Bump version to 3.0.1

Using the stdlib's http.cookie module, cookies are now stored as one
"Set-Cookie" header per line. Previously, the aiohttp.CookieJar's save() and
load() methods were used (which use pickling).

CHANGELOG.md

@@ -22,6 +22,19 @@ ambiguous situations.
 
 ## Unreleased
 
+## 3.0.1 - 2021-06-01
+
+### Added
+- `credential-file` authenticator
+- `--credential-file` option for `kit-ilias-web` command
+- Warning if using concurrent tasks with `kit-ilias-web`
+
+### Changed
+- Cookies are now stored in a text-based format
+
+### Fixed
+- Date parsing now also works correctly in non-group exercises
+
 ## 3.0.0 - 2021-05-31
 
 ### Added

CONFIG.md

@@ -180,6 +180,19 @@ via the terminal.
 - `username`: The username. (Optional)
 - `password`: The password. (Optional)
 
+### The `credential-file` authenticator
+
+This authenticator reads a username and a password from a credential file. The
+credential file has exactly two lines (trailing newline optional). The first
+line starts with `username=` and contains the username, the second line starts
+with `password=` and contains the password. The username and password may
+contain any characters except a line break.
+
+```
+username=AzureDiamond
+password=hunter2
+```
+
 ### The `keyring` authenticator
 
 This authenticator uses the system keyring to store passwords. The username can

PFERD/__main__.py

@@ -5,7 +5,8 @@ import os
 import sys
 from pathlib import Path
 
-from .cli import PARSER, load_default_section
+from .auth import AuthLoadError
+from .cli import PARSER, ParserLoadError, load_default_section
 from .config import Config, ConfigDumpError, ConfigLoadError, ConfigOptionError
 from .logging import log
 from .pferd import Pferd, PferdLoadError
@@ -36,6 +37,9 @@ def load_config(args: argparse.Namespace) -> Config:
         log.error(str(e))
         log.error_contd(e.reason)
         sys.exit(1)
+    except ParserLoadError as e:
+        log.error(str(e))
+        sys.exit(1)
 
 
 def configure_logging_from_args(args: argparse.Namespace) -> None:
@@ -131,7 +135,7 @@ def main() -> None:
             loop.close()
         else:
             asyncio.run(pferd.run(args.debug_transforms))
-    except ConfigOptionError as e:
+    except (ConfigOptionError, AuthLoadError) as e:
         log.unlock()
         log.error(str(e))
         sys.exit(1)

PFERD/auth/__init__.py

@@ -2,7 +2,8 @@ from configparser import SectionProxy
 from typing import Callable, Dict
 
 from ..config import Config
-from .authenticator import Authenticator, AuthError, AuthSection  # noqa: F401
+from .authenticator import Authenticator, AuthError, AuthLoadError, AuthSection  # noqa: F401
+from .credential_file import CredentialFileAuthenticator, CredentialFileAuthSection
 from .keyring import KeyringAuthenticator, KeyringAuthSection
 from .simple import SimpleAuthenticator, SimpleAuthSection
 from .tfa import TfaAuthenticator
@@ -14,10 +15,12 @@ AuthConstructor = Callable[[
 ], Authenticator]
 
 AUTHENTICATORS: Dict[str, AuthConstructor] = {
+    "credential-file": lambda n, s, c:
+        CredentialFileAuthenticator(n, CredentialFileAuthSection(s), c),
+    "keyring": lambda n, s, c:
+        KeyringAuthenticator(n, KeyringAuthSection(s)),
     "simple": lambda n, s, c:
         SimpleAuthenticator(n, SimpleAuthSection(s)),
     "tfa": lambda n, s, c:
         TfaAuthenticator(n),
-    "keyring": lambda n, s, c:
-        KeyringAuthenticator(n, KeyringAuthSection(s))
 }

PFERD/auth/authenticator.py

@@ -17,10 +17,7 @@ class AuthSection(Section):
 
 
 class Authenticator(ABC):
-    def __init__(
-            self,
-            name: str
-    ) -> None:
+    def __init__(self, name: str) -> None:
         """
         Initialize an authenticator from its name and its section in the config
         file.

PFERD/auth/credential_file.py

@@ -0,0 +1,44 @@
+from pathlib import Path
+from typing import Tuple
+
+from ..config import Config
+from ..utils import fmt_real_path
+from .authenticator import Authenticator, AuthLoadError, AuthSection
+
+
+class CredentialFileAuthSection(AuthSection):
+    def path(self) -> Path:
+        value = self.s.get("path")
+        if value is None:
+            self.missing_value("path")
+        return Path(value)
+
+
+class CredentialFileAuthenticator(Authenticator):
+    def __init__(self, name: str, section: CredentialFileAuthSection, config: Config) -> None:
+        super().__init__(name)
+
+        path = config.default_section.working_dir() / section.path()
+        try:
+            with open(path) as f:
+                lines = list(f)
+        except OSError as e:
+            raise AuthLoadError(f"No credential file at {fmt_real_path(path)}") from e
+
+        if len(lines) != 2:
+            raise AuthLoadError("Credential file must be two lines long")
+        [uline, pline] = lines
+        uline = uline[:-1]  # Remove trailing newline
+        if pline.endswith("\n"):
+            pline = pline[:-1]
+
+        if not uline.startswith("username="):
+            raise AuthLoadError("First line must start with 'username='")
+        if not pline.startswith("password="):
+            raise AuthLoadError("Second line must start with 'password='")
+
+        self._username = uline[9:]
+        self._password = pline[9:]
+
+    async def credentials(self) -> Tuple[str, str]:
+        return self._username, self._password

PFERD/auth/keyring.py

@@ -18,11 +18,7 @@ class KeyringAuthSection(AuthSection):
 
 class KeyringAuthenticator(Authenticator):
 
-    def __init__(
-            self,
-            name: str,
-            section: KeyringAuthSection,
-    ) -> None:
+    def __init__(self, name: str, section: KeyringAuthSection) -> None:
         super().__init__(name)
 
         self._username = section.username()

PFERD/auth/simple.py

@@ -14,11 +14,7 @@ class SimpleAuthSection(AuthSection):
 
 
 class SimpleAuthenticator(Authenticator):
-    def __init__(
-            self,
-            name: str,
-            section: SimpleAuthSection,
-    ) -> None:
+    def __init__(self, name: str, section: SimpleAuthSection) -> None:
         super().__init__(name)
 
         self._username = section.username()

PFERD/auth/tfa.py

@@ -6,10 +6,7 @@ from .authenticator import Authenticator, AuthError
 
 
 class TfaAuthenticator(Authenticator):
-    def __init__(
-            self,
-            name: str,
-    ) -> None:
+    def __init__(self, name: str) -> None:
         super().__init__(name)
 
     async def username(self) -> str:

PFERD/cli/__init__.py

@@ -1,11 +1,12 @@
 # isort: skip_file
 
 # The order of imports matters because each command module registers itself
-# with the parser from ".parser". Because of this, isort is disabled for this
+# with the parser from ".parser" and the import order affects the order in
+# which they appear in the help. Because of this, isort is disabled for this
 # file. Also, since we're reexporting or just using the side effect of
 # importing itself, we get a few linting warnings, which we're disabling as
 # well.
 
 from . import command_local  # noqa: F401 imported but unused
 from . import command_kit_ilias_web  # noqa: F401 imported but unused
-from .parser import PARSER, load_default_section  # noqa: F401 imported but unused
+from .parser import PARSER, ParserLoadError, load_default_section  # noqa: F401 imported but unused

PFERD/cli/command_kit_ilias_web.py

@@ -4,7 +4,8 @@ from pathlib import Path
 
 from ..crawl.ilias.file_templates import Links
 from ..logging import log
-from .parser import CRAWLER_PARSER, SUBPARSERS, BooleanOptionalAction, load_crawler, show_value_error
+from .parser import (CRAWLER_PARSER, SUBPARSERS, BooleanOptionalAction, ParserLoadError, load_crawler,
+                     show_value_error)
 
 SUBPARSER = SUBPARSERS.add_parser(
     "kit-ilias-web",
@@ -38,6 +39,12 @@ GROUP.add_argument(
     action=BooleanOptionalAction,
     help="use the system keyring to store and retrieve passwords"
 )
+GROUP.add_argument(
+    "--credential-file",
+    type=Path,
+    metavar="PATH",
+    help="read username and password from a credential file"
+)
 GROUP.add_argument(
     "--links",
     type=show_value_error(Links.from_string),
@@ -88,11 +95,19 @@ def load(
 
     parser["auth:ilias"] = {}
     auth_section = parser["auth:ilias"]
+    if args.credential_file is not None:
+        if args.username is not None:
+            raise ParserLoadError("--credential-file and --username can't be used together")
+        if args.keyring:
+            raise ParserLoadError("--credential-file and --keyring can't be used together")
+        auth_section["type"] = "credential-file"
+        auth_section["path"] = str(args.credential_file)
+    elif args.keyring:
+        auth_section["type"] = "keyring"
+    else:
         auth_section["type"] = "simple"
     if args.username is not None:
         auth_section["username"] = args.username
-    if args.keyring:
-        auth_section["type"] = "keyring"
 
 
 SUBPARSER.set_defaults(command=load)

PFERD/cli/parser.py

@@ -8,6 +8,10 @@ from ..output_dir import OnConflict, Redownload
 from ..version import NAME, VERSION
 
 
+class ParserLoadError(Exception):
+    pass
+
+
 # TODO Replace with argparse version when updating to 3.9?
 class BooleanOptionalAction(argparse.Action):
     def __init__(

PFERD/config.py

@@ -69,6 +69,7 @@ class Section:
 
 class DefaultSection(Section):
     def working_dir(self) -> Path:
+        # TODO Change to working dir instead of manually prepending it to paths
         pathstr = self.s.get("working_dir", ".")
         return Path(pathstr).expanduser()
 

PFERD/crawl/http_crawler.py

@@ -1,7 +1,8 @@
 import asyncio
+import http.cookies
 import ssl
 from pathlib import Path, PurePath
-from typing import Dict, List, Optional
+from typing import Any, Dict, List, Optional
 
 import aiohttp
 import certifi
@@ -105,6 +106,25 @@ class HttpCrawler(Crawler):
 
         self._shared_cookie_jar_paths.append(self._cookie_jar_path)
 
+    def _load_cookies_from_file(self, path: Path) -> None:
+        jar: Any = http.cookies.SimpleCookie()
+        with open(path) as f:
+            for i, line in enumerate(f):
+                # Names of headers are case insensitive
+                if line[:11].lower() == "set-cookie:":
+                    jar.load(line[11:])
+                else:
+                    log.explain(f"Line {i} doesn't start with 'Set-Cookie:', ignoring it")
+        self._cookie_jar.update_cookies(jar)
+
+    def _save_cookies_to_file(self, path: Path) -> None:
+        jar: Any = http.cookies.SimpleCookie()
+        for morsel in self._cookie_jar:
+            jar[morsel.key] = morsel
+        with open(path, "w") as f:
+            f.write(jar.output(sep="\n"))
+            f.write("\n")  # A trailing newline is just common courtesy
+
     def _load_cookies(self) -> None:
         log.explain_topic("Loading cookies")
 
@@ -134,7 +154,7 @@ class HttpCrawler(Crawler):
 
         log.explain(f"Loading cookies from {fmt_real_path(cookie_jar_path)}")
         try:
-            self._cookie_jar.load(cookie_jar_path)
+            self._load_cookies_from_file(cookie_jar_path)
         except Exception as e:
             log.explain("Failed to load cookies")
             log.explain(str(e))
@@ -144,7 +164,7 @@ class HttpCrawler(Crawler):
 
         try:
             log.explain(f"Saving cookies to {fmt_real_path(self._cookie_jar_path)}")
-            self._cookie_jar.save(self._cookie_jar_path)
+            self._save_cookies_to_file(self._cookie_jar_path)
         except Exception as e:
             log.warn(f"Failed to save cookies to {fmt_real_path(self._cookie_jar_path)}")
             log.warn(str(e))

PFERD/crawl/ilias/kit_ilias_html.py

@@ -230,12 +230,16 @@ class IliasPage:
             parent_row: Tag = link.findParent("tr")
             children: List[Tag] = parent_row.findChildren("td")
 
-            # <checkbox> <name> <uploader> <date> <download>
-            #     0         1        2       3        4
             name = _sanitize_path_name(children[1].getText().strip())
-            date = demangle_date(children[3].getText().strip())
-
             log.explain(f"Found exercise detail entry {name!r}")
+
+            for child in reversed(children):
+                date = demangle_date(child.getText().strip(), fail_silently=True)
+                if date is not None:
+                    break
+            if date is None:
+                log.warn(f"Date parsing failed for exercise entry {name!r}")
+
             results.append(IliasPageElement(
                 IliasElementType.FILE,
                 self._abs_url_from_link(link),
@@ -522,7 +526,7 @@ german_months = ['Jan', 'Feb', 'Mär', 'Apr', 'Mai', 'Jun', 'Jul', 'Aug', 'Sep',
 english_months = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']
 
 
-def demangle_date(date_str: str) -> Optional[datetime]:
+def demangle_date(date_str: str, fail_silently: bool = False) -> Optional[datetime]:
     """
     Demangle a given date in one of the following formats:
     "Gestern, HH:MM"
@@ -554,6 +558,7 @@ def demangle_date(date_str: str) -> Optional[datetime]:
 
         return datetime(year, month, day, hour, minute)
     except Exception:
+        if not fail_silently:
             log.warn(f"Date parsing failed for {date_str!r}")
         return None
 

PFERD/crawl/ilias/kit_ilias_web_crawler.py

@@ -21,7 +21,6 @@ TargetType = Union[str, int]
 
 
 class KitIliasWebCrawlerSection(HttpCrawlerSection):
-
     def target(self) -> TargetType:
         target = self.s.get("target")
         if not target:
@@ -164,6 +163,12 @@ class KitIliasWebCrawler(HttpCrawler):
         auth = section.auth(authenticators)
         super().__init__(name, section, config, shared_auth=auth)
 
+        if section.tasks() > 1:
+            log.warn("""
+Please avoid using too many parallel requests as these are the KIT ILIAS
+instance's greatest bottleneck.
+            """.strip())
+
         self._shibboleth_login = KitShibbolethLogin(
             auth,
             section.tfa_auth(authenticators),

PFERD/version.py

@@ -1,2 +1,2 @@
 NAME = "PFERD"
-VERSION = "3.0.0"
+VERSION = "3.0.1"