'>summary</a><a class='button' href='/cgit/baserock/baserock/baserock-chroot.git/log/'>log</a><a class='button' href='/cgit/baserock/baserock/baserock-chroot.git/tree/'>tree</a></td></tr>
+          <tr><td class='toplevel-repo'><a title='baserock/baserock/bsp-support.git' href='/cgit/baserock/baserock/bsp-support.git/'>baserock/baserock/bsp-support.git</a></td><td><a href='/cgit/baserock/baserock/bsp-support.git/'>Programs and configuration needed to support specific devices
+            </a></td><td><span class='age-years' title='2015-10-25 19:53:10 +0000'>5 years</span></td><td><a class='button' href='/cgit/baserock/baserock/bsp-support.git/'>summary</a><a class='button' href='/cgit/baserock/baserock/bsp-support.git/log/'>log</a><a class='button' href='/cgit/baserock/baserock/bsp-support.git/tree/'>tree</a></td></tr>
+          <tr><td class='toplevel-repo'><a title='baserock/baserock/definitions.git' href='/cgit/baserock/baserock/definitions.git/'>baserock/baserock/definitions.git</a></td><td><a href='/cgit/baserock/baserock/definitions.git/'>gitlab.com: baserock/definitions.git
+            </a></td><td><span class='age-months' title='2019-05-15 17:58:47 +0000'>21 months</span></td><td><a class='button' href='/cgit/baserock/baserock/definitions.git/'>summary</a><a class='button' href='/cgit/baserock/baserock/definitions.git/log/'>log</a><a class='button' href='/cgit/baserock/baserock/definitions.git/tree/'>tree</a></td></tr>
+        </table>
+      </div> <!-- class=content -->
+    </div> <!-- id=cgit -->
+  </body>
+</html>
diff --git a/swh/lister/cgit/tests/data/https_git.eclipse.org/c b/swh/lister/cgit/tests/data/https_git.eclipse.org/c
new file mode 100644
index 0000000..8cd1d4b
--- /dev/null
+++ b/swh/lister/cgit/tests/data/https_git.eclipse.org/c
@@ -0,0 +1,42 @@
+<!DOCTYPE html>
+<html lang='en'>
+  <head>
+    <title>Eclipse Git repositories</title>
+    <meta name='generator' content='cgit v1.2.1'/>
+    <meta name='robots' content='index, nofollow'/>
+    <meta charset="utf-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <meta name="keywords" content="eclipse.org, Eclipse Foundation, Eclipse, Git, Source code, Source" />
+  </head>
+  <body>
+    <!-- /#breadcrumb -->
+    <main>
+      <div class="container-fluid legacy-page" id="novaContent">
+        <div class="col-md-24"><div id='cgit'><table id='header'>
+              <tr>
+                <td class='logo' rowspan='2'><a href='/c/'><img src='/git.png' alt='cgit logo'/></a></td>
+                <td class='main'>Eclipse Git repositories</td></tr>
+              <tr><td class='sub'>To use Git in Eclipse, check out the EGit project.</td></tr></table>
+            <table class='tabs'><tr><td>
+                  <a class='active' href='/c/'>index</a><a href='/c/?p=about'>about</a></td><td class='form'><form method='get' action='/c/'>
+                    <input type='search' name='q' size='10' value=''/>
+                    <input type='submit' value='search'/>
+            </form></td></tr></table>
+            <div class='content'><table summary='repository list' class='list nowrap'><tr class='nohover'><th class='left'><a href='/c/?s=name'>Name</a></th><th class='left'><a href='/c/?s=desc'>Description</a></th><th class='left'><a href='/c/?s=idle'>Idle</a></th></tr>
+                <tr class='nohover-highlight'><td colspan='3' class='reposection'>3p</td></tr>
+                <tr><td class='sublevel-repo'><a title='3p.git' href='/c/3p/3p.git/'>3p.git</a></td><td><a href='/c/3p/3p.git/'>3P - PolarSys Packaging</a></td><td><span class='age-months' title='2020-01-17 23:52:00 +0000'>12 months</span></td></tr>
+                <tr><td class='sublevel-repo'><a title='qvtd.git' href='/c/www.eclipse.org/qvtd.git/'>qvtd.git</a></td><td><a href='/c/www.eclipse.org/qvtd.git/'>www.eclipse.org project repository</a></td><td><span class='age-years' title='2018-07-20 23:51:54 +0000'>3 years</span></td></tr>
+                <tr><td class='sublevel-repo'><a title='r4e.git' href='/c/www.eclipse.org/r4e.git/'>r4e.git</a></td><td><a href='/c/www.eclipse.org/r4e.git/'>www.eclipse.org project repository</a></td><td><span class='age-years' title='2018-11-17 00:57:51 +0000'>2 years</span></td></tr>
+                <tr><td class='sublevel-repo'><a title='rap.git' href='/c/www.eclipse.org/rap.git/'>rap.git</a></td><td><a href='/c/www.eclipse.org/rap.git/'>RAP project website</a></td><td><span class='age-weeks' title='2020-12-20 01:16:37 +0000'>6 weeks</span></td></tr>
+                <tr class='nohover-highlight'><td colspan='3' class='reposection'>zenoh</td></tr>
+                <tr><td class='sublevel-repo'><a title='zenoh.git' href='/c/zenoh/zenoh.git/'>zenoh.git</a></td><td><a href='/c/zenoh/zenoh.git/'>Unnamed repository; edit this file 'description' to name the repository.</a></td><td><span class='age-months' title='2020-01-25 05:07:25 +0000'>12 months</span></td></tr>
+            </table></div> <!-- class=content -->
+          </div>
+        </div>
+    </main>
+    <p id="back-to-top">
+      <a class="visible-xs" href="#top">Back to the top</a>
+    </p>
+  </body>
+</html>
diff --git a/swh/lister/cgit/tests/data/https_jff.email/cgit b/swh/lister/cgit/tests/data/https_jff.email/cgit
new file mode 100644
index 0000000..ebc0289
--- /dev/null
+++ b/swh/lister/cgit/tests/data/https_jff.email/cgit
@@ -0,0 +1,33 @@
+<!DOCTYPE html>
+<html lang='en'>
+  <head>
+    <title>Jörgs Debian Repository</title>
+    <meta name='generator' content='cgit v1.1'/>
+    <meta name='robots' content='index, nofollow'/>
+    <link rel='stylesheet' type='text/css' href='/cgit-css/cgit.css'/>
+    <link rel='shortcut icon' href='/favicon.ico'/>
+  </head>
+  <body>
+    <div id='cgit'><table id='header'>
+        <tr>
+          <td class='logo' rowspan='2'><a href='/cgit/'><img src='/cgit-css/cgit.png' alt='cgit logo'/></a></td>
+          <td class='main'>Jörgs Debian Repository</td></tr>
+        <tr><td class='sub'>ask debian-cgit@jff.email</td></tr></table>
+      <table class='tabs'><tr><td>
+            <a class='active' href='/cgit/'>index</a></td><td class='form'><form method='get' action='/cgit/'>
+              <input type='text' name='q' size='10' value=''/>
+              <input type='submit' value='search'/>
+      </form></td></tr></table>
+      <div class='content'><table summary='repository list' class='list nowrap'>
+          <tr class='nohover'><th class='left'><a href='/cgit/?s=name'>Name</a></th><th class='left'><a href='/cgit/?s=desc'>Description</a></th><th class='left'><a href='/cgit/?s=owner'>Owner</a></th><th class='left'><a href='/cgit/?s=idle'>Idle</a></th></tr>
+          <tr><td class='toplevel-repo'><a title='gnome-pie.git' href='/cgit/gnome-pie.git/'>gnome-pie.git</a></td><td><a href='/cgit/gnome-pie.git/'>Debian repo for gnome-pie</a></td><td><a href='/cgit/?q=debian@jff.email'>debian@jff.email</a></td><td><span class='age-months' title='2020-06-01 15:22:58 +0000'>8 months</span></td></tr>
+          <tr><td class='toplevel-repo'><a title='gs5.git' href='/cgit/gs5.git/'>gs5.git</a></td><td><a href='/cgit/gs5.git/'>Clone of gs5</a></td><td><a href='/cgit/?q=jff@jff.email'>jff@jff.email</a></td><td><span class='age-years' title='2018-10-01 17:24:55 +0000'>2 years</span></td></tr>
+          <tr><td class='toplevel-repo'><a title='libunistring.git' href='/cgit/libunistring.git/'>libunistring.git</a></td><td><a href='/cgit/libunistring.git/'>Debian repo for libunistring</a></td><td><a href='/cgit/?q=debian@jff.email'>debian@jff.email</a></td><td><span class='age-months' title='2020-06-02 06:00:00 +0000'>8 months</span></td></tr>
+          <tr><td class='toplevel-repo'><a title='mailgraph.git' href='/cgit/mailgraph.git/'>mailgraph.git</a></td><td><a href='/cgit/mailgraph.git/'>Debian repo for mailgraph</a></td><td><a href='/cgit/?q=debian@jff.email'>debian@jff.email</a></td><td><span class='age-years' title='2018-09-09 19:18:23 +0000'>2 years</span></td></tr>
+          <tr><td class='toplevel-repo'><a title='mwc.git' href='/cgit/mwc.git/'>mwc.git</a></td><td><a href='/cgit/mwc.git/'>Debian repo for mwc</a></td><td><a href='/cgit/?q=debian@jff.email'>debian@jff.email</a></td><td><span class='age-months' title='2019-07-14 14:58:18 +0000'>19 months</span></td></tr>
+          <tr><td class='toplevel-repo'><a title='xtrkcad.git' href='/cgit/xtrkcad.git/'>xtrkcad.git</a></td><td><a href='/cgit/xtrkcad.git/'>Debian repo for xtrkcad</a></td><td><a href='/cgit/?q=debian@jff.email'>debian@jff.email</a></td><td><span class='age-months' title='2020-08-24 19:27:40 +0000'>5 months</span></td></tr>
+      </table></div> <!-- class=content -->
+      <div class='footer'>generated by <a href='https://git.zx2c4.com/cgit/about/'>cgit v1.1</a> at 2021-01-29 14:18:26 +0000</div>
+    </div> <!-- id=cgit -->
+  </body>
+</html>
diff --git a/swh/lister/cgit/tests/test_lister.py b/swh/lister/cgit/tests/test_lister.py
index cf4c9fc..f963a4e 100644
--- a/swh/lister/cgit/tests/test_lister.py
+++ b/swh/lister/cgit/tests/test_lister.py
@@ -1,198 +1,233 @@
 # Copyright (C) 2019-2021 The Software Heritage developers
 # License: GNU General Public License version 3, or any later version
 # See top-level LICENSE file for more information
 
 from datetime import datetime, timedelta, timezone
 from typing import List
 
 import pytest
 
 from swh.core.pytest_plugin import requests_mock_datadir_factory
 from swh.lister import __version__
 from swh.lister.cgit.lister import CGitLister, _parse_last_updated_date
 from swh.lister.pattern import ListerStats
 
 
 def test_lister_cgit_get_pages_one_page(requests_mock_datadir, swh_scheduler):
     url = "https://git.savannah.gnu.org/cgit/"
     lister_cgit = CGitLister(swh_scheduler, url=url)
 
     repos: List[List[str]] = list(lister_cgit.get_pages())
     flattened_repos = sum(repos, [])
     assert len(flattened_repos) == 977
 
     assert (
         flattened_repos[0]["url"] == "https://git.savannah.gnu.org/cgit/elisp-es.git/"
     )
     # note the url below is NOT a subpath of /cgit/
     assert (
         flattened_repos[-1]["url"] == "https://git.savannah.gnu.org/path/to/yetris.git/"
     )  # noqa
     # note the url below is NOT on the same server
     assert flattened_repos[-2]["url"] == "http://example.org/cgit/xstarcastle.git/"
 
 
 def test_lister_cgit_get_pages_with_pages(requests_mock_datadir, swh_scheduler):
     url = "https://git.tizen/cgit/"
     lister_cgit = CGitLister(swh_scheduler, url=url)
 
     repos: List[List[str]] = list(lister_cgit.get_pages())
     flattened_repos = sum(repos, [])
     # we should have 16 repos (listed on 3 pages)
     assert len(repos) == 3
     assert len(flattened_repos) == 16
 
 
 def test_lister_cgit_run_with_page(requests_mock_datadir, swh_scheduler):
     """cgit lister supports pagination"""
 
     url = "https://git.tizen/cgit/"
     lister_cgit = CGitLister(swh_scheduler, url=url)
 
     stats = lister_cgit.run()
 
     expected_nb_origins = 16
     assert stats == ListerStats(pages=3, origins=expected_nb_origins)
 
     # test page parsing
     scheduler_origins = swh_scheduler.get_listed_origins(
         lister_cgit.lister_obj.id
     ).results
     assert len(scheduler_origins) == expected_nb_origins
 
     # test listed repositories
     for listed_origin in scheduler_origins:
         assert listed_origin.visit_type == "git"
         assert listed_origin.url.startswith("https://git.tizen")
 
     # test user agent content
     assert len(requests_mock_datadir.request_history) != 0
     for request in requests_mock_datadir.request_history:
         assert "User-Agent" in request.headers
         user_agent = request.headers["User-Agent"]
         assert "Software Heritage Lister" in user_agent
         assert __version__ in user_agent
 
 
 def test_lister_cgit_run_populates_last_update(requests_mock_datadir, swh_scheduler):
     """cgit lister returns last updated date"""
 
     url = "https://git.tizen/cgit"
 
     urls_without_date = [
         f"https://git.tizen.org/cgit/{suffix_url}"
         for suffix_url in ["All-Projects", "All-Users", "Lock-Projects",]
     ]
 
     lister_cgit = CGitLister(swh_scheduler, url=url)
 
     stats = lister_cgit.run()
 
     expected_nb_origins = 16
     assert stats == ListerStats(pages=3, origins=expected_nb_origins)
 
     # test page parsing
     scheduler_origins = swh_scheduler.get_listed_origins(
         lister_cgit.lister_obj.id
     ).results
     assert len(scheduler_origins) == expected_nb_origins
 
     # test listed repositories
     for listed_origin in scheduler_origins:
         if listed_origin.url in urls_without_date:
             assert listed_origin.last_update is None
         else:
             assert listed_origin.last_update is not None
 
 
 @pytest.mark.parametrize(
     "date_str,expected_date",
     [
         ({}, None),
         ("unexpected date", None),
         ("2020-0140-10 10:10:10 (GMT)", None),
         (
             "2020-01-10 10:10:10 (GMT)",
             datetime(
                 year=2020,
                 month=1,
                 day=10,
                 hour=10,
                 minute=10,
                 second=10,
                 tzinfo=timezone.utc,
             ),
         ),
         (
             "2019-08-04 05:10:41 +0100",
             datetime(
                 year=2019,
                 month=8,
                 day=4,
                 hour=5,
                 minute=10,
                 second=41,
                 tzinfo=timezone(timedelta(hours=1)),
             ),
         ),
     ],
 )
 def test_lister_cgit_date_parsing(date_str, expected_date):
     """test cgit lister date parsing"""
 
     repository = {"url": "url", "last_updated_date": date_str}
 
     assert _parse_last_updated_date(repository) == expected_date
 
 
 requests_mock_datadir_missing_url = requests_mock_datadir_factory(
     ignore_urls=["https://git.tizen/cgit/adaptation/ap_samsung/audio-hal-e4x12/",]
 )
 
 
 def test_lister_cgit_get_origin_from_repo_failing(
     requests_mock_datadir_missing_url, swh_scheduler
 ):
     url = "https://git.tizen/cgit/"
     lister_cgit = CGitLister(swh_scheduler, url=url)
 
     stats = lister_cgit.run()
 
     expected_nb_origins = 15
     assert stats == ListerStats(pages=3, origins=expected_nb_origins)
 
 
 @pytest.mark.parametrize(
     "credentials, expected_credentials",
     [
         (None, []),
         ({"key": "value"}, []),
         (
             {"cgit": {"tizen": [{"username": "user", "password": "pass"}]}},
             [{"username": "user", "password": "pass"}],
         ),
     ],
 )
 def test_lister_cgit_instantiation_with_credentials(
     credentials, expected_credentials, swh_scheduler
 ):
     url = "https://git.tizen/cgit/"
     lister = CGitLister(
         swh_scheduler, url=url, instance="tizen", credentials=credentials
     )
 
     # Credentials are allowed in constructor
     assert lister.credentials == expected_credentials
 
 
 def test_lister_cgit_from_configfile(swh_scheduler_config, mocker):
     load_from_envvar = mocker.patch("swh.lister.pattern.load_from_envvar")
     load_from_envvar.return_value = {
         "scheduler": {"cls": "local", **swh_scheduler_config},
         "url": "https://git.tizen/cgit/",
         "instance": "tizen",
         "credentials": {},
     }
     lister = CGitLister.from_configfile()
     assert lister.scheduler is not None
     assert lister.credentials is not None
+
+
+@pytest.mark.parametrize(
+    "url,base_git_url,expected_nb_origins",
+    [
+        ("https://git.eclipse.org/c", "https://eclipse.org/r", 5),
+        ("https://git.baserock.org/cgit/", "https://git.baserock.org/git/", 3),
+        ("https://jff.email/cgit/", "git://jff.email/opt/git/", 6),
+    ],
+)
+def test_lister_cgit_with_base_git_url(
+    url, base_git_url, expected_nb_origins, requests_mock_datadir, swh_scheduler
+):
+    """With base git url provided, listed urls should be the computed origin urls
+
+    """
+    lister_cgit = CGitLister(swh_scheduler, url=url, base_git_url=base_git_url,)
+
+    stats = lister_cgit.run()
+
+    assert stats == ListerStats(pages=1, origins=expected_nb_origins)
+
+    # test page parsing
+    scheduler_origins = swh_scheduler.get_listed_origins(
+        lister_cgit.lister_obj.id
+    ).results
+    assert len(scheduler_origins) == expected_nb_origins
+
+    # test listed repositories
+    for listed_origin in scheduler_origins:
+        assert listed_origin.visit_type == "git"
+        assert listed_origin.url.startswith(base_git_url)
+        assert (
+            listed_origin.url.startswith(url) is False
+        ), f"url should be mapped to {base_git_url}"
diff --git a/swh/lister/cgit/tests/test_tasks.py b/swh/lister/cgit/tests/test_tasks.py
index f348221..b9a00cd 100644
--- a/swh/lister/cgit/tests/test_tasks.py
+++ b/swh/lister/cgit/tests/test_tasks.py
@@ -1,35 +1,35 @@
 # Copyright (C) 2019-2021 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
 
 from swh.lister.pattern import ListerStats
 
 
 def test_cgit_ping(swh_scheduler_celery_app, swh_scheduler_celery_worker):
     res = swh_scheduler_celery_app.send_task("swh.lister.cgit.tasks.ping")
     assert res
     res.wait()
     assert res.successful()
     assert res.result == "OK"
 
 
 def test_cgit_lister_task(
     swh_scheduler_celery_app, swh_scheduler_celery_worker, mocker
 ):
     # setup the mocked CGitLister
     lister = mocker.patch("swh.lister.cgit.tasks.CGitLister")
     lister.from_configfile.return_value = lister
     lister.run.return_value = ListerStats(pages=10, origins=500)
 
-    kwargs = dict(url="https://git.kernel.org/", instance="kernel")
+    kwargs = dict(url="https://git.kernel.org/", instance="kernel", base_git_url=None)
 
     res = swh_scheduler_celery_app.send_task(
         "swh.lister.cgit.tasks.CGitListerTask", kwargs=kwargs,
     )
     assert res
     res.wait()
     assert res.successful()
 
     lister.from_configfile.assert_called_once_with(**kwargs)
     lister.run.assert_called_once_with()
diff --git a/swh/lister/gnu/__init__.py b/swh/lister/gnu/__init__.py
index eec08d4..e750c90 100644
--- a/swh/lister/gnu/__init__.py
+++ b/swh/lister/gnu/__init__.py
@@ -1,14 +1,12 @@
-# Copyright (C) 2019 the Software Heritage developers
+# Copyright (C) 2019-2021 the Software Heritage developers
 # License: GNU General Public License version 3, or any later version
 # See top-level LICENSE file for more information
 
 
 def register():
     from .lister import GNULister
-    from .models import GNUModel
 
     return {
-        "models": [GNUModel],
         "lister": GNULister,
         "task_modules": ["%s.tasks" % __name__],
     }
diff --git a/swh/lister/gnu/lister.py b/swh/lister/gnu/lister.py
index e6582fb..7d976ee 100644
--- a/swh/lister/gnu/lister.py
+++ b/swh/lister/gnu/lister.py
@@ -1,112 +1,68 @@
-# Copyright (C) 2019 the Software Heritage developers
+# Copyright (C) 2019-2021  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 Any, Dict, List
+from typing import Any, Iterator, Mapping
 
-from requests import Response
+import iso8601
 
-from swh.lister.core.simple_lister import SimpleLister
-from swh.lister.gnu.models import GNUModel
-from swh.lister.gnu.tree import GNUTree
-from swh.scheduler import utils
+from swh.scheduler.interface import SchedulerInterface
+from swh.scheduler.model import ListedOrigin
 
-logger = logging.getLogger(__name__)
-
-
-class GNULister(SimpleLister):
-    MODEL = GNUModel
-    LISTER_NAME = "gnu"
-    instance = "gnu"
+from ..pattern import CredentialsType, StatelessLister
+from .tree import GNUTree
 
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.gnu_tree = GNUTree("https://ftp.gnu.org/tree.json.gz")
+logger = logging.getLogger(__name__)
 
-    def task_dict(self, origin_type, origin_url, **kwargs):
-        """Return task format dict
+GNUPageType = Mapping[str, Any]
 
-        This is overridden from the lister_base as more information is
-        needed for the ingestion task creation.
 
-        This creates tasks with args and kwargs set, for example:
+class GNULister(StatelessLister[GNUPageType]):
+    """
+    List all GNU projects and associated artifacts.
+    """
 
-        .. code-block:: python
+    LISTER_NAME = "GNU"
+    GNU_FTP_URL = "https://ftp.gnu.org"
 
-            args:
-            kwargs: {
-                'url': 'https://ftp.gnu.org/gnu/3dldf/',
-                'artifacts': [{
-                    'url': 'https://...',
-                    'time': '2003-12-09T21:43:20+00:00',
-                    'length': 128,
-                    'version': '1.0.1',
-                    'filename': 'something-1.0.1.tar.gz',
-                },
-                ...
-                ]
-            }
+    def __init__(
+        self, scheduler: SchedulerInterface, credentials: CredentialsType = None,
+    ):
+        super().__init__(
+            scheduler=scheduler,
+            url=self.GNU_FTP_URL,
+            instance="GNU",
+            credentials=credentials,
+        )
+        self.gnu_tree = GNUTree(f"{self.url}/tree.json.gz")
 
+    def get_pages(self) -> Iterator[GNUPageType]:
         """
-        artifacts = self.gnu_tree.artifacts[origin_url]
-        assert origin_type == "tar"
-        return utils.create_task_dict(
-            "load-archive-files",
-            kwargs.get("policy", "oneshot"),
-            url=origin_url,
-            artifacts=artifacts,
-            retries_left=3,
-        )
+        Yield a single page listing all GNU projects.
+        """
+        yield self.gnu_tree.projects
 
-    def safely_issue_request(self, identifier: int) -> None:
-        """Bypass the implementation. It's now the GNUTree which deals with
-        querying the gnu mirror.
+    def get_origins_from_page(self, page: GNUPageType) -> Iterator[ListedOrigin]:
+        """
+        Iterate on all GNU projects and yield ListedOrigin instances.
+        """
+        assert self.lister_obj.id is not None
 
-        As an implementation detail, we cannot change simply the base
-        SimpleLister as other implementation still uses it. This shall be part
-        of another refactoring pass.
+        artifacts = self.gnu_tree.artifacts
 
-        """
-        return None
-
-    def list_packages(self, response: Response) -> List[Dict[str, Any]]:
-        """List the actual gnu origins (package name) with their name, url and
-           associated tarballs.
-
-        Args:
-            response: Unused
-
-        Returns:
-            List of packages name, url, last modification time::
-
-                [
-                    {
-                        'name': '3dldf',
-                        'url': 'https://ftp.gnu.org/gnu/3dldf/',
-                        'time_modified': '2003-12-09T20:43:20+00:00'
-                    },
-                    {
-                        'name': '8sync',
-                        'url': 'https://ftp.gnu.org/gnu/8sync/',
-                        'time_modified': '2016-12-06T02:37:10+00:00'
-                    },
-                    ...
-                ]
+        for project_name, project_info in page.items():
 
-        """
-        return list(self.gnu_tree.projects.values())
+            origin_url = project_info["url"]
+            last_update = iso8601.parse_date(project_info["time_modified"])
 
-    def get_model_from_repo(self, repo: Dict[str, Any]) -> Dict[str, Any]:
-        """Transform from repository representation to model
+            logger.debug("Found origin %s last updated on %s", origin_url, last_update)
 
-        """
-        return {
-            "uid": repo["url"],
-            "name": repo["name"],
-            "full_name": repo["name"],
-            "html_url": repo["url"],
-            "origin_url": repo["url"],
-            "time_last_updated": repo["time_modified"],
-            "origin_type": "tar",
-        }
+            yield ListedOrigin(
+                lister_id=self.lister_obj.id,
+                url=origin_url,
+                visit_type="tar",
+                last_update=last_update,
+                extra_loader_arguments={"artifacts": artifacts[project_name]},
+            )
diff --git a/swh/lister/gnu/models.py b/swh/lister/gnu/models.py
deleted file mode 100644
index db024f7..0000000
--- a/swh/lister/gnu/models.py
+++ /dev/null
@@ -1,18 +0,0 @@
-# Copyright (C) 2019 the Software Heritage developers
-# License: GNU General Public License version 3, or any later version
-# See top-level LICENSE file for more information
-
-from sqlalchemy import Column, DateTime, String
-
-from ..core.models import ModelBase
-
-
-class GNUModel(ModelBase):
-    """a GNU repository representation
-
-    """
-
-    __tablename__ = "gnu_repo"
-
-    uid = Column(String, primary_key=True)
-    time_last_updated = Column(DateTime)
diff --git a/swh/lister/gnu/tasks.py b/swh/lister/gnu/tasks.py
index 3134582..8c90b36 100644
--- a/swh/lister/gnu/tasks.py
+++ b/swh/lister/gnu/tasks.py
@@ -1,18 +1,18 @@
-# Copyright (C) 2019 the Software Heritage developers
+# Copyright (C) 2019-2021 the Software Heritage developers
 # License: GNU General Public License version 3, or any later version
 # See top-level LICENSE file for more information
 
 from celery import shared_task
 
 from .lister import GNULister
 
 
 @shared_task(name=__name__ + ".GNUListerTask")
 def list_gnu_full(**lister_args):
     """List lister for the GNU source code archive"""
-    return GNULister(**lister_args).run()
+    return GNULister.from_configfile(**lister_args).run().dict()
 
 
 @shared_task(name=__name__ + ".ping")
 def _ping():
     return "OK"
diff --git a/swh/lister/gnu/tests/api_response.json b/swh/lister/gnu/tests/api_response.json
deleted file mode 100644
index 55e8204..0000000
--- a/swh/lister/gnu/tests/api_response.json
+++ /dev/null
@@ -1,37 +0,0 @@
-[{"type":"directory","name": ".","contents":[
-  {"type":"file","name":".footer.shtml","size":444,"time":"1359994299"},
-  {"type":"file","name":"find.txt.gz","size":261428,"time":"1557684608"},
-  {"type":"directory","name":"gnu","size":12288,"time":"1556742017","contents":[]},
-  {"type":"directory","name":"gnu+linux-distros","size":4096,"time":"1299783002","contents":[
-    {"type":"directory","name":"ututo-e","size":4096,"time":"1487780066","contents":[
-      {"type":"file","name":"README","size":48,"time":"1487780066"},
-      {"type":"file","name":"index.html","size":158,"time":"1487780054"}
-    ]}
-  ]},
-  {"type":"file","name":"ls-lrRt.txt.gz","size":480054,"time":"1557684607"},
-  {"type":"directory","name":"mirrors","size":4096,"time":"1114010630","contents":[
-    {"type":"directory","name":"dynebolic","size":4096,"time":"1317827602","contents":[
-      {"type":"file","name":"MOVED_TO_mirror.fsf.org_dynebolic","size":0,"time":"1317826935"},
-      {"type":"file","name":"index.html","size":107,"time":"1317827601"}
-    ]}
-  ]},
-  {"type":"link","name":"non-gnu","target":"gnu/non-gnu","size":11,"time":"1082055542","contents":[]},
-  {"type":"directory","name":"old-gnu","size":4096,"time":"1548360019","contents":[]},
-  {"type":"link","name":"pub","target":".","size":1,"time":"1060090003","contents":[]},
-  {"type":"directory","name":"savannah","size":4096,"time":"1194544006","contents":[
-    {"type":"file","name":"README","size":473,"time":"1143758028"}
-  ]},
-  {"type":"directory","name":"third-party","size":4096,"time":"1059825710","contents":[
-    {"type":"file","name":"README","size":374,"time":"983824071"}
-  ]},
-  {"type":"directory","name":"tmp","size":4096,"time":"1239072509","contents":[
-  ]},
-  {"type":"file","name":"tree.json.gz","size":0,"time":"1557684608"},
-  {"type":"directory","name":"video","size":4096,"time":"1367963189","contents":[
-    {"type":"file","name":".bash_history","size":27,"time":"1307027604"},
-    {"type":"file","name":"stallmanupv.ogg.sig","size":536,"time":"1299776853"}
-  ]},
-  {"type":"file","name":"welcome.msg","size":2830,"time":"1545163301"}
-]},
-{"type":"report","directories":2743,"files":63983}
-]
diff --git a/swh/lister/gnu/tests/conftest.py b/swh/lister/gnu/tests/conftest.py
deleted file mode 100644
index 23cd215..0000000
--- a/swh/lister/gnu/tests/conftest.py
+++ /dev/null
@@ -1,26 +0,0 @@
-# Copyright (C) 2019-2020 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 pytest
-
-
-@pytest.fixture
-def lister_under_test():
-    return "gnu"
-
-
-@pytest.fixture
-def lister_gnu(swh_lister):
-    for task_type in [
-        {
-            "type": "load-archive-files",
-            "description": "Load archive repository",
-            "backend_name": "swh.loader.packages.tasks.LoadArchive",
-            "default_interval": "1 day",
-        },
-    ]:
-        swh_lister.scheduler.create_task_type(task_type)
-
-    return swh_lister
diff --git a/swh/lister/gnu/tests/find_tarballs_output.json b/swh/lister/gnu/tests/find_tarballs_output.json
deleted file mode 100644
index f1ccd6c..0000000
--- a/swh/lister/gnu/tests/find_tarballs_output.json
+++ /dev/null
@@ -1,182 +0,0 @@
-[
-    {
-      "archive": "https://ftp.gnu.org/gnu/artanis/artanis-0.2.1.tar.bz2",
-      "date": "1495205979"
-    },
-    {
-      "archive": "https://ftp.gnu.org/gnu/artanis/artanis-0.2.1.tar.gz",
-      "date": "1495205967"
-    },
-    {
-      "archive": "https://ftp.gnu.org/gnu/artanis/artanis-0.2.12-f39e-dirty.tar.gz",
-      "date": "1494994222"
-    },
-    {
-      "archive": "https://ftp.gnu.org/gnu/artanis/artanis-0.2.3.tar.bz2",
-      "date": "1520284021"
-    },
-    {
-      "archive": "https://ftp.gnu.org/gnu/artanis/artanis-0.2.3.tar.gz",
-      "date": "1520284007"
-    },
-    {
-      "archive": "https://ftp.gnu.org/gnu/artanis/artanis-0.2.4.tar.bz2",
-      "date": "1521742071"
-    },
-    {
-      "archive": "https://ftp.gnu.org/gnu/artanis/artanis-0.2.4.tar.gz",
-      "date": "1521742057"
-    },
-    {
-      "archive": "https://ftp.gnu.org/gnu/artanis/artanis-0.2.5.tar.bz2",
-      "date": "1525717261"
-    },
-    {
-      "archive": "https://ftp.gnu.org/gnu/artanis/artanis-0.2.5.tar.gz",
-      "date": "1525717246"
-    },
-    {
-      "archive": "https://ftp.gnu.org/gnu/artanis/artanis-0.3.1.tar.bz2",
-      "date": "1546205569"
-    },
-    {
-      "archive": "https://ftp.gnu.org/gnu/artanis/artanis-0.3.1.tar.gz",
-      "date": "1546205555"
-    },
-    {
-      "archive": "https://ftp.gnu.org/gnu/artanis/artanis-0.3.tar.bz2",
-      "date": "1546205025"
-    },
-    {
-      "archive": "https://ftp.gnu.org/gnu/artanis/artanis-0.3.tar.gz",
-      "date": "1546205012"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/winboard/winboard-4_0_0-src.zip",
-      "date": "898422900"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/winboard/winboard-4_0_2-src.zip",
-      "date": "920018269"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/winboard/winboard-4_0_3-src.zip",
-      "date": "936750503"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/winboard/winboard-4_0_4-src.tar.gz",
-      "date": "944290190"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/winboard/winboard-4_0_5-src.tar.gz",
-      "date": "944600462"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/winboard/winboard-4_0_6-src.tar.gz",
-      "date": "952156231"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/winboard/winboard-4_0_7-src.tar.gz",
-      "date": "952313061"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/winboard/winboard-4_1_0-src.tar.gz",
-      "date": "969299378"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/winboard/winboard-4_2_0beta-src.tar.gz",
-      "date": "977027031"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/winboard/winboard-4_2_1-src.tar.gz",
-      "date": "981323331"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/winboard/winboard-4_2_2-src.tar.gz",
-      "date": "981570576"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/winboard/winboard-4_2_3-src.tar.gz",
-      "date": "982656672"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/winboard/winboard-4_2_4-src.tar.gz",
-      "date": "1007952574"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/winboard/winboard-4_2_5-src.tar.gz",
-      "date": "1008502483"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/winboard/winboard-4_2_6-src.tar.gz",
-      "date": "1012641285"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/xboard-3.6.2.tar.gz",
-      "date": "869814000"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/xboard-4.0.0.tar.gz",
-      "date": "898422900"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/xboard-4.0.2.tar.gz",
-      "date": "920018202"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/xboard-4.0.3.tar.gz",
-      "date": "936750512"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/xboard-4.0.4.tar.gz",
-      "date": "944290148"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/xboard-4.0.5.tar.gz",
-      "date": "944599461"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/xboard-4.0.6.tar.gz",
-      "date": "952156235"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/xboard-4.0.7.tar.gz",
-      "date": "952313085"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/xboard-4.1.0.tar.gz",
-      "date": "969299287"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/xboard-4.2.0beta.tar.gz",
-      "date": "977027108"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/xboard-4.2.1.tar.gz",
-      "date": "981323501"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/xboard-4.2.2.tar.gz",
-      "date": "981562809"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/xboard-4.2.3.tar.gz",
-      "date": "982657006"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/xboard-4.2.4.tar.gz",
-      "date": "1007952745"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/xboard-4.2.5.tar.gz",
-      "date": "1008466945"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/xboard-4.2.6.tar.gz",
-      "date": "1012641715"
-    },
-    {
-      "archive": "https://ftp.gnu.org/old-gnu/xboard/xboard-4.2.7.tar.gz",
-      "date": "1070057764"
-    }
-  ]
\ No newline at end of file
diff --git a/swh/lister/gnu/tests/test_lister.py b/swh/lister/gnu/tests/test_lister.py
index e17365a..8cbb3b1 100644
--- a/swh/lister/gnu/tests/test_lister.py
+++ b/swh/lister/gnu/tests/test_lister.py
@@ -1,47 +1,36 @@
-# Copyright (C) 2019-2020 The Software Heritage developers
+# Copyright (C) 2019-2021 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 ..lister import GNULister
 
-logger = logging.getLogger(__name__)
 
+def test_gnu_lister(swh_scheduler, requests_mock_datadir):
+    lister = GNULister(scheduler=swh_scheduler)
 
-def test_gnu_lister(lister_gnu, requests_mock_datadir):
-    lister_gnu.run()
+    stats = lister.run()
 
-    r = lister_gnu.scheduler.search_tasks(task_type="load-archive-files")
-    assert len(r) == 383
+    assert stats.pages == 1
+    assert stats.origins == 383
 
-    for row in r:
-        assert row["type"] == "load-archive-files"
-        # arguments check
-        args = row["arguments"]["args"]
-        assert len(args) == 0
+    scheduler_origins = swh_scheduler.get_listed_origins(lister.lister_obj.id).results
 
-        # kwargs
-        kwargs = row["arguments"]["kwargs"]
-        assert set(kwargs.keys()) == {"url", "artifacts"}
+    assert len(scheduler_origins) == stats.origins
 
-        url = kwargs["url"]
-        assert url.startswith("https://ftp.gnu.org")
+    for origin in scheduler_origins:
+        assert origin.url.startswith(GNULister.GNU_FTP_URL)
+        assert origin.last_update is not None
+        assert "artifacts" in origin.extra_loader_arguments
+        assert len(origin.extra_loader_arguments["artifacts"]) > 0
 
-        url_suffix = url.split("https://ftp.gnu.org")[1]
-        assert "gnu" in url_suffix or "old-gnu" in url_suffix
 
-        artifacts = kwargs["artifacts"]
-        # check the artifact's structure
-        artifact = artifacts[0]
-        assert set(artifact.keys()) == {"url", "length", "time", "filename", "version"}
-
-        for artifact in artifacts:
-            logger.debug(artifact)
-            # 'time' is an isoformat string now
-            for key in ["url", "time", "filename", "version"]:
-                assert isinstance(artifact[key], str)
-            assert isinstance(artifact["length"], int)
-
-        assert row["policy"] == "oneshot"
-        assert row["priority"] is None
-        assert row["retries_left"] == 3
+def test_gnu_lister_from_configfile(swh_scheduler_config, mocker):
+    load_from_envvar = mocker.patch("swh.lister.pattern.load_from_envvar")
+    load_from_envvar.return_value = {
+        "scheduler": {"cls": "local", **swh_scheduler_config},
+        "credentials": {},
+    }
+    lister = GNULister.from_configfile()
+    assert lister.scheduler is not None
+    assert lister.credentials is not None
diff --git a/swh/lister/gnu/tests/test_tasks.py b/swh/lister/gnu/tests/test_tasks.py
index d91f86a..464d622 100644
--- a/swh/lister/gnu/tests/test_tasks.py
+++ b/swh/lister/gnu/tests/test_tasks.py
@@ -1,30 +1,30 @@
-# Copyright (C) 2019-2020  The Software Heritage developers
+# Copyright (C) 2019-2021  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
 
-from unittest.mock import patch
+from swh.lister.pattern import ListerStats
 
 
 def test_ping(swh_scheduler_celery_app, swh_scheduler_celery_worker):
     res = swh_scheduler_celery_app.send_task("swh.lister.gnu.tasks.ping")
     assert res
     res.wait()
     assert res.successful()
     assert res.result == "OK"
 
 
-@patch("swh.lister.gnu.tasks.GNULister")
-def test_lister(lister, swh_scheduler_celery_app, swh_scheduler_celery_worker):
-    # setup the mocked GNULister
-    lister.return_value = lister
-    lister.run.return_value = None
+def test_lister(swh_scheduler_celery_app, swh_scheduler_celery_worker, mocker):
+    lister = mocker.patch("swh.lister.gnu.tasks.GNULister")
+    lister.from_configfile.return_value = lister
+    stats = ListerStats(pages=1, origins=300)
+    lister.run.return_value = stats
 
     res = swh_scheduler_celery_app.send_task("swh.lister.gnu.tasks.GNUListerTask")
     assert res
     res.wait()
     assert res.successful()
+    assert res.result == stats.dict()
 
-    lister.assert_called_once_with()
-    lister.db_last_index.assert_not_called()
+    lister.from_configfile.assert_called_once_with()
     lister.run.assert_called_once_with()
diff --git a/swh/lister/pattern.py b/swh/lister/pattern.py
index 4f541fb..1a6b3e3 100644
--- a/swh/lister/pattern.py
+++ b/swh/lister/pattern.py
@@ -1,277 +1,277 @@
 # Copyright (C) 2020  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
 
 from dataclasses import dataclass
 from typing import Any, Dict, Generic, Iterable, Iterator, List, Optional, TypeVar
 
 from swh.core.config import load_from_envvar
 from swh.core.utils import grouper
 from swh.scheduler import get_scheduler, model
 from swh.scheduler.interface import SchedulerInterface
 
 
 @dataclass
 class ListerStats:
     pages: int = 0
     origins: int = 0
 
     def __add__(self, other: "ListerStats") -> "ListerStats":
         return self.__class__(self.pages + other.pages, self.origins + other.origins)
 
     def __iadd__(self, other: "ListerStats"):
         self.pages += other.pages
         self.origins += other.origins
 
     def dict(self) -> Dict[str, int]:
         return {"pages": self.pages, "origins": self.origins}
 
 
 StateType = TypeVar("StateType")
 PageType = TypeVar("PageType")
 
 BackendStateType = Dict[str, Any]
 CredentialsType = Optional[Dict[str, Dict[str, List[Dict[str, str]]]]]
 
 
 class Lister(Generic[StateType, PageType]):
     """The base class for a Software Heritage lister.
 
     A lister scrapes a page by page list of origins from an upstream (a forge, the API
     of a package manager, ...), and massages the results of that scrape into a list of
     origins that are recorded by the scheduler backend.
 
     The main loop of the lister, :meth:`run`, basically revolves around the
     :meth:`get_pages` iterator, which sets up the lister state, then yields the scrape
     results page by page. The :meth:`get_origins_from_page` method converts the pages
     into a list of :class:`model.ListedOrigin`, sent to the scheduler at every page. The
     :meth:`commit_page` method can be used to update the lister state after a page of
     origins has been recorded in the scheduler backend.
 
     The :func:`finalize` method is called at lister teardown (whether the run has
     been successful or not) to update the local :attr:`state` object before it's sent to
     the database. This method must set the :attr:`updated` attribute if an updated
     state needs to be sent to the scheduler backend. This method can call
     :func:`get_state_from_scheduler` to refresh and merge the lister state from the
     scheduler before it's finalized (and potentially minimize the risk of race
     conditions between concurrent runs of the lister).
 
     The state of the lister is serialized and deserialized from the dict stored in the
     scheduler backend, using the :meth:`state_from_dict` and :meth:`state_to_dict`
     methods.
 
     Args:
       scheduler: the instance of the Scheduler being used to register the
         origins listed by this lister
       url: a URL representing this lister, e.g. the API's base URL
       instance: the instance name used, in conjunction with :attr:`LISTER_NAME`, to
         uniquely identify this lister instance.
       credentials: dictionary of credentials for all listers. The first level
         identifies the :attr:`LISTER_NAME`, the second level the lister
         :attr:`instance`. The final level is a list of dicts containing the
         expected credentials for the given instance of that lister.
 
     Generic types:
       - *StateType*: concrete lister type; should usually be a :class:`dataclass` for
         stricter typing
       - *PageType*: type of scrape results; can usually be a :class:`requests.Response`,
         or a :class:`dict`
 
     """
 
     LISTER_NAME: str = ""
 
     def __init__(
         self,
         scheduler: SchedulerInterface,
         url: str,
         instance: str,
         credentials: CredentialsType = None,
     ):
         if not self.LISTER_NAME:
             raise ValueError("Must set the LISTER_NAME attribute on Lister classes")
 
         self.url = url
         self.instance = instance
 
         self.scheduler = scheduler
 
         if not credentials:
             credentials = {}
         self.credentials = list(
             credentials.get(self.LISTER_NAME, {}).get(self.instance, [])
         )
 
         # store the initial state of the lister
         self.state = self.get_state_from_scheduler()
         self.updated = False
 
     def run(self) -> ListerStats:
         """Run the lister.
 
         Returns:
           A counter with the number of pages and origins seen for this run
           of the lister.
 
         """
         full_stats = ListerStats()
 
         try:
             for page in self.get_pages():
                 full_stats.pages += 1
                 origins = self.get_origins_from_page(page)
                 full_stats.origins += self.send_origins(origins)
                 self.commit_page(page)
         finally:
             self.finalize()
             if self.updated:
                 self.set_state_in_scheduler()
 
         return full_stats
 
     def get_state_from_scheduler(self) -> StateType:
         """Update the state in the current instance from the state in the scheduler backend.
 
         This updates :attr:`lister_obj`, and returns its (deserialized) current state,
         to allow for comparison with the local state.
 
         Returns:
           the state retrieved from the scheduler backend
         """
         self.lister_obj = self.scheduler.get_or_create_lister(
             name=self.LISTER_NAME, instance_name=self.instance
         )
         return self.state_from_dict(self.lister_obj.current_state)
 
     def set_state_in_scheduler(self) -> None:
         """Update the state in the scheduler backend from the state of the current instance.
 
         Raises:
           :class:`swh.scheduler.exc.StaleData` in case of a race condition between
           concurrent listers (from :meth:`swh.scheduler.Scheduler.update_lister`).
         """
         self.lister_obj.current_state = self.state_to_dict(self.state)
         self.lister_obj = self.scheduler.update_lister(self.lister_obj)
 
     # State management to/from the scheduler
 
     def state_from_dict(self, d: BackendStateType) -> StateType:
         """Convert the state stored in the scheduler backend (as a dict),
         to the concrete StateType for this lister."""
         raise NotImplementedError
 
     def state_to_dict(self, state: StateType) -> BackendStateType:
         """Convert the StateType for this lister to its serialization as dict for
         storage in the scheduler.
 
         Values must be JSON-compatible as that's what the backend database expects.
         """
         raise NotImplementedError
 
     def finalize(self) -> None:
         """Custom hook to finalize the lister state before returning from the main loop.
 
         This method must set :attr:`updated` if the lister has done some work.
 
         If relevant, this method can use :meth`get_state_from_scheduler` to merge the
         current lister state with the one from the scheduler backend, reducing the risk
         of race conditions if we're running concurrent listings.
 
         This method is called in a `finally` block, which means it will also run when
         the lister fails.
 
         """
         pass
 
     # Actual listing logic
 
     def get_pages(self) -> Iterator[PageType]:
         """Retrieve a list of pages of listed results. This is the main loop of the lister.
 
         Returns:
           an iterator of raw pages fetched from the platform currently being listed.
         """
         raise NotImplementedError
 
     def get_origins_from_page(self, page: PageType) -> Iterator[model.ListedOrigin]:
         """Extract a list of :class:`model.ListedOrigin` from a raw page of results.
 
         Args:
           page: a single page of results
         Returns:
           an iterator for the origins present on the given page of results
         """
         raise NotImplementedError
 
     def commit_page(self, page: PageType) -> None:
         """Custom hook called after the current page has been committed in the scheduler
         backend.
 
         This method can be used to update the state after a page of origins has been
         successfully recorded in the scheduler backend. If the new state should be
         recorded at the point the lister completes, the :attr:`updated` attribute must
         be set.
 
         """
         pass
 
     def send_origins(self, origins: Iterable[model.ListedOrigin]) -> int:
         """Record a list of :class:`model.ListedOrigin` in the scheduler.
 
         Returns:
           the number of listed origins recorded in the scheduler
         """
         count = 0
-        for batch_origins in grouper(origins, n=100):
+        for batch_origins in grouper(origins, n=1000):
             ret = self.scheduler.record_listed_origins(batch_origins)
             count += len(ret)
 
         return count
 
     @classmethod
     def from_config(cls, scheduler: Dict[str, Any], **config: Any):
         """Instantiate a lister from a configuration dict.
 
         This is basically a backwards-compatibility shim for the CLI.
 
         Args:
           scheduler: instantiation config for the scheduler
           config: the configuration dict for the lister, with the following keys:
             - credentials (optional): credentials list for the scheduler
             - any other kwargs passed to the lister.
 
         Returns:
           the instantiated lister
         """
         # Drop the legacy config keys which aren't used for this generation of listers.
         for legacy_key in ("storage", "lister", "celery"):
             config.pop(legacy_key, None)
 
         # Instantiate the scheduler
         scheduler_instance = get_scheduler(**scheduler)
 
         return cls(scheduler=scheduler_instance, **config)
 
     @classmethod
     def from_configfile(cls, **kwargs: Any):
         """Instantiate a lister from the configuration loaded from the
         SWH_CONFIG_FILENAME envvar, with potential extra keyword arguments
         if their value is not None.
 
         Args:
             kwargs: kwargs passed to the lister instantiation
         """
         config = dict(load_from_envvar())
         config.update({k: v for k, v in kwargs.items() if v is not None})
         return cls.from_config(**config)
 
 
 class StatelessLister(Lister[None, PageType], Generic[PageType]):
     def state_from_dict(self, d: BackendStateType) -> None:
         """Always return empty state"""
         return None
 
     def state_to_dict(self, state: None) -> BackendStateType:
         """Always set empty state"""
         return {}