diff --git a/linkcheck/__init__.py b/linkcheck/__init__.py index 573d6bcf..b342f80a 100644 --- a/linkcheck/__init__.py +++ b/linkcheck/__init__.py @@ -74,7 +74,7 @@ def get_link_pat(arg, strict=False): @rtype: dict @raises: re.error on invalid regular expressions """ - log.debug(LOG_CHECK, "Link pattern %r strict=%s", arg, strict) + log.debug(LOG_CHECK, _("Link pattern %r strict=%s"), arg, strict) if arg.startswith('!'): pattern = arg[1:] negate = True @@ -84,7 +84,7 @@ def get_link_pat(arg, strict=False): try: regex = re.compile(pattern) except re.error as msg: - log.warn(LOG_CHECK, "invalid regular expression %r: %s" % (pattern, msg)) + log.warn(LOG_CHECK, _("invalid regular expression %r: %s"), pattern, msg) raise return { "pattern": regex, diff --git a/linkcheck/better_exchook2.py b/linkcheck/better_exchook2.py index cd5cc4f1..f4a5dee6 100644 --- a/linkcheck/better_exchook2.py +++ b/linkcheck/better_exchook2.py @@ -232,7 +232,7 @@ def better_exchook(etype, value, tb, out=sys.stdout): if value is None or not valuestr: line = "%s" % etype else: - line = "%s: %s" % (etype, valuestr) + line = f"{etype}: {valuestr}" return line if (isinstance(etype, BaseException) or (hasattr(types, "InstanceType") and isinstance(etype, types.InstanceType)) or diff --git a/linkcheck/bookmarks/chromium.py b/linkcheck/bookmarks/chromium.py index 4a4bf026..7183b10e 100644 --- a/linkcheck/bookmarks/chromium.py +++ b/linkcheck/bookmarks/chromium.py @@ -22,15 +22,13 @@ def parse_bookmark_data(data): Return iterator for bookmarks of the form (url, name). Bookmarks are not sorted. """ - for url, name in parse_bookmark_json(json.loads(data)): - yield url, name + yield from parse_bookmark_json(json.loads(data)) def parse_bookmark_json(data): """Parse complete JSON data for Chromium Bookmarks.""" for entry in data["roots"].values(): - for url, name in parse_bookmark_node(entry): - yield url, name + yield from parse_bookmark_node(entry) def parse_bookmark_node(node): @@ -39,5 +37,4 @@ def parse_bookmark_node(node): yield node["url"], node["name"] elif node["type"] == "folder": for child in node["children"]: - for entry in parse_bookmark_node(child): - yield entry + yield from parse_bookmark_node(child) diff --git a/linkcheck/bookmarks/safari.py b/linkcheck/bookmarks/safari.py index 6d593f39..9ea2e97b 100644 --- a/linkcheck/bookmarks/safari.py +++ b/linkcheck/bookmarks/safari.py @@ -48,8 +48,7 @@ def parse_plist(entry): yield (url, title) elif has_children(entry): for child in entry[KEY_CHILDREN]: - for item in parse_plist(child): - yield item + yield from parse_plist(child) def is_leaf(entry): diff --git a/linkcheck/checker/__init__.py b/linkcheck/checker/__init__.py index dd0a28f5..91fbb588 100644 --- a/linkcheck/checker/__init__.py +++ b/linkcheck/checker/__init__.py @@ -39,10 +39,10 @@ def guess_url(url): return url if url.lower().startswith("www."): # syntactic sugar - return "http://%s" % url + return f"http://{url}" elif url.lower().startswith("ftp."): # syntactic sugar - return "ftp://%s" % url + return f"ftp://{url}" return url @@ -197,7 +197,7 @@ def get_index_html(urls): except KeyError: # Some unicode entries raise KeyError. url = name - lines.append('%s' % (url, name)) + lines.append(f'{name}') lines.extend(["", ""]) return os.linesep.join(lines) diff --git a/linkcheck/checker/const.py b/linkcheck/checker/const.py index bf4a8be6..c5d3fe9e 100644 --- a/linkcheck/checker/const.py +++ b/linkcheck/checker/const.py @@ -17,7 +17,6 @@ Helper constants. """ import socket -import select import nntplib import ftplib import requests @@ -37,8 +36,6 @@ ExcCacheList = [ OSError, # OSError is thrown on Windows when a file is not found LinkCheckerError, DNSException, - socket.error, - select.error, # nttp errors (including EOFError) nntplib.NNTPError, EOFError, diff --git a/linkcheck/checker/fileurl.py b/linkcheck/checker/fileurl.py index 39d8ab6d..1503a29d 100644 --- a/linkcheck/checker/fileurl.py +++ b/linkcheck/checker/fileurl.py @@ -357,10 +357,10 @@ class AnchorCheckFileUrl(FileUrl): if self.anchor: self.add_warning( _( - f" URL `{self.url}' is a directory with an anchor." + "URL `%s' is a directory with an anchor." " When checking local files AnchorCheck does not support" " anchors for directories." - ), + ) % self.url, tag=WARN_FILE_ANCHORCHECK_DIRECTORY, ) diff --git a/linkcheck/checker/ftpurl.py b/linkcheck/checker/ftpurl.py index 15d55f8f..cf776655 100644 --- a/linkcheck/checker/ftpurl.py +++ b/linkcheck/checker/ftpurl.py @@ -118,7 +118,7 @@ class FtpUrl(internpaturl.InternPatternUrl): # file found return # it could be a directory if the trailing slash was forgotten - if "%s/" % self.filename in files: + if f"{self.filename}/" in files: if not self.url.endswith('/'): self.add_warning( _("Missing trailing directory slash in ftp url."), @@ -178,7 +178,7 @@ class FtpUrl(internpaturl.InternPatternUrl): data = get_index_html(self.files) else: # download file in BINARY mode - ftpcmd = "RETR %s" % self.filename + ftpcmd = f"RETR {self.filename}" buf = StringIO() def stor_data(s): diff --git a/linkcheck/checker/httpurl.py b/linkcheck/checker/httpurl.py index 66280219..40392a44 100644 --- a/linkcheck/checker/httpurl.py +++ b/linkcheck/checker/httpurl.py @@ -348,7 +348,7 @@ class HttpUrl(internpaturl.InternPatternUrl): """Parse URLs in HTTP headers Link:.""" for linktype, linkinfo in self.url_connection.links.items(): url = linkinfo["url"] - name = "Link: header %s" % linktype + name = f"Link: header {linktype}" self.add_url(url, name=name) if 'Refresh' in self.headers: from ..htmlutil.linkparse import refresh_re diff --git a/linkcheck/checker/mailtourl.py b/linkcheck/checker/mailtourl.py index 536f0baa..9180aa61 100644 --- a/linkcheck/checker/mailtourl.py +++ b/linkcheck/checker/mailtourl.py @@ -247,7 +247,7 @@ class MailtoUrl(urlbase.UrlBase): ) return for char in '@ \\",[]': - if char in local.replace("\\%s" % char, ""): + if char in local.replace(f"\\{char}", ""): self.set_result( _( "Local part of mail address `%(addr)s' contains" @@ -370,7 +370,7 @@ class MailtoUrl(urlbase.UrlBase): The cache url is a comma separated list of emails. """ emails = ",".join(sorted(self.addresses)) - self.cache_url = "%s:%s" % (self.scheme, emails) + self.cache_url = f"{self.scheme}:{emails}" def can_get_content(self): """ diff --git a/linkcheck/checker/unknownurl.py b/linkcheck/checker/unknownurl.py index 44422a49..f4e5a34d 100644 --- a/linkcheck/checker/unknownurl.py +++ b/linkcheck/checker/unknownurl.py @@ -423,7 +423,7 @@ ignored_schemes_other = r""" |whatsapp # WhatsApp """ -ignored_schemes = "^(%s%s%s%s)$" % ( +ignored_schemes = "^({}{}{}{})$".format( ignored_schemes_permanent, ignored_schemes_provisional, ignored_schemes_historical, diff --git a/linkcheck/checker/urlbase.py b/linkcheck/checker/urlbase.py index 9bd0484f..1a1cdcaa 100644 --- a/linkcheck/checker/urlbase.py +++ b/linkcheck/checker/urlbase.py @@ -23,7 +23,6 @@ from urllib.request import urlopen import time import errno import socket -import select from io import BytesIO from . import absolute_url, get_url_from @@ -507,9 +506,9 @@ class UrlBase: if not self.port or self.port == urlutil.default_ports.get(self.scheme): host = self.host else: - host = "%s:%d" % (self.host, self.port) + host = f"{self.host}:{self.port}" if self.userinfo: - urlparts[1] = "%s@%s" % (self.userinfo, host) + urlparts[1] = f"{self.userinfo}@{host}" else: urlparts[1] = host # save anchor for later checking @@ -538,7 +537,7 @@ class UrlBase: trace.trace_on() try: self.local_check() - except (socket.error, select.error): + except OSError: # on Unix, ctrl-c can raise # error: (4, 'Interrupted system call') etype, value = sys.exc_info()[:2] @@ -624,7 +623,7 @@ class UrlBase: # format message ": " errmsg = etype.__name__ if evalue: - errmsg += ": %s" % evalue + errmsg += f": {evalue}" # limit length to 240 return strformat.limit(errmsg, length=240) @@ -882,7 +881,7 @@ class UrlBase: @return: URL info @rtype: unicode """ - return "<%s>" % self.serialized(sep=", ") + return f'<{self.serialized(sep=", ")}>' def to_wire_dict(self): """Return a simplified transport object for logging and caching. diff --git a/linkcheck/colorama.py b/linkcheck/colorama.py index d3bd1273..afa3046e 100644 --- a/linkcheck/colorama.py +++ b/linkcheck/colorama.py @@ -119,7 +119,7 @@ def init(): global _default_foreground, _default_background, _default_style try: attrs = GetConsoleScreenBufferInfo().wAttributes - except (ArgumentError, WindowsError): + except (ArgumentError, OSError): _default_foreground = GREY _default_background = BLACK _default_style = NORMAL diff --git a/linkcheck/command/arg_parser.py b/linkcheck/command/arg_parser.py index 0f1fa291..1e8c346a 100644 --- a/linkcheck/command/arg_parser.py +++ b/linkcheck/command/arg_parser.py @@ -180,7 +180,7 @@ file entry: ) + "\n".join( [ - " o %s - %s" % (tag, desc) + f" o {tag} - {desc}" for tag, desc in sorted(checker.const.Warnings.items()) ] ) diff --git a/linkcheck/configuration/__init__.py b/linkcheck/configuration/__init__.py index 9892da0d..f940c5ba 100644 --- a/linkcheck/configuration/__init__.py +++ b/linkcheck/configuration/__init__.py @@ -46,7 +46,7 @@ HtmlCopyright = ( HtmlAppInfo = App + ", " + HtmlCopyright Url = _release.__url__ SupportUrl = _release.__support_url__ -UserAgent = "Mozilla/5.0 (compatible; %s/%s; +%s)" % (AppName, Version, Url) +UserAgent = f"Mozilla/5.0 (compatible; {AppName}/{Version}; +{Url})" Freeware = ( AppName + """ comes with ABSOLUTELY NO WARRANTY! @@ -87,7 +87,7 @@ def get_modules_info(): if version_attr and hasattr(mod, version_attr): attr = getattr(mod, version_attr) version = attr() if callable(attr) else attr - module_infos.append("%s %s" % (name, version)) + module_infos.append(f"{name} {version}") else: # ignore attribute errors in case library developers # change the version information attribute diff --git a/linkcheck/configuration/confparse.py b/linkcheck/configuration/confparse.py index 2d64c75a..544dce3e 100644 --- a/linkcheck/configuration/confparse.py +++ b/linkcheck/configuration/confparse.py @@ -227,7 +227,7 @@ class LCConfigParser(RawConfigParser): self.config.add_auth( pattern=auth[0], user=auth[1], password=auth[2] ) - password_fields.append("entry/%s/%s" % (auth[0], auth[1])) + password_fields.append(f"entry/{auth[0]}/{auth[1]}") elif len(auth) == 2: self.config.add_auth(pattern=auth[0], user=auth[1]) else: diff --git a/linkcheck/director/console.py b/linkcheck/director/console.py index e2bc6e06..761b7fab 100644 --- a/linkcheck/director/console.py +++ b/linkcheck/director/console.py @@ -53,7 +53,7 @@ class StatusLogger: def writeln(self, msg): """Write status message and line break to file descriptor.""" - self.fd.write("%s%s" % (msg, os.linesep)) + self.fd.write(f"{msg}{os.linesep}") def flush(self): """Flush file descriptor.""" diff --git a/linkcheck/htmlutil/loginformsearch.py b/linkcheck/htmlutil/loginformsearch.py index 77103414..238994e7 100644 --- a/linkcheck/htmlutil/loginformsearch.py +++ b/linkcheck/htmlutil/loginformsearch.py @@ -34,7 +34,7 @@ class Form: def __repr__(self): """Return string displaying URL and form data.""" - return "" % (self.url, self.data) + return f"" def search_form(content, cgiuser, cgipassword): diff --git a/linkcheck/i18n.py b/linkcheck/i18n.py index 847ebccd..182acfe2 100644 --- a/linkcheck/i18n.py +++ b/linkcheck/i18n.py @@ -25,7 +25,7 @@ import sys import codecs # more supported languages are added in init() -supported_languages = set(['en']) +supported_languages = {'en'} default_language = default_encoding = None default_directory = None default_domain = None @@ -68,7 +68,7 @@ def init(domain, directory, loc=None): # get supported languages for lang in os.listdir(directory): path = os.path.join(directory, lang, 'LC_MESSAGES') - mo_file = os.path.join(path, '%s.mo' % domain) + mo_file = os.path.join(path, f"{domain}.mo") if os.path.exists(mo_file): supported_languages.add(lang) if loc is None: diff --git a/linkcheck/lc_cgi.py b/linkcheck/lc_cgi.py index b8f9d921..a3820f16 100644 --- a/linkcheck/lc_cgi.py +++ b/linkcheck/lc_cgi.py @@ -60,8 +60,7 @@ def application(environ, start_response): status = '200 OK' start_response(status, get_response_headers()) - for output in checklink(form=form, env=environ): - yield output + yield from checklink(form=form, env=environ) _supported_langs = ('de', 'C') @@ -113,7 +112,7 @@ class ThreadsafeIO: """Write given unicode data to buffer.""" assert isinstance(data, str) if self.closed: - raise IOError("Write on closed I/O object") + raise OSError("Write on closed I/O object") if data: self.buf.append(data) @@ -213,7 +212,7 @@ def checkform(form, env): locale.setlocale(locale.LC_ALL, localestr) init_i18n() except locale.Error as errmsg: - log(env, "could not set locale %r: %s" % (localestr, errmsg)) + log(env, _("could not set locale %r: %s") % (localestr, errmsg)) else: raise LCFormError(_("unsupported language %r") % lang) # check url syntax diff --git a/linkcheck/loader.py b/linkcheck/loader.py index d835d63e..25e94879 100644 --- a/linkcheck/loader.py +++ b/linkcheck/loader.py @@ -34,10 +34,10 @@ def get_package_modules(packagename, packagepath): for mod in pkgutil.iter_modules(packagepath): if not mod.ispkg: try: - name = "..%s.%s" % (packagename, mod.name) + name = f"..{packagename}.{mod.name}" yield importlib.import_module(name, __name__) except ImportError as msg: - print("WARN: could not load module %s: %s" % (mod.name, msg)) + print(_("WARN: could not load module %s: %s") % (mod.name, msg)) def get_folder_modules(folder, parentpackage): @@ -54,7 +54,7 @@ def get_folder_modules(folder, parentpackage): spec.loader.exec_module(module) yield module except ImportError as msg: - print("WARN: could not load file %s: %s" % (fullname, msg)) + print(_("WARN: could not load file %s: %s") % (fullname, msg)) def get_importable_files(folder): @@ -85,8 +85,7 @@ def get_plugins(modules, classes): @rtype: iterator of class objects """ for module in modules: - for plugin in get_module_plugins(module, classes): - yield plugin + yield from get_module_plugins(module, classes) def get_module_plugins(module, classes): diff --git a/linkcheck/logger/__init__.py b/linkcheck/logger/__init__.py index 77c4b6bc..f69ab088 100644 --- a/linkcheck/logger/__init__.py +++ b/linkcheck/logger/__init__.py @@ -226,7 +226,7 @@ class _Logger(abc.ABC): os.makedirs(path) self.fd = self.create_fd() self.close_fd = True - except IOError: + except OSError: msg = sys.exc_info()[1] log.warn( LOG_CHECK, @@ -255,13 +255,13 @@ class _Logger(abc.ABC): if self.fd is not None: try: self.flush() - except IOError: + except OSError: # ignore flush errors pass if self.close_fd: try: self.fd.close() - except IOError: + except OSError: # ignore close errors pass self.fd = None @@ -308,7 +308,7 @@ class _Logger(abc.ABC): else: try: self.fd.write(s, **args) - except IOError: + except OSError: msg = sys.exc_info()[1] log.warn( LOG_CHECK, @@ -325,7 +325,7 @@ class _Logger(abc.ABC): """ Write string to output descriptor plus a newline. """ - self.write("%s%s" % (s, os.linesep), **args) + self.write(f"{s}{os.linesep}", **args) def has_part(self, name): """ @@ -436,7 +436,7 @@ class _Logger(abc.ABC): if hasattr(self, "fd"): try: self.fd.flush() - except (IOError, AttributeError): + except (OSError, AttributeError): pass def log_internal_error(self): @@ -453,7 +453,7 @@ class _Logger(abc.ABC): @rtype: unicode """ if modified is not None: - return modified.strftime("%Y-%m-%d{0}%H:%M:%S.%fZ".format(sep)) + return modified.strftime(f"%Y-%m-%d{sep}%H:%M:%S.%fZ") return "" diff --git a/linkcheck/logger/dot.py b/linkcheck/logger/dot.py index fb17d0a1..a404cf56 100644 --- a/linkcheck/logger/dot.py +++ b/linkcheck/logger/dot.py @@ -70,10 +70,10 @@ class DOTLogger(_GraphLogger): """Write edge from parent to node.""" source = dotquote(self.nodes[node["parent_url"]]["label"]) target = dotquote(node["label"]) - self.writeln(' "%s" -> "%s" [' % (source, target)) - self.writeln(' label="%s",' % dotquote(node["edge"])) + self.writeln(f' "{source}" -> "{target}" [') + self.writeln(f' label="{dotquote(node["edge"])}",') if self.has_part("result"): - self.writeln(" valid=%d," % node["valid"]) + self.writeln(f' valid={node["valid"]},') self.writeln(" ];") def end_graph(self): diff --git a/linkcheck/logger/failures.py b/linkcheck/logger/failures.py index 7f93314f..a2b6fcdf 100644 --- a/linkcheck/logger/failures.py +++ b/linkcheck/logger/failures.py @@ -85,7 +85,7 @@ class FailuresLogger(_Logger): """ Read a previously stored failures from file fd. """ - with open(self.filename, 'r', encoding=self.output_encoding, + with open(self.filename, encoding=self.output_encoding, errors=self.codec_errors) as fd: for line in fd: line = line.rstrip() diff --git a/linkcheck/logger/sql.py b/linkcheck/logger/sql.py index 375174da..a16e55ba 100644 --- a/linkcheck/logger/sql.py +++ b/linkcheck/logger/sql.py @@ -112,8 +112,8 @@ class SQLLogger(_Logger): % { 'table': self.dbname, 'base_url': sqlify(url_data.base_url), - 'url_parent': sqlify((url_data.parent_url)), - 'base_ref': sqlify((url_data.base_ref)), + 'url_parent': sqlify(url_data.parent_url), + 'base_ref': sqlify(url_data.base_ref), 'valid': intify(url_data.valid), 'result': sqlify(url_data.result), 'warning': sqlify(os.linesep.join(x[1] for x in url_data.warnings)), diff --git a/linkcheck/logger/text.py b/linkcheck/logger/text.py index e4c697ae..ba09b2d9 100644 --- a/linkcheck/logger/text.py +++ b/linkcheck/logger/text.py @@ -202,7 +202,7 @@ class TextLogger(_Logger): def write_warning(self, url_data): """Write url_data.warning.""" self.write(self.part("warning") + self.spaces("warning")) - warning_msgs = ["[%s] %s" % x for x in url_data.warnings] + warning_msgs = [f"[{tag}] {msg}" for tag, msg in url_data.warnings] self.writeln(self.wrap(warning_msgs, 65), color=self.colorwarning) def write_result(self, url_data): diff --git a/linkcheck/logger/xmllog.py b/linkcheck/logger/xmllog.py index 33338d0a..995acb8c 100644 --- a/linkcheck/logger/xmllog.py +++ b/linkcheck/logger/xmllog.py @@ -113,4 +113,4 @@ class _XMLLogger(_Logger): for aname, avalue in attrs.items(): args = (xmlquote(aname), xmlquoteattr(avalue)) self.write(' %s="%s"' % args) - self.writeln(">%s" % (xmlquote(content), xmlquote(name))) + self.writeln(f">{xmlquote(content)}") diff --git a/linkcheck/network/iputil.py b/linkcheck/network/iputil.py index 16386fbe..4a846ea6 100644 --- a/linkcheck/network/iputil.py +++ b/linkcheck/network/iputil.py @@ -47,7 +47,7 @@ def resolve_host(host): # canonical name, socket address) # add first ip of socket address ips.append(res[4][0]) - except socket.error: + except OSError: log.info(LOG_CHECK, "Ignored invalid host %r", host) return ips diff --git a/linkcheck/plugins/__init__.py b/linkcheck/plugins/__init__.py index d357e4f5..e567cba6 100644 --- a/linkcheck/plugins/__init__.py +++ b/linkcheck/plugins/__init__.py @@ -65,10 +65,8 @@ class _ParserPlugin(_PluginBase): def get_plugin_modules(folders): """Get plugin modules for given folders.""" for folder in folders: - for module in loader.get_folder_modules(folder, 'linkcheck.dummy'): - yield module - for module in loader.get_package_modules('plugins', __path__): - yield module + yield from loader.get_folder_modules(folder, 'linkcheck.dummy') + yield from loader.get_package_modules('plugins', __path__) def get_plugin_classes(modules): diff --git a/linkcheck/plugins/anchorcheck.py b/linkcheck/plugins/anchorcheck.py index f7576b36..74a7183e 100644 --- a/linkcheck/plugins/anchorcheck.py +++ b/linkcheck/plugins/anchorcheck.py @@ -61,12 +61,12 @@ class UrlAnchorCheck: if any(x for x in self.anchors if x[0] == decoded_anchor): return if self.anchors: - anchornames = sorted(set("`%s'" % x[0] for x in self.anchors)) + anchornames = sorted({f"`{x[0]}'" for x in self.anchors}) anchors = ", ".join(anchornames) else: anchors = "-" args = {"name": url_data.anchor, "decoded": decoded_anchor, "anchors": anchors} - msg = "%s %s" % ( + msg = "{} {}".format( _("Anchor `%(name)s' (decoded: `%(decoded)s') not found.") % args, _("Available anchors: %(anchors)s.") % args, ) diff --git a/linkcheck/plugins/httpheaderinfo.py b/linkcheck/plugins/httpheaderinfo.py index 7e299d47..0c925274 100644 --- a/linkcheck/plugins/httpheaderinfo.py +++ b/linkcheck/plugins/httpheaderinfo.py @@ -39,7 +39,7 @@ class HttpHeaderInfo(_ConnectionPlugin): headers.append(name.lower()) if headers: items = [ - "%s=%s" % (name.capitalize(), url_data.headers[name]) + f"{name.capitalize()}={url_data.headers[name]}" for name in headers ] info = "HTTP headers %s" % ", ".join(items) diff --git a/linkcheck/plugins/locationinfo.py b/linkcheck/plugins/locationinfo.py index 502ae090..8b835bb3 100644 --- a/linkcheck/plugins/locationinfo.py +++ b/linkcheck/plugins/locationinfo.py @@ -19,7 +19,6 @@ Store and retrieve country names for IPs. from . import _ConnectionPlugin import os import sys -import socket from ..lock import get_lock from ..decorators import synchronized from .. import log, LOG_PLUGIN @@ -105,7 +104,7 @@ def get_location(host): return None try: record = get_geoip_record(host) - except (geoip_error, socket.error): + except (geoip_error, OSError): log.debug(LOG_PLUGIN, "Geoip error for %r", host, exception=True) # ignore lookup errors return None diff --git a/linkcheck/plugins/markdowncheck.py b/linkcheck/plugins/markdowncheck.py index 7c01f054..0a05415b 100644 --- a/linkcheck/plugins/markdowncheck.py +++ b/linkcheck/plugins/markdowncheck.py @@ -85,7 +85,7 @@ class MarkdownCheck(_ContentPlugin): try: self.filename_re = re.compile(pattern) except re.error as msg: - log.warn(LOG_PLUGIN, "Invalid regex pattern %r: %s" % (pattern, msg)) + log.warn(LOG_PLUGIN, _("Invalid regex pattern %r: %s"), pattern, msg) @classmethod def read_config(cls, configparser): diff --git a/linkcheck/plugins/parseword.py b/linkcheck/plugins/parseword.py index 8e865cd3..feb6e1d9 100644 --- a/linkcheck/plugins/parseword.py +++ b/linkcheck/plugins/parseword.py @@ -64,7 +64,7 @@ def has_word(): key = winreg.OpenKey(winreg.HKEY_CLASSES_ROOT, "Word.Application") winreg.CloseKey(key) return True - except (EnvironmentError, ImportError): + except (OSError, ImportError): pass return False diff --git a/linkcheck/plugins/regexcheck.py b/linkcheck/plugins/regexcheck.py index 6b0dc3d6..43ef498b 100644 --- a/linkcheck/plugins/regexcheck.py +++ b/linkcheck/plugins/regexcheck.py @@ -42,7 +42,7 @@ class RegexCheck(_ContentPlugin): try: self.warningregex = re.compile(pattern) except re.error as msg: - log.warn(LOG_PLUGIN, "Invalid regex pattern %r: %s" % (pattern, msg)) + log.warn(LOG_PLUGIN, _("Invalid regex pattern %r: %s"), pattern, msg) def applies_to(self, url_data): """Check for warningregex, extern flag and parseability.""" diff --git a/linkcheck/plugins/viruscheck.py b/linkcheck/plugins/viruscheck.py index d034f555..6adbdfef 100644 --- a/linkcheck/plugins/viruscheck.py +++ b/linkcheck/plugins/viruscheck.py @@ -94,7 +94,7 @@ class ClamdScanner: if i != -1: port = int(data[i + 5:]) break - except socket.error: + except OSError: self.sock.close() raise if port is None: @@ -103,7 +103,7 @@ class ClamdScanner: wsock = create_socket(socket.AF_INET, socket.SOCK_STREAM) try: wsock.connect(sockinfo[0][4]) - except socket.error: + except OSError: wsock.close() raise return wsock @@ -199,7 +199,7 @@ class ClamavConfig(dict): addr = self['LocalSocket'] try: sock.connect(addr) - except socket.error: + except OSError: sock.close() raise return sock @@ -211,7 +211,7 @@ class ClamavConfig(dict): sock = create_socket(socket.AF_INET, socket.SOCK_STREAM) try: sock.connect(sockinfo[0][4]) - except socket.error: + except OSError: sock.close() raise return sock @@ -225,7 +225,7 @@ def scan(data, clamconf): """ try: scanner = ClamdScanner(clamconf) - except socket.error: + except OSError: errmsg = _("Could not connect to ClamAV daemon.") return ([], [errmsg]) try: diff --git a/linkcheck/socketutil.py b/linkcheck/socketutil.py index 97eafcd2..503c86bc 100644 --- a/linkcheck/socketutil.py +++ b/linkcheck/socketutil.py @@ -25,7 +25,7 @@ if socket.has_ipv6: try: socket.socket(socket.AF_INET6, socket.SOCK_STREAM).close() has_ipv6 = True - except socket.error as msg: + except OSError as msg: # only catch these one: # socket.error: (97, 'Address family not supported by protocol') # socket.error: (10047, 'Address family not supported by protocol') diff --git a/linkcheck/strformat.py b/linkcheck/strformat.py index f16d6e3e..0783fab7 100644 --- a/linkcheck/strformat.py +++ b/linkcheck/strformat.py @@ -73,10 +73,10 @@ def unquote(s, matching=False): return s -_para_mac = r"(?:%(sep)s)(?:(?:%(sep)s)\s*)+" % {'sep': '\r'} -_para_posix = r"(?:%(sep)s)(?:(?:%(sep)s)\s*)+" % {'sep': '\n'} -_para_win = r"(?:%(sep)s)(?:(?:%(sep)s)\s*)+" % {'sep': '\r\n'} -_para_ro = re.compile("%s|%s|%s" % (_para_mac, _para_posix, _para_win)) +_para_mac = r"(?:{sep})(?:(?:{sep})\s*)+".format(sep='\r') +_para_posix = r"(?:{sep})(?:(?:{sep})\s*)+".format(sep='\n') +_para_win = r"(?:{sep})(?:(?:{sep})\s*)+".format(sep='\r\n') +_para_ro = re.compile(f"{_para_mac}|{_para_posix}|{_para_win}") def get_paragraphs(text): @@ -104,7 +104,7 @@ def wrap(text, width, **kwargs): def indent(text, indent_string=" "): """Indent each line of text with the given indent string.""" - return os.linesep.join("%s%s" % (indent_string, x) for x in text.splitlines()) + return os.linesep.join(f"{indent_string}{x}" for x in text.splitlines()) def paginate(text): @@ -191,7 +191,7 @@ def strduration_long(duration, do_translate=True): time_str.reverse() if len(time_str) > 2: time_str.pop() - return "%s%s" % (prefix, ", ".join(time_str)) + return "{}{}".format(prefix, ", ".join(time_str)) def strtimezone(): diff --git a/linkcheck/url.py b/linkcheck/url.py index e6ad1df5..0644636f 100644 --- a/linkcheck/url.py +++ b/linkcheck/url.py @@ -43,36 +43,34 @@ default_ports = { # adapted from David Wheelers "Secure Programming for Linux and Unix HOWTO" # http://www.dwheeler.com/secure-programs/Secure-Programs-HOWTO/\ # filter-html.html#VALIDATING-URIS -_basic = { - "_path": r"\-\_\.\!\~\*\'\(\),", - "_hex_safe": r"2-9a-f", - "_hex_full": r"0-9a-f", - "_part": r"([a-z0-9][-a-z0-9]{0,61}|[a-z])", -} +_path = r"\-\_\.\!\~\*\'\(\)," +_hex_safe = r"2-9a-f" +_hex_full = r"0-9a-f" +_part = r"([a-z0-9][-a-z0-9]{0,61}|[a-z])" _safe_char = ( - r"([a-z0-9%(_path)s\+]|" - r"(%%[%(_hex_safe)s][%(_hex_full)s]))" % _basic + fr"([a-z0-9{_path}\+]|" + fr"(%[{_hex_safe}][{_hex_full}]))" ) _safe_scheme_pattern = r"(https?|ftp)" -_safe_domain_pattern = r"(%(_part)s(\.%(_part)s)*\.?)" % _basic -_safe_host_pattern = _safe_domain_pattern + r"(:(80|8080|8000|443))?" % _basic +_safe_domain_pattern = fr"({_part}(\.{_part})*\.?)" +_safe_host_pattern = fr"{_safe_domain_pattern}(:(80|8080|8000|443))?" _safe_path_pattern = ( - r"((/([a-z0-9%(_path)s]|" - r"(%%[%(_hex_safe)s][%(_hex_full)s]))+)*/?)" % _basic + fr"((/([a-z0-9{_path}]|" + fr"(%[{_hex_safe}][{_hex_full}]))+)*/?)" ) -_safe_fragment_pattern = r"%s*" % _safe_char -_safe_cgi = r"%s+(=(%s|/)+)?" % (_safe_char, _safe_char) -_safe_query_pattern = r"(%s(&%s)*)?" % (_safe_cgi, _safe_cgi) -_safe_param_pattern = r"(%s(;%s)*)?" % (_safe_cgi, _safe_cgi) -safe_url_pattern = r"%s://%s%s(#%s)?" % ( +_safe_fragment_pattern = fr"{_safe_char}*" +_safe_cgi = fr"{_safe_char}+(=({_safe_char}|/)+)?" +_safe_query_pattern = fr"({_safe_cgi}(&{_safe_cgi})*)?" +_safe_param_pattern = fr"({_safe_cgi}(;{_safe_cgi})*)?" +safe_url_pattern = r"{}://{}{}(#{})?".format( _safe_scheme_pattern, _safe_host_pattern, _safe_path_pattern, _safe_fragment_pattern, ) -is_safe_url = re.compile("(?i)^%s$" % safe_url_pattern).match -is_safe_domain = re.compile("(?i)^%s$" % _safe_domain_pattern).match +is_safe_url = re.compile(f"(?i)^{safe_url_pattern}$").match +is_safe_domain = re.compile(f"(?i)^{_safe_domain_pattern}$").match # snatched form urlparse.py @@ -195,7 +193,7 @@ def url_fix_host(urlparts, encoding): if not urlparts[2] or urlparts[2] == '/': urlparts[2] = comps else: - urlparts[2] = "%s%s" % ( + urlparts[2] = "{}{}".format( comps, urllib.parse.unquote(urlparts[2], encoding=encoding), ) @@ -219,7 +217,7 @@ def url_fix_host(urlparts, encoding): if host.endswith("."): host = host[:-1] if port != dport: - host = "%s:%d" % (host, port) + host = f"{host}:{port}" netloc = host urlparts[1] = userpass + netloc return is_idn @@ -255,12 +253,12 @@ def url_parse_query(query, encoding): k = urllib.parse.quote(k, safe='/-:,;') if v: v = urllib.parse.quote(v, safe='/-:,;') - f.append("%s=%s%s" % (k, v, sep)) + f.append(f"{k}={v}{sep}") elif v is None: - f.append("%s%s" % (k, sep)) + f.append(f"{k}{sep}") else: # some sites do not work when the equal sign is missing - f.append("%s=%s" % (k, sep)) + f.append(f"{k}={sep}") return ''.join(f) + append @@ -381,9 +379,9 @@ def url_quote(url, encoding): k = urllib.parse.quote(k, safe='/-:,;') if v: v = urllib.parse.quote(v, safe='/-:,;') - f.append("%s=%s%s" % (k, v, sep)) + f.append(f"{k}={v}{sep}") else: - f.append("%s%s" % (k, sep)) + f.append(f"{k}{sep}") urlparts[3] = ''.join(f) urlparts[4] = urllib.parse.quote(urlparts[4]) # anchor return urlunsplit(urlparts) @@ -397,7 +395,7 @@ def document_quote(document): query = None doc = urllib.parse.quote(doc, safe='/=,') if query: - return "%s?%s" % (doc, query) + return f"{doc}?{query}" return doc @@ -405,7 +403,7 @@ _nopathquote_chars = "-;/=,~*+()@!" if os.name == 'nt': _nopathquote_chars += "|" _safe_url_chars = re.escape(_nopathquote_chars + "_:.&#%?[]!") + "a-zA-Z0-9" -_safe_url_chars_ro = re.compile(r"^[%s]*$" % _safe_url_chars) +_safe_url_chars_ro = re.compile(fr"^[{_safe_url_chars}]*$") def url_needs_quoting(url): diff --git a/scripts/update_iana_uri_schemes.py b/scripts/update_iana_uri_schemes.py index 261e5d0a..48b5cc12 100644 --- a/scripts/update_iana_uri_schemes.py +++ b/scripts/update_iana_uri_schemes.py @@ -87,7 +87,7 @@ def main(args): def get_regex(schemes): expr = [ - "|%s # %s" % (re.escape(scheme).ljust(10), description) + f"|{re.escape(scheme).ljust(10)} # {description}" for scheme, description in sorted(schemes.items()) ] return "\n".join(expr) diff --git a/tests/checker/__init__.py b/tests/checker/__init__.py index b5e46a39..dfbc400d 100644 --- a/tests/checker/__init__.py +++ b/tests/checker/__init__.py @@ -224,7 +224,7 @@ class LinkCheckTest(TestBase): if hasattr(self, "port"): d["port"] = self.port # all result files are encoded in utf-8 - with open(resultfile, "r", encoding="utf-8") as f: + with open(resultfile, encoding="utf-8") as f: return [ line.rstrip("\r\n") % d for line in f diff --git a/tests/checker/httpserver.py b/tests/checker/httpserver.py index 4a28d5e4..6b58dd63 100644 --- a/tests/checker/httpserver.py +++ b/tests/checker/httpserver.py @@ -132,7 +132,7 @@ class NoQueryHttpRequestHandler(StoppableHttpRequestHandler): list = ["example1.txt", "example2.html", "example3"] for name in list: displayname = linkname = name - list_item = '
  • %s\n' % ( + list_item = '
  • {}\n'.format( urllib.parse.quote(linkname), html.escape(displayname), ) @@ -247,7 +247,7 @@ def get_cookie(maxage=2000): ("Version", "1"), ("Foo", "Bar"), ) - return "; ".join('%s="%s"' % (key, value) for key, value in data) + return "; ".join(f'{key}="{value}"' for key, value in data) class CookieRedirectHttpRequestHandler(NoQueryHttpRequestHandler): diff --git a/tests/checker/telnetserver.py b/tests/checker/telnetserver.py index 15f12dc1..fa23851c 100644 --- a/tests/checker/telnetserver.py +++ b/tests/checker/telnetserver.py @@ -40,9 +40,9 @@ class TelnetServerTest(LinkCheckTest): def get_url(self, user=None, password=None): if user is not None: if password is not None: - netloc = "%s:%s@%s" % (user, password, self.host) + netloc = f"{user}:{password}@{self.host}" else: - netloc = "%s@%s" % (user, self.host) + netloc = f"{user}@{self.host}" else: netloc = self.host return "telnet://%s:%d" % (netloc, self.port) diff --git a/tests/checker/test_httpbin.py b/tests/checker/test_httpbin.py index 7b449585..e24f4a7e 100644 --- a/tests/checker/test_httpbin.py +++ b/tests/checker/test_httpbin.py @@ -54,7 +54,7 @@ class TestHttpbin(LinkCheckTest): def test_basic_auth(self): user = "testuser" password = "testpassword" - url = get_httpbin_url("/basic-auth/%s/%s" % (user, password)) + url = get_httpbin_url(f"/basic-auth/{user}/{password}") nurl = self.norm(url) entry = dict(user=user, password=password, pattern=re.compile(r".*")) confargs = dict(authentication=[entry]) diff --git a/tests/configuration/test_config.py b/tests/configuration/test_config.py index 959c7e05..4a2fbf27 100644 --- a/tests/configuration/test_config.py +++ b/tests/configuration/test_config.py @@ -64,7 +64,7 @@ class TestConfig(TestBase): patterns = [x["pattern"].pattern for x in config["externlinks"]] for prefix in ("ignore_", "nofollow_"): for suffix in ("1", "2"): - key = "%simadoofus%s" % (prefix, suffix) + key = f"{prefix}imadoofus{suffix}" self.assertTrue(key in patterns) for key in ("url-unicode-domain",): self.assertTrue(key in config["ignorewarnings"]) diff --git a/tests/htmllib.py b/tests/htmllib.py index a59d03dc..16d56c0d 100644 --- a/tests/htmllib.py +++ b/tests/htmllib.py @@ -37,9 +37,9 @@ def pretty_print_html(fd, soup): if val is None: fd.write(" %s" % key) else: - fd.write(' %s="%s"' % (key, quote_attrval(val))) + fd.write(f' {key}="{quote_attrval(val)}"') if element_text: - fd.write(">%s" % (element_text, tag)) + fd.write(f">{element_text}") else: fd.write("/>") diff --git a/tests/test_containers.py b/tests/test_containers.py index a5eb9884..8c957c2e 100644 --- a/tests/test_containers.py +++ b/tests/test_containers.py @@ -43,8 +43,8 @@ class TestLFUCache(unittest.TestCase): self.assertTrue(not self.d) self.d["a"] = 1 self.d["b"] = 2 - self.assertEqual(set([1, 2]), set(self.d.values())) - self.assertEqual(set([1, 2]), set(self.d.itervalues())) + self.assertEqual({1, 2}, set(self.d.values())) + self.assertEqual({1, 2}, set(self.d.itervalues())) def test_popitem(self): self.assertTrue(not self.d) diff --git a/tests/test_ftpparse.py b/tests/test_ftpparse.py index 7a9b617f..56ed3ba9 100644 --- a/tests/test_ftpparse.py +++ b/tests/test_ftpparse.py @@ -125,5 +125,5 @@ class TestFtpparse(unittest.TestCase): for line, expected in patterns: res = ftpparse(line) self.assertEqual( - expected, res, "got %r\nexpected %r\n%r" % (res, expected, line) + expected, res, f"got {res!r}\nexpected {expected!r}\n{line!r}" ) diff --git a/tests/test_parser.py b/tests/test_parser.py index 40bc922c..465656a8 100644 --- a/tests/test_parser.py +++ b/tests/test_parser.py @@ -165,7 +165,7 @@ class TestParser(unittest.TestCase): Check parse results. """ res = out.getvalue() - msg = "Test error; in: %r, out: %r, expect: %r" % (_in, res, _out) + msg = f"Test error; in: {_in!r}, out: {res!r}, expect: {_out!r}" self.assertEqual(res, _out, msg=msg) def test_encoding_detection_utf_content(self): diff --git a/tests/test_po.py b/tests/test_po.py index 30d5f459..e5b49103 100644 --- a/tests/test_po.py +++ b/tests/test_po.py @@ -70,5 +70,5 @@ class TestGTranslator(unittest.TestCase): continue self.assertFalse( "ยท" in line, - "Broken GTranslator copy/paste in %r:\n%s" % (f, line), + f"Broken GTranslator copy/paste in {f!r}:\n{line}", ) diff --git a/tests/test_robotparser.py b/tests/test_robotparser.py index bebf3afd..c6b452ea 100644 --- a/tests/test_robotparser.py +++ b/tests/test_robotparser.py @@ -40,7 +40,7 @@ class TestRobotParser(unittest.TestCase): else: ac = "access allowed" if a != b: - self.fail("%s != %s (%s)" % (a, b, ac)) + self.fail(f"{a} != {b} ({ac})") @need_network def test_nonexisting_robots(self):