Remove euscanwww leftovers from TODO

Signed-off-by: Alfred Wingate <parona@protonmail.com>

MANIFEST.in

@@ -1,8 +1,8 @@
 include AUTHORS
+include CHANGELOG.rst
 include LICENSE
 include README.rst
 include TODO
-include setup.py
+include pyproject.toml
 recursive-include bin *
-recursive-include man *
-recursive-include pym *.py
+recursive-include src *.py

TODO

@@ -50,43 +50,6 @@ euscan
 - Propose new remote-id: freecode
   e.g.: <remote-id type="freecode">projectname</remote-id>
 
-
-euscanwww
----------
-
-### misc
-
-- Really fix mails: better formating
-- Always keep in db all found versions (when using an API only?). But don't display them if older than current packaged version, except maybe in the "upstream_version" column.
-
-### packages
-
-- Ignore alpha/beta if current is not alpha/beta: per-package setting using metadata.xml ?
-- ~arch / stable support: see "models: keywords"
-- stabilisation candidates: check stabilizations rules, and see how this can be automated
-- set upstream version by hand: will be done after uscan compatiblity
-
-### logs
-
-- Move log models into djeuscanhistory ?
-
-### models
-
-- Repository (added or not, from layman + repositories.xml)
-- Arches and Keyword
-- Metadata, herds, maintainers and homepage are per-version, not per package. Store it in Version instead.
-
-### djportage (LOW-PRIORITY))
-
-- Create standalone application to scan and represent portage trees in models using work done in:
--- euscan
--- p.g.o: https://github.com/bacher09/gentoo-packages
--- gentoostats: https://github.com/gg7/gentoostats_server/blob/master/gentoostats/stats/models.py
-
-The application should be easy to use, and we should be able to launch the scan process in a celery worker using "logging" for logs.
-The application should also be usable for p.g.o and gentoostats later...
-The scan process should be faster than the one using euscan. gentoo-packages have some interesting ideas for that (keeping metadata and ebuild hash, etc..)
-
 ### API (LOW-PRIORITY)
 
 - Move to tastypie

pyproject.toml

@@ -22,6 +22,7 @@ dynamic = ["version"]
 
 [project.urls]
 homepage = "https://gitlab.com/src_prepare/euscan-ng"
+changelog = "https://gitlab.com/src_prepare/euscan-ng/-/blob/master/CHANGELOG.rst"
 
 [tool.setuptools]
 script-files = ["bin/euscan"]

src/euscan/handlers/generic.py

@@ -8,14 +8,11 @@ import re
 import urllib.error
 import urllib.parse
 import urllib.request
+import warnings
 from urllib.parse import urljoin, urlparse
 
-try:
-    from BeautifulSoup import BeautifulSoup
-except ImportError:
-    from bs4 import BeautifulSoup
-
 import portage
+from bs4 import BeautifulSoup, XMLParsedAsHTMLWarning
 
 from euscan import (
     BRUTEFORCE_BLACKLIST_PACKAGES,
@@ -65,6 +62,7 @@ def confidence_score(found, original, minimum=CONFIDENCE):
 
 
 def scan_html(data, url, pattern):
+    warnings.filterwarnings("ignore", category=XMLParsedAsHTMLWarning)
     soup = BeautifulSoup(data, features="lxml")
     results = []