Bump version to 3.6.0

Related to issue #93

.github/dependabot.yml

@@ -0,0 +1,10 @@
+version: 2
+updates:
+  - package-ecosystem: github-actions
+    directory: /
+    schedule:
+      interval: monthly
+    groups:
+      gh-actions:
+        patterns:
+          - "*"

.github/workflows/build-and-release.yml

@@ -1,6 +1,6 @@
 name: build-and-release
 
-on: push
+on: [push, pull_request]
 
 defaults:
   run:
@@ -13,13 +13,12 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-latest, windows-latest, macos-latest]
+        os: [ubuntu-latest, windows-latest, macos-13, macos-latest]
         python: ["3.9"]
     steps:
+      - uses: actions/checkout@v4
 
-      - uses: actions/checkout@v3
-
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python }}
 
@@ -34,7 +33,12 @@ jobs:
         run: ./scripts/setup --no-pip
 
       - name: Run checks
-        run: ./scripts/check
+        run: |
+          ./scripts/check
+          ./scripts/format
+
+      - name: Assert no changes
+        run: git diff --exit-code
 
       - name: Build
         run: ./scripts/build
@@ -45,9 +49,9 @@ jobs:
         run: mv dist/pferd* dist/pferd-${{ matrix.os }}
 
       - name: Upload binary
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
-          name: Binaries
+          name: pferd-${{ matrix.os }}
           path: dist/pferd-${{ matrix.os }}
 
   release:
@@ -57,18 +61,20 @@ jobs:
     steps:
 
       - name: Download binaries
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
         with:
-          name: Binaries
+          pattern: pferd-*
+          merge-multiple: true
 
       - name: Rename binaries
         run: |
           mv pferd-ubuntu-latest pferd-linux
           mv pferd-windows-latest pferd-windows.exe
+          mv pferd-macos-13 pferd-mac-x86_64
           mv pferd-macos-latest pferd-mac
 
       - name: Create release
-        uses: softprops/action-gh-release@v1
+        uses: softprops/action-gh-release@v2
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:
@@ -76,3 +82,4 @@ jobs:
             pferd-linux
             pferd-windows.exe
             pferd-mac
+            pferd-mac-x86_64

CHANGELOG.md

@@ -22,6 +22,19 @@ ambiguous situations.
 
 ## Unreleased
 
+## 3.6.0 - 2024-10-23
+
+### Added
+- Generic `ilias-web` crawler and `ilias-web` CLI command
+- Support for the course overview page. Using this URL as a target might cause
+  duplication warnings, as subgroups are listed separately.
+- Support for named capture groups in regex transforms
+- Crawl custom item groups as folders
+
+### Fixed
+- Normalization of meeting names in cards
+- Sanitization of slashes in exercise container names
+
 ## 3.5.2 - 2024-04-14
 
 ### Fixed

CONFIG.md

@@ -4,11 +4,11 @@ A config file consists of sections. A section begins with a `[section]` header,
 which is followed by a list of `key = value` pairs. Comments must be on their
 own line and start with `#`. Multiline values must be indented beyond their key.
 Boolean values can be `yes` or `no`. For more details and some examples on the
-format, see the [configparser documentation][1] ([interpolation][2] is
-disabled).
+format, see the [configparser documentation][cp-file]
+([interpolation][cp-interp] is disabled).
 
-[1]: <https://docs.python.org/3/library/configparser.html#supported-ini-file-structure> "Supported INI File Structure"
-[2]: <https://docs.python.org/3/library/configparser.html#interpolation-of-values> "Interpolation of values"
+[cp-file]: <https://docs.python.org/3/library/configparser.html#supported-ini-file-structure> "Supported INI File Structure"
+[cp-interp]: <https://docs.python.org/3/library/configparser.html#interpolation-of-values> "Interpolation of values"
 
 ## The `DEFAULT` section
 
@@ -146,7 +146,7 @@ crawler simulate a slower, network-based crawler.
 
 This crawler crawls a KIT-IPD page by url. The root page can be crawled from
 outside the KIT network so you will be informed about any new/deleted files,
-but downloading files requires you to be within. Adding a show delay between
+but downloading files requires you to be within. Adding a short delay between
 requests is likely a good idea.
 
 - `target`: URL to a KIT-IPD page
@@ -154,6 +154,56 @@ requests is likely a good idea.
   matches, the given link is downloaded as a file. This is used to extract
   files from KIT-IPD pages. (Default: `^.*?[^/]+\.(pdf|zip|c|cpp|java)$`)
 
+### The `ilias-web` crawler
+
+This crawler crawls a generic ILIAS instance.
+
+Inspired by [this ILIAS downloader][ilias-dl], the following configurations should work
+out of the box for the corresponding universities:
+
+[ilias-dl]: https://github.com/V3lop5/ilias-downloader/blob/main/configs "ilias-downloader configs"
+
+| University    | `base_url`                           | `client_id`   |
+|---------------|--------------------------------------|---------------|
+| FH Aachen     | https://www.ili.fh-aachen.de         | elearning     |
+| Uni Köln      | https://www.ilias.uni-koeln.de/ilias | uk            |
+| Uni Konstanz  | https://ilias.uni-konstanz.de        | ILIASKONSTANZ |
+| Uni Stuttgart | https://ilias3.uni-stuttgart.de      | Uni_Stuttgart |
+
+If your university isn't listed, try navigating to your instance's login page.
+Assuming no custom login service is used, the URL will look something like this:
+
+```jinja
+{{ base_url }}/login.php?client_id={{ client_id }}&cmd=force_login&lang=
+```
+
+If the values work, feel free to submit a PR and add them to the table above.
+
+- `base_url`: The URL where the ILIAS instance is located. (Required)
+- `client_id`: An ID used for authentication. (Required)
+- `target`: The ILIAS element to crawl. (Required)
+    - `desktop`: Crawl your personal desktop / dashboard
+    - `<course id>`: Crawl the course with the given id
+    - `<url>`: Crawl a given element by URL (preferably the permanent URL linked
+      at the bottom of its ILIAS page).  
+      This also supports the "My Courses" overview page to download *all*
+      courses. Note that this might produce confusing local directory layouts
+      and duplication warnings if you are a member of an ILIAS group. The
+      `desktop` target is generally preferable.
+- `auth`: Name of auth section to use for login. (Required)
+- `links`: How to represent external links. (Default: `fancy`)
+    - `ignore`: Don't download links.
+    - `plaintext`: A text file containing only the URL.
+    - `fancy`: A HTML file looking like the ILIAS link element.
+    - `internet-shortcut`: An internet shortcut file (`.url` file).
+- `link_redirect_delay`: Time (in seconds) until `fancy` link files will
+  redirect to the actual URL. Set to a negative value to disable the automatic
+  redirect. (Default: `-1`)
+- `videos`: Whether to download videos. (Default: `no`)
+- `forums`: Whether to download forum threads. (Default: `no`)
+- `http_timeout`: The timeout (in seconds) for all HTTP requests. (Default:
+  `20.0`)
+
 ### The `kit-ilias-web` crawler
 
 This crawler crawls the KIT ILIAS instance.
@@ -232,10 +282,10 @@ is stored in the keyring.
 
 ### The `pass` authenticator
 
-This authenticator queries the [`pass` password manager][3] for a username and
-password. It tries to be mostly compatible with [browserpass][4] and
-[passff][5], so see those links for an overview of the format. If PFERD fails
-to load your password, you can use the `--explain` flag to see why.
+This authenticator queries the [`pass` password manager][pass] for a username
+and password. It tries to be mostly compatible with [browserpass][browserpass]
+and [passff][passff], so see those links for an overview of the format. If PFERD
+fails to load your password, you can use the `--explain` flag to see why.
 
 - `passname`: The name of the password to use (Required)
 - `username_prefixes`: A comma-separated list of username line prefixes
@@ -243,9 +293,9 @@ to load your password, you can use the `--explain` flag to see why.
 - `password_prefixes`: A comma-separated list of password line prefixes
   (Default: `password,pass,secret`)
 
-[3]: <https://www.passwordstore.org/> "Pass: The Standard Unix Password Manager"
-[4]: <https://github.com/browserpass/browserpass-extension#organizing-password-store> "Organizing password store"
-[5]: <https://github.com/passff/passff#multi-line-format> "Multi-line format"
+[pass]: <https://www.passwordstore.org/> "Pass: The Standard Unix Password Manager"
+[browserpass]: <https://github.com/browserpass/browserpass-extension#organizing-password-store> "Organizing password store"
+[passff]: <https://github.com/passff/passff#multi-line-format> "Multi-line format"
 
 ### The `tfa` authenticator
 
@@ -344,7 +394,8 @@ matches `SOURCE`, the output path is created using `TARGET` as template.
 be referred to as `{g<n>}` (e.g. `{g3}`). `{g0}` refers to the original path.
 If capturing group *n*'s contents are a valid integer, the integer value is
 available as `{i<n>}` (e.g. `{i3}`). If capturing group *n*'s contents are a
-valid float, the float value is available as `{f<n>}` (e.g. `{f3}`). If a
+valid float, the float value is available as `{f<n>}` (e.g. `{f3}`). Named capture
+groups (e.g. `(?P<name>)`) are available by their name (e.g. `{name}`). If a
 capturing group is not present (e.g. when matching the string `cd` with the
 regex `(ab)?cd`), the corresponding variables are not defined.
 

LICENSE

@@ -1,6 +1,6 @@
-Copyright 2019-2021 Garmelon, I-Al-Istannen, danstooamerican, pavelzw,
+Copyright 2019-2024 Garmelon, I-Al-Istannen, danstooamerican, pavelzw,
                     TheChristophe, Scriptim, thelukasprobst, Toorero,
-                    Mr-Pine
+                    Mr-Pine, p-fruck
 
 Permission is hereby granted, free of charge, to any person obtaining a copy of
 this software and associated documentation files (the "Software"), to deal in

PFERD/cli/__init__.py

@@ -8,6 +8,7 @@
 # well.
 
 from . import command_local  # noqa: F401 imported but unused
+from . import command_ilias_web  # noqa: F401 imported but unused
 from . import command_kit_ilias_web  # noqa: F401 imported but unused
 from . import command_kit_ipd  # noqa: F401 imported but unused
 from .parser import PARSER, ParserLoadError, load_default_section  # noqa: F401 imported but unused

PFERD/cli/command_ilias_web.py

@@ -0,0 +1,56 @@
+import argparse
+import configparser
+
+from ..logging import log
+from .common_ilias_args import configure_common_group_args, load_common
+from .parser import CRAWLER_PARSER, SUBPARSERS, load_crawler
+
+COMMAND_NAME = "ilias-web"
+
+SUBPARSER = SUBPARSERS.add_parser(
+    COMMAND_NAME,
+    parents=[CRAWLER_PARSER],
+)
+
+GROUP = SUBPARSER.add_argument_group(
+    title=f"{COMMAND_NAME} crawler arguments",
+    description=f"arguments for the '{COMMAND_NAME}' crawler",
+)
+
+GROUP.add_argument(
+    "--base-url",
+    type=str,
+    metavar="BASE_URL",
+    help="The base url of the ilias instance"
+)
+
+GROUP.add_argument(
+    "--client-id",
+    type=str,
+    metavar="CLIENT_ID",
+    help="The client id of the ilias instance"
+)
+
+configure_common_group_args(GROUP)
+
+
+def load(
+        args: argparse.Namespace,
+        parser: configparser.ConfigParser,
+) -> None:
+    log.explain(f"Creating config for command '{COMMAND_NAME}'")
+
+    parser["crawl:ilias"] = {}
+    section = parser["crawl:ilias"]
+    load_crawler(args, section)
+
+    section["type"] = COMMAND_NAME
+    if args.ilias_url is not None:
+        section["base_url"] = args.ilias_url
+    if args.client_id is not None:
+        section["client_id"] = args.client_id
+
+    load_common(section, args, parser)
+
+
+SUBPARSER.set_defaults(command=load)

PFERD/cli/command_kit_ilias_web.py

@@ -1,120 +1,37 @@
 import argparse
 import configparser
-from pathlib import Path
 
-from ..crawl.ilias.file_templates import Links
 from ..logging import log
-from .parser import (CRAWLER_PARSER, SUBPARSERS, BooleanOptionalAction, ParserLoadError, load_crawler,
-                     show_value_error)
+from .common_ilias_args import configure_common_group_args, load_common
+from .parser import CRAWLER_PARSER, SUBPARSERS, load_crawler
+
+COMMAND_NAME = "kit-ilias-web"
 
 SUBPARSER = SUBPARSERS.add_parser(
-    "kit-ilias-web",
+    COMMAND_NAME,
     parents=[CRAWLER_PARSER],
 )
 
 GROUP = SUBPARSER.add_argument_group(
-    title="kit-ilias-web crawler arguments",
-    description="arguments for the 'kit-ilias-web' crawler",
-)
-GROUP.add_argument(
-    "target",
-    type=str,
-    metavar="TARGET",
-    help="course id, 'desktop', or ILIAS URL to crawl"
-)
-GROUP.add_argument(
-    "output",
-    type=Path,
-    metavar="OUTPUT",
-    help="output directory"
-)
-GROUP.add_argument(
-    "--username", "-u",
-    type=str,
-    metavar="USERNAME",
-    help="user name for authentication"
-)
-GROUP.add_argument(
-    "--keyring",
-    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),
-    metavar="OPTION",
-    help="how to represent external links"
-)
-GROUP.add_argument(
-    "--link-redirect-delay",
-    type=int,
-    metavar="SECONDS",
-    help="time before 'fancy' links redirect to to their target (-1 to disable)"
-)
-GROUP.add_argument(
-    "--videos",
-    action=BooleanOptionalAction,
-    help="crawl and download videos"
-)
-GROUP.add_argument(
-    "--forums",
-    action=BooleanOptionalAction,
-    help="crawl and download forum posts"
-)
-GROUP.add_argument(
-    "--http-timeout", "-t",
-    type=float,
-    metavar="SECONDS",
-    help="timeout for all HTTP requests"
+    title=f"{COMMAND_NAME} crawler arguments",
+    description=f"arguments for the '{COMMAND_NAME}' crawler",
 )
 
+configure_common_group_args(GROUP)
+
 
 def load(
         args: argparse.Namespace,
         parser: configparser.ConfigParser,
 ) -> None:
-    log.explain("Creating config for command 'kit-ilias-web'")
+    log.explain(f"Creating config for command '{COMMAND_NAME}'")
 
     parser["crawl:ilias"] = {}
     section = parser["crawl:ilias"]
     load_crawler(args, section)
 
-    section["type"] = "kit-ilias-web"
-    section["target"] = str(args.target)
-    section["output_dir"] = str(args.output)
-    section["auth"] = "auth:ilias"
-    if args.links is not None:
-        section["links"] = str(args.links.value)
-    if args.link_redirect_delay is not None:
-        section["link_redirect_delay"] = str(args.link_redirect_delay)
-    if args.videos is not None:
-        section["videos"] = "yes" if args.videos else "no"
-    if args.forums is not None:
-        section["forums"] = "yes" if args.forums else "no"
-    if args.http_timeout is not None:
-        section["http_timeout"] = str(args.http_timeout)
-
-    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
+    section["type"] = COMMAND_NAME
+    load_common(section, args, parser)
 
 
 SUBPARSER.set_defaults(command=load)

PFERD/cli/common_ilias_args.py

@@ -0,0 +1,104 @@
+import argparse
+import configparser
+from pathlib import Path
+
+from ..crawl.ilias.file_templates import Links
+from .parser import BooleanOptionalAction, ParserLoadError, show_value_error
+
+
+def configure_common_group_args(group: argparse._ArgumentGroup) -> None:
+    """These arguments are shared between the KIT and generic Ilias web command."""
+    group.add_argument(
+        "target",
+        type=str,
+        metavar="TARGET",
+        help="course id, 'desktop', or ILIAS URL to crawl"
+    )
+    group.add_argument(
+        "output",
+        type=Path,
+        metavar="OUTPUT",
+        help="output directory"
+    )
+    group.add_argument(
+        "--username", "-u",
+        type=str,
+        metavar="USERNAME",
+        help="user name for authentication"
+    )
+    group.add_argument(
+        "--keyring",
+        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),
+        metavar="OPTION",
+        help="how to represent external links"
+    )
+    group.add_argument(
+        "--link-redirect-delay",
+        type=int,
+        metavar="SECONDS",
+        help="time before 'fancy' links redirect to to their target (-1 to disable)"
+    )
+    group.add_argument(
+        "--videos",
+        action=BooleanOptionalAction,
+        help="crawl and download videos"
+    )
+    group.add_argument(
+        "--forums",
+        action=BooleanOptionalAction,
+        help="crawl and download forum posts"
+    )
+    group.add_argument(
+        "--http-timeout", "-t",
+        type=float,
+        metavar="SECONDS",
+        help="timeout for all HTTP requests"
+    )
+
+
+def load_common(
+    section: configparser.SectionProxy,
+    args: argparse.Namespace,
+    parser: configparser.ConfigParser,
+) -> None:
+    """Load common config between generic and KIT ilias web command"""
+    section["target"] = str(args.target)
+    section["output_dir"] = str(args.output)
+    section["auth"] = "auth:ilias"
+    if args.links is not None:
+        section["links"] = str(args.links.value)
+    if args.link_redirect_delay is not None:
+        section["link_redirect_delay"] = str(args.link_redirect_delay)
+    if args.videos is not None:
+        section["videos"] = "yes" if args.videos else "no"
+    if args.forums is not None:
+        section["forums"] = "yes" if args.forums else "no"
+    if args.http_timeout is not None:
+        section["http_timeout"] = str(args.http_timeout)
+
+    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

PFERD/crawl/__init__.py

@@ -4,7 +4,7 @@ from typing import Callable, Dict
 from ..auth import Authenticator
 from ..config import Config
 from .crawler import Crawler, CrawlError, CrawlerSection  # noqa: F401
-from .ilias import KitIliasWebCrawler, KitIliasWebCrawlerSection
+from .ilias import IliasWebCrawler, IliasWebCrawlerSection, KitIliasWebCrawler, KitIliasWebCrawlerSection
 from .kit_ipd_crawler import KitIpdCrawler, KitIpdCrawlerSection
 from .local_crawler import LocalCrawler, LocalCrawlerSection
 
@@ -18,6 +18,8 @@ CrawlerConstructor = Callable[[
 CRAWLERS: Dict[str, CrawlerConstructor] = {
     "local": lambda n, s, c, a:
         LocalCrawler(n, LocalCrawlerSection(s), c),
+    "ilias-web": lambda n, s, c, a:
+        IliasWebCrawler(n, IliasWebCrawlerSection(s), c, a),
     "kit-ilias-web": lambda n, s, c, a:
         KitIliasWebCrawler(n, KitIliasWebCrawlerSection(s), c, a),
     "kit-ipd": lambda n, s, c, a:

PFERD/crawl/ilias/__init__.py

@@ -1,3 +1,9 @@
-from .kit_ilias_web_crawler import KitIliasWebCrawler, KitIliasWebCrawlerSection
+from .kit_ilias_web_crawler import (IliasWebCrawler, IliasWebCrawlerSection, KitIliasWebCrawler,
+                                    KitIliasWebCrawlerSection)
 
-__all__ = ["KitIliasWebCrawler", "KitIliasWebCrawlerSection"]
+__all__ = [
+    "IliasWebCrawler",
+    "IliasWebCrawlerSection",
+    "KitIliasWebCrawler",
+    "KitIliasWebCrawlerSection",
+]

PFERD/crawl/ilias/async_helper.py

@@ -0,0 +1,39 @@
+import asyncio
+from typing import Any, Callable, Optional
+
+import aiohttp
+
+from ...logging import log
+from ..crawler import AWrapped, CrawlError, CrawlWarning
+
+
+def _iorepeat(attempts: int, name: str, failure_is_error: bool = False) -> Callable[[AWrapped], AWrapped]:
+    def decorator(f: AWrapped) -> AWrapped:
+        async def wrapper(*args: Any, **kwargs: Any) -> Optional[Any]:
+            last_exception: Optional[BaseException] = None
+            for round in range(attempts):
+                try:
+                    return await f(*args, **kwargs)
+                except aiohttp.ContentTypeError:  # invalid content type
+                    raise CrawlWarning("ILIAS returned an invalid content type")
+                except aiohttp.TooManyRedirects:
+                    raise CrawlWarning("Got stuck in a redirect loop")
+                except aiohttp.ClientPayloadError as e:  # encoding or not enough bytes
+                    last_exception = e
+                except aiohttp.ClientConnectionError as e:  # e.g. timeout, disconnect, resolve failed, etc.
+                    last_exception = e
+                except asyncio.exceptions.TimeoutError as e:  # explicit http timeouts in HttpCrawler
+                    last_exception = e
+                log.explain_topic(f"Retrying operation {name}. Retries left: {attempts - 1 - round}")
+
+            if last_exception:
+                message = f"Error in I/O Operation: {last_exception}"
+                if failure_is_error:
+                    raise CrawlError(message) from last_exception
+                else:
+                    raise CrawlWarning(message) from last_exception
+            raise CrawlError("Impossible return in ilias _iorepeat")
+
+        return wrapper  # type: ignore
+
+    return decorator

PFERD/crawl/ilias/kit_ilias_html.py

@@ -48,6 +48,10 @@ class IliasPageElement:
         regexes = [
             r"eid=(?P<id>[0-9a-z\-]+)",
             r"file_(?P<id>\d+)",
+            r"copa_(?P<id>\d+)",
+            r"fold_(?P<id>\d+)",
+            r"frm_(?P<id>\d+)",
+            r"exc_(?P<id>\d+)",
             r"ref_id=(?P<id>\d+)",
             r"target=[a-z]+_(?P<id>\d+)",
             r"mm_(?P<id>\d+)"
@@ -61,6 +65,52 @@ class IliasPageElement:
         log.warn(f"Didn't find identity for {self.name} - {self.url}. Please report this.")
         return self.url
 
+    @staticmethod
+    def create_new(
+        typ: IliasElementType,
+        url: str,
+        name: str,
+        mtime: Optional[datetime] = None,
+        description: Optional[str] = None,
+        skip_sanitize: bool = False
+    ) -> 'IliasPageElement':
+        if typ == IliasElementType.MEETING:
+            normalized = IliasPageElement._normalize_meeting_name(name)
+            log.explain(f"Normalized meeting name from {name!r} to {normalized!r}")
+            name = normalized
+
+        if not skip_sanitize:
+            name = _sanitize_path_name(name)
+
+        return IliasPageElement(typ, url, name, mtime, description)
+
+    @staticmethod
+    def _normalize_meeting_name(meeting_name: str) -> str:
+        """
+        Normalizes meeting names, which have a relative time as their first part,
+        to their date in ISO format.
+        """
+
+        # This checks whether we can reach a `:` without passing a `-`
+        if re.search(r"^[^-]+: ", meeting_name):
+            # Meeting name only contains date: "05. Jan 2000:"
+            split_delimiter = ":"
+        else:
+            # Meeting name contains date and start/end times: "05. Jan 2000, 16:00 - 17:30:"
+            split_delimiter = ", "
+
+        # We have a meeting day without time
+        date_portion_str = meeting_name.split(split_delimiter)[0]
+        date_portion = demangle_date(date_portion_str)
+
+        # We failed to parse the date, bail out
+        if not date_portion:
+            return meeting_name
+
+        # Replace the first section with the absolute date
+        rest_of_name = split_delimiter.join(meeting_name.split(split_delimiter)[1:])
+        return datetime.strftime(date_portion, "%Y-%m-%d") + split_delimiter + rest_of_name
+
 
 @dataclass
 class IliasDownloadForumData:
@@ -130,7 +180,7 @@ class IliasPage:
             attrs={"href": lambda x: x and "cmdClass=ilinfoscreengui" in x}
         )
         if tab is not None:
-            return IliasPageElement(
+            return IliasPageElement.create_new(
                 IliasElementType.INFO_TAB,
                 self._abs_url_from_link(tab),
                 "infos"
@@ -295,7 +345,7 @@ class IliasPage:
         if not element:
             return None
         link = self._abs_url_from_link(element)
-        return IliasPageElement(IliasElementType.FOLDER, link, "show all meetings")
+        return IliasPageElement.create_new(IliasElementType.FOLDER, link, "show all meetings")
 
     def _is_content_tab_selected(self) -> bool:
         return self._select_content_page_url() is None
@@ -304,6 +354,9 @@ class IliasPage:
         might_be_info = self._soup.find("form", attrs={"name": lambda x: x == "formInfoScreen"}) is not None
         return self._page_type == IliasElementType.INFO_TAB and might_be_info
 
+    def _is_course_overview_page(self) -> bool:
+        return "baseClass=ilmembershipoverviewgui" in self._page_url
+
     def _select_content_page_url(self) -> Optional[IliasPageElement]:
         tab = self._soup.find(
             id="tab_view_content",
@@ -315,7 +368,7 @@ class IliasPage:
         link = tab.find("a")
         if link:
             link = self._abs_url_from_link(link)
-            return IliasPageElement(IliasElementType.FOLDER, link, "select content page")
+            return IliasPageElement.create_new(IliasElementType.FOLDER, link, "select content page")
 
         _unexpected_html_warning()
         log.warn_contd(f"Could not find content tab URL on {self._page_url!r}.")
@@ -345,14 +398,16 @@ class IliasPage:
         # and just fetch the lone video url!
         if len(streams) == 1:
             video_url = streams[0]["sources"]["mp4"][0]["src"]
-            return [IliasPageElement(IliasElementType.OPENCAST_VIDEO, video_url, self._source_name)]
+            return [
+                IliasPageElement.create_new(IliasElementType.OPENCAST_VIDEO, video_url, self._source_name)
+            ]
 
         log.explain(f"Found multiple videos for stream at {self._source_name}")
         items = []
         for stream in sorted(streams, key=lambda stream: stream["content"]):
             full_name = f"{self._source_name.replace('.mp4', '')} ({stream['content']}).mp4"
             video_url = stream["sources"]["mp4"][0]["src"]
-            items.append(IliasPageElement(IliasElementType.OPENCAST_VIDEO, video_url, full_name))
+            items.append(IliasPageElement.create_new(IliasElementType.OPENCAST_VIDEO, video_url, full_name))
 
         return items
 
@@ -367,7 +422,7 @@ class IliasPage:
 
         link = self._abs_url_from_link(correct_link)
 
-        return IliasPageElement(IliasElementType.FORUM, link, "show all forum threads")
+        return IliasPageElement.create_new(IliasElementType.FORUM, link, "show all forum threads")
 
     def _find_personal_desktop_entries(self) -> List[IliasPageElement]:
         items: List[IliasPageElement] = []
@@ -394,7 +449,7 @@ class IliasPage:
                 url = re.sub(r"(target=file_\d+)", r"\1_download", url)
                 log.explain("Rewired file URL to include download part")
 
-            items.append(IliasPageElement(type, url, name))
+            items.append(IliasPageElement.create_new(type, url, name))
 
         return items
 
@@ -412,7 +467,7 @@ class IliasPage:
                 log.warn_contd(f"Found unknown content page item {name!r} with url {url!r}")
                 continue
 
-            items.append(IliasPageElement(IliasElementType.FILE, url, name))
+            items.append(IliasPageElement.create_new(IliasElementType.FILE, url, name))
 
         return items
 
@@ -425,7 +480,7 @@ class IliasPage:
                 continue
             if "cmd=sendfile" not in link["href"]:
                 continue
-            items.append(IliasPageElement(
+            items.append(IliasPageElement.create_new(
                 IliasElementType.FILE,
                 self._abs_url_from_link(link),
                 _sanitize_path_name(link.getText())
@@ -453,7 +508,9 @@ class IliasPage:
             query_params = {"limit": "800", "cmd": "asyncGetTableGUI", "cmdMode": "asynch"}
             url = url_set_query_params(url, query_params)
             log.explain("Found ILIAS video frame page, fetching actual content next")
-            return [IliasPageElement(IliasElementType.OPENCAST_VIDEO_FOLDER_MAYBE_PAGINATED, url, "")]
+            return [
+                IliasPageElement.create_new(IliasElementType.OPENCAST_VIDEO_FOLDER_MAYBE_PAGINATED, url, "")
+            ]
 
         is_paginated = self._soup.find(id=re.compile(r"tab_page_sel.+")) is not None
 
@@ -482,7 +539,7 @@ class IliasPage:
         url = url_set_query_params(self._page_url, query_params)
 
         log.explain("Disabled pagination, retrying folder as a new entry")
-        return [IliasPageElement(IliasElementType.OPENCAST_VIDEO_FOLDER, url, "")]
+        return [IliasPageElement.create_new(IliasElementType.OPENCAST_VIDEO_FOLDER, url, "")]
 
     def _find_opencast_video_entries_no_paging(self) -> List[IliasPageElement]:
         """
@@ -527,7 +584,7 @@ class IliasPage:
         video_url = self._abs_url_from_link(link)
 
         log.explain(f"Found video {video_name!r} at {video_url}")
-        return IliasPageElement(
+        return IliasPageElement.create_new(
             IliasElementType.OPENCAST_VIDEO_PLAYER, video_url, video_name, modification_time
         )
 
@@ -563,7 +620,7 @@ class IliasPage:
             if date is None:
                 log.warn(f"Date parsing failed for exercise entry {name!r}")
 
-            results.append(IliasPageElement(
+            results.append(IliasPageElement.create_new(
                 IliasElementType.FILE,
                 self._abs_url_from_link(link),
                 name,
@@ -596,15 +653,15 @@ class IliasPage:
                 # Two divs, side by side. Left is the name, right is the link ==> get left
                 # sibling
                 file_name = file_link.parent.findPrevious(name="div").getText().strip()
-                file_name = _sanitize_path_name(file_name)
                 url = self._abs_url_from_link(file_link)
 
                 log.explain(f"Found exercise entry {file_name!r}")
-                results.append(IliasPageElement(
+                results.append(IliasPageElement.create_new(
                     IliasElementType.FILE,
                     url,
-                    container_name + "/" + file_name,
-                    None  # We do not have any timestamp
+                    _sanitize_path_name(container_name) + "/" + _sanitize_path_name(file_name),
+                    mtime=None,  # We do not have any timestamp
+                    skip_sanitize=True
                 ))
 
             # Find all links to file listings (e.g. "Submitted Files" for groups)
@@ -622,14 +679,15 @@ class IliasPage:
                 label_container: Tag = parent_container.find(
                     attrs={"class": lambda x: x and "control-label" in x}
                 )
-                file_name = _sanitize_path_name(label_container.getText().strip())
+                file_name = label_container.getText().strip()
                 url = self._abs_url_from_link(listing)
                 log.explain(f"Found exercise detail {file_name!r} at {url}")
-                results.append(IliasPageElement(
+                results.append(IliasPageElement.create_new(
                     IliasElementType.EXERCISE_FILES,
                     url,
-                    container_name + "/" + file_name,
-                    None  # we do not have any timestamp
+                    _sanitize_path_name(container_name) + "/" + _sanitize_path_name(file_name),
+                    None,  # we do not have any timestamp
+                    skip_sanitize=True
                 ))
 
         return results
@@ -637,12 +695,18 @@ class IliasPage:
     def _find_normal_entries(self) -> List[IliasPageElement]:
         result: List[IliasPageElement] = []
 
+        links: List[Tag] = []
         # Fetch all links and throw them to the general interpreter
-        links: List[Tag] = self._soup.select("a.il_ContainerItemTitle")
+        if self._is_course_overview_page():
+            log.explain("Page is a course overview page, adjusting link selector")
+            links.extend(self._soup.select(".il-item-title > a"))
+        else:
+            links.extend(self._soup.select("a.il_ContainerItemTitle"))
 
         for link in links:
             abs_url = self._abs_url_from_link(link)
-            parents = self._find_upwards_folder_hierarchy(link)
+            # Make sure parents are sanitized. We do not want accidental parents
+            parents = [_sanitize_path_name(x) for x in self._find_upwards_folder_hierarchy(link)]
 
             if parents:
                 element_name = "/".join(parents) + "/" + _sanitize_path_name(link.getText())
@@ -660,16 +724,18 @@ class IliasPage:
 
             if not element_type:
                 continue
-            if element_type == IliasElementType.MEETING:
-                normalized = _sanitize_path_name(self._normalize_meeting_name(element_name))
-                log.explain(f"Normalized meeting name from {element_name!r} to {normalized!r}")
-                element_name = normalized
             elif element_type == IliasElementType.FILE:
                 result.append(self._file_to_element(element_name, abs_url, link))
                 continue
 
             log.explain(f"Found {element_name!r}")
-            result.append(IliasPageElement(element_type, abs_url, element_name, description=description))
+            result.append(IliasPageElement.create_new(
+                element_type,
+                abs_url,
+                element_name,
+                description=description,
+                skip_sanitize=True
+            ))
 
         result += self._find_cards()
         result += self._find_mediacast_videos()
@@ -692,8 +758,8 @@ class IliasPage:
                 log.warn_contd(f"No <video> element found for mediacast video '{element_name}'")
                 continue
 
-            videos.append(IliasPageElement(
-                type=IliasElementType.MEDIACAST_VIDEO,
+            videos.append(IliasPageElement.create_new(
+                typ=IliasElementType.MEDIACAST_VIDEO,
                 url=self._abs_url_from_relative(video_element.get("src")),
                 name=element_name,
                 mtime=self._find_mediacast_video_mtime(elem.findParent(name="td"))
@@ -751,11 +817,14 @@ class IliasPage:
             # ILIAS has proper accordions and weird blocks that look like normal headings,
             # but some JS later transforms them into an accordion.
 
-            # This is for these weird JS-y blocks
+            # This is for these weird JS-y blocks and custom item groups
             if "ilContainerItemsContainer" in parent.get("class"):
+                data_store_url = parent.parent.get("data-store-url", "").lower()
+                is_custom_item_group = "baseclass=ilcontainerblockpropertiesstoragegui" in data_store_url \
+                                       and "cont_block_id=" in data_store_url
                 # I am currently under the impression that *only* those JS blocks have an
                 # ilNoDisplay class.
-                if "ilNoDisplay" not in parent.get("class"):
+                if not is_custom_item_group and "ilNoDisplay" not in parent.get("class"):
                     continue
                 prev: Tag = parent.findPreviousSibling("div")
                 if "ilContainerBlockHeader" in prev.get("class"):
@@ -815,7 +884,9 @@ class IliasPage:
         full_path = name + "." + file_type
 
         log.explain(f"Found file {full_path!r}")
-        return IliasPageElement(IliasElementType.FILE, url, full_path, modification_date)
+        return IliasPageElement.create_new(
+            IliasElementType.FILE, url, full_path, modification_date, skip_sanitize=True
+        )
 
     def _find_cards(self) -> List[IliasPageElement]:
         result: List[IliasPageElement] = []
@@ -832,7 +903,7 @@ class IliasPage:
                 log.warn_contd(f"Could not extract type for {title}")
                 continue
 
-            result.append(IliasPageElement(type, url, name))
+            result.append(IliasPageElement.create_new(type, url, name))
 
         card_button_tiles: List[Tag] = self._soup.select(".card-title button")
 
@@ -861,7 +932,7 @@ class IliasPage:
                 log.warn_contd(f"Could not extract type for {button}")
                 continue
 
-            result.append(IliasPageElement(type, url, name, description=description))
+            result.append(IliasPageElement.create_new(type, url, name, description=description))
 
         return result
 
@@ -955,6 +1026,19 @@ class IliasPage:
         if "baseClass=ilSAHSPresentationGUI" in parsed_url.query:
             return IliasElementType.SCORM_LEARNING_MODULE
 
+        # other universities might have content type specified in URL path
+        if "_file_" in parsed_url.path:
+            return IliasElementType.FILE
+
+        if "_fold_" in parsed_url.path or "_copa_" in parsed_url.path:
+            return IliasElementType.FOLDER
+
+        if "_frm_" in parsed_url.path:
+            return IliasElementType.FORUM
+
+        if "_exc_" in parsed_url.path:
+            return IliasElementType.EXERCISE
+
         # Booking and Meeting can not be detected based on the link. They do have a ref_id though, so
         # try to guess it from the image.
 
@@ -1038,33 +1122,6 @@ class IliasPage:
 
         return IliasElementType.FOLDER
 
-    @staticmethod
-    def _normalize_meeting_name(meeting_name: str) -> str:
-        """
-        Normalizes meeting names, which have a relative time as their first part,
-        to their date in ISO format.
-        """
-
-        # This checks whether we can reach a `:` without passing a `-`
-        if re.search(r"^[^-]+: ", meeting_name):
-            # Meeting name only contains date: "05. Jan 2000:"
-            split_delimiter = ":"
-        else:
-            # Meeting name contains date and start/end times: "05. Jan 2000, 16:00 - 17:30:"
-            split_delimiter = ", "
-
-        # We have a meeting day without time
-        date_portion_str = meeting_name.split(split_delimiter)[0]
-        date_portion = demangle_date(date_portion_str)
-
-        # We failed to parse the date, bail out
-        if not date_portion:
-            return meeting_name
-
-        # Replace the first section with the absolute date
-        rest_of_name = split_delimiter.join(meeting_name.split(split_delimiter)[1:])
-        return datetime.strftime(date_portion, "%Y-%m-%d") + split_delimiter + rest_of_name
-
     @staticmethod
     def is_logged_in(soup: BeautifulSoup) -> bool:
         # Normal ILIAS pages

PFERD/crawl/ilias/kit_ilias_web_crawler.py

@@ -1,28 +1,16 @@
-import asyncio
-import base64
-import os
-import re
-from collections.abc import Awaitable, Coroutine
-from pathlib import PurePath
-from typing import Any, Callable, Dict, List, Literal, Optional, Set, Union, cast
-from urllib.parse import urljoin
+from typing import Any, Dict, Optional, Union
 
 import aiohttp
 import yarl
-from aiohttp import hdrs
-from bs4 import BeautifulSoup, Tag
+from bs4 import BeautifulSoup
 
 from ...auth import Authenticator, TfaAuthenticator
 from ...config import Config
-from ...logging import ProgressBar, log
-from ...output_dir import FileSink, Redownload
-from ...utils import fmt_path, soupify, url_set_query_param
-from ..crawler import AWrapped, CrawlError, CrawlToken, CrawlWarning, DownloadToken, anoncritical
-from ..http_crawler import HttpCrawler, HttpCrawlerSection
-from .file_templates import Links, learning_module_template
-from .ilias_html_cleaner import clean, insert_base_markup
-from .kit_ilias_html import (IliasElementType, IliasForumThread, IliasLearningModulePage, IliasPage,
-                             IliasPageElement, _sanitize_path_name, parse_ilias_forum_export)
+from ...logging import log
+from ...utils import soupify
+from ..crawler import CrawlError, CrawlWarning
+from .async_helper import _iorepeat
+from .ilias_web_crawler import IliasWebCrawler, IliasWebCrawlerSection
 
 TargetType = Union[str, int]
 
@@ -33,23 +21,14 @@ class KitShibbolethBackgroundLoginSuccessful():
     pass
 
 
-class KitIliasWebCrawlerSection(HttpCrawlerSection):
-    def target(self) -> TargetType:
-        target = self.s.get("target")
-        if not target:
-            self.missing_value("target")
+class KitIliasWebCrawlerSection(IliasWebCrawlerSection):
+    def base_url(self) -> str:
+        return _ILIAS_URL
 
-        if re.fullmatch(r"\d+", target):
-            # Course id
-            return int(target)
-        if target == "desktop":
-            # Full personal desktop
-            return target
-        if target.startswith(_ILIAS_URL):
-            # ILIAS URL
-            return target
-
-        self.invalid_value("target", target, "Should be <course id | desktop | kit ilias URL>")
+    def client_id(self) -> str:
+        # KIT ILIAS uses the Shibboleth service for authentication. There's no
+        # use for a client id.
+        return "unused"
 
     def tfa_auth(self, authenticators: Dict[str, Authenticator]) -> Optional[Authenticator]:
         value: Optional[str] = self.s.get("tfa_auth")
@@ -60,123 +39,8 @@ class KitIliasWebCrawlerSection(HttpCrawlerSection):
             self.invalid_value("tfa_auth", value, "No such auth section exists")
         return auth
 
-    def links(self) -> Links:
-        type_str: Optional[str] = self.s.get("links")
 
-        if type_str is None:
-            return Links.FANCY
-
-        try:
-            return Links.from_string(type_str)
-        except ValueError as e:
-            self.invalid_value("links", type_str, str(e).capitalize())
-
-    def link_redirect_delay(self) -> int:
-        return self.s.getint("link_redirect_delay", fallback=-1)
-
-    def videos(self) -> bool:
-        return self.s.getboolean("videos", fallback=False)
-
-    def forums(self) -> bool:
-        return self.s.getboolean("forums", fallback=False)
-
-
-_DIRECTORY_PAGES: Set[IliasElementType] = {
-    IliasElementType.EXERCISE,
-    IliasElementType.EXERCISE_FILES,
-    IliasElementType.FOLDER,
-    IliasElementType.INFO_TAB,
-    IliasElementType.MEETING,
-    IliasElementType.MEDIACAST_VIDEO_FOLDER,
-    IliasElementType.OPENCAST_VIDEO_FOLDER,
-    IliasElementType.OPENCAST_VIDEO_FOLDER_MAYBE_PAGINATED,
-}
-
-_VIDEO_ELEMENTS: Set[IliasElementType] = {
-    IliasElementType.MEDIACAST_VIDEO_FOLDER,
-    IliasElementType.MEDIACAST_VIDEO,
-    IliasElementType.OPENCAST_VIDEO,
-    IliasElementType.OPENCAST_VIDEO_PLAYER,
-    IliasElementType.OPENCAST_VIDEO_FOLDER,
-    IliasElementType.OPENCAST_VIDEO_FOLDER_MAYBE_PAGINATED,
-}
-
-
-def _iorepeat(attempts: int, name: str, failure_is_error: bool = False) -> Callable[[AWrapped], AWrapped]:
-    def decorator(f: AWrapped) -> AWrapped:
-        async def wrapper(*args: Any, **kwargs: Any) -> Optional[Any]:
-            last_exception: Optional[BaseException] = None
-            for round in range(attempts):
-                try:
-                    return await f(*args, **kwargs)
-                except aiohttp.ContentTypeError:  # invalid content type
-                    raise CrawlWarning("ILIAS returned an invalid content type")
-                except aiohttp.TooManyRedirects:
-                    raise CrawlWarning("Got stuck in a redirect loop")
-                except aiohttp.ClientPayloadError as e:  # encoding or not enough bytes
-                    last_exception = e
-                except aiohttp.ClientConnectionError as e:  # e.g. timeout, disconnect, resolve failed, etc.
-                    last_exception = e
-                except asyncio.exceptions.TimeoutError as e:  # explicit http timeouts in HttpCrawler
-                    last_exception = e
-                log.explain_topic(f"Retrying operation {name}. Retries left: {attempts - 1 - round}")
-
-            if last_exception:
-                message = f"Error in I/O Operation: {last_exception}"
-                if failure_is_error:
-                    raise CrawlError(message) from last_exception
-                else:
-                    raise CrawlWarning(message) from last_exception
-            raise CrawlError("Impossible return in ilias _iorepeat")
-
-        return wrapper  # type: ignore
-
-    return decorator
-
-
-def _wrap_io_in_warning(name: str) -> Callable[[AWrapped], AWrapped]:
-    """
-    Wraps any I/O exception in a CrawlWarning.
-    """
-    return _iorepeat(1, name)
-
-
-def _get_video_cache_key(element: IliasPageElement) -> str:
-    return f"ilias-video-cache-{element.id()}"
-
-
-# Crawler control flow:
-#
-#     crawl_desktop -+
-#                    |
-#     crawl_course --+
-#                    |
-#     @_io_repeat    |        # retries internally (before the bar)
-#  +- crawl_url    <-+
-#  |
-#  |
-#  |  @_wrap_io_exception     # does not need to retry as children acquire bars
-#  +> crawl_ilias_element -+
-#  ^                       |
-#  |  @_io_repeat          |  # retries internally (before the bar)
-#  +- crawl_ilias_page <---+
-#  |                       |
-#  +> get_page             |  # Handles and retries authentication
-#                          |
-#     @_io_repeat          |  # retries internally (before the bar)
-#  +- download_link    <---+
-#  |                       |
-#  +> resolve_target       |  # Handles and retries authentication
-#                          |
-#     @_io_repeat          |  # retries internally (before the bar)
-#  +- download_video   <---+
-#  |                       |
-#  |  @_io_repeat          |  # retries internally (before the bar)
-#  +- download_file    <---+
-#  |
-#  +> stream_from_url         # Handles and retries authentication
-
-class KitIliasWebCrawler(HttpCrawler):
+class KitIliasWebCrawler(IliasWebCrawler):
     def __init__(
         self,
         name: str,
@@ -184,806 +48,13 @@ class KitIliasWebCrawler(HttpCrawler):
         config: Config,
         authenticators: Dict[str, Authenticator]
     ):
-        # Setting a main authenticator for cookie sharing
-        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())
+        super().__init__(name, section, config, authenticators)
 
         self._shibboleth_login = KitShibbolethLogin(
-            auth,
+            self._auth,
             section.tfa_auth(authenticators),
         )
 
-        self._base_url = _ILIAS_URL
-
-        self._target = section.target()
-        self._link_file_redirect_delay = section.link_redirect_delay()
-        self._links = section.links()
-        self._videos = section.videos()
-        self._forums = section.forums()
-        self._visited_urls: Dict[str, PurePath] = dict()
-
-    async def _run(self) -> None:
-        if isinstance(self._target, int):
-            log.explain_topic(f"Inferred crawl target: Course with id {self._target}")
-            await self._crawl_course(self._target)
-        elif self._target == "desktop":
-            log.explain_topic("Inferred crawl target: Personal desktop")
-            await self._crawl_desktop()
-        else:
-            log.explain_topic(f"Inferred crawl target: URL {self._target}")
-            await self._crawl_url(self._target)
-
-    async def _crawl_course(self, course_id: int) -> None:
-        # Start crawling at the given course
-        root_url = url_set_query_param(
-            self._base_url + "/goto.php", "target", f"crs_{course_id}"
-        )
-
-        await self._crawl_url(root_url, expected_id=course_id)
-
-    async def _crawl_desktop(self) -> None:
-        appendix = r"ILIAS\Repository\Provider\RepositoryMainBarProvider|mm_pd_sel_items"
-        appendix = appendix.encode("ASCII").hex()
-        await self._crawl_url(self._base_url + "/gs_content.php?item=" + appendix)
-
-    async def _crawl_url(self, url: str, expected_id: Optional[int] = None) -> None:
-        maybe_cl = await self.crawl(PurePath("."))
-        if not maybe_cl:
-            return
-        cl = maybe_cl  # Not mypy's fault, but explained here: https://github.com/python/mypy/issues/2608
-
-        elements: List[IliasPageElement] = []
-        # A list as variable redefinitions are not propagated to outer scopes
-        description: List[BeautifulSoup] = []
-
-        @_iorepeat(3, "crawling url")
-        async def gather_elements() -> None:
-            elements.clear()
-            async with cl:
-                next_stage_url: Optional[str] = url
-                current_parent = None
-
-                # Duplicated code, but the root page is special - we want to avoid fetching it twice!
-                while next_stage_url:
-                    soup = await self._get_page(next_stage_url, root_page_allowed=True)
-
-                    if current_parent is None and expected_id is not None:
-                        perma_link = IliasPage.get_soup_permalink(soup)
-                        if not perma_link or "crs_" not in perma_link:
-                            raise CrawlError("Invalid course id? Didn't find anything looking like a course")
-
-                    log.explain_topic(f"Parsing HTML page for {fmt_path(cl.path)}")
-                    log.explain(f"URL: {next_stage_url}")
-                    page = IliasPage(soup, next_stage_url, current_parent)
-                    if next_element := page.get_next_stage_element():
-                        current_parent = next_element
-                        next_stage_url = next_element.url
-                    else:
-                        next_stage_url = None
-
-                elements.extend(page.get_child_elements())
-                if info_tab := page.get_info_tab():
-                    elements.append(info_tab)
-                if description_string := page.get_description():
-                    description.append(description_string)
-
-        # Fill up our task list with the found elements
-        await gather_elements()
-
-        if description:
-            await self._download_description(PurePath("."), description[0])
-
-        elements.sort(key=lambda e: e.id())
-
-        tasks: List[Awaitable[None]] = []
-        for element in elements:
-            if handle := await self._handle_ilias_element(PurePath("."), element):
-                tasks.append(asyncio.create_task(handle))
-
-        # And execute them
-        await self.gather(tasks)
-
-    async def _handle_ilias_page(
-        self,
-        url: str,
-        parent: IliasPageElement,
-        path: PurePath,
-    ) -> Optional[Coroutine[Any, Any, None]]:
-        maybe_cl = await self.crawl(path)
-        if not maybe_cl:
-            return None
-        return self._crawl_ilias_page(url, parent, maybe_cl)
-
-    @anoncritical
-    async def _crawl_ilias_page(
-        self,
-        url: str,
-        parent: IliasPageElement,
-        cl: CrawlToken,
-    ) -> None:
-        elements: List[IliasPageElement] = []
-        # A list as variable redefinitions are not propagated to outer scopes
-        description: List[BeautifulSoup] = []
-
-        @_iorepeat(3, "crawling folder")
-        async def gather_elements() -> None:
-            elements.clear()
-            async with cl:
-                next_stage_url: Optional[str] = url
-                current_parent = parent
-
-                while next_stage_url:
-                    soup = await self._get_page(next_stage_url)
-                    log.explain_topic(f"Parsing HTML page for {fmt_path(cl.path)}")
-                    log.explain(f"URL: {next_stage_url}")
-                    page = IliasPage(soup, next_stage_url, current_parent)
-                    if next_element := page.get_next_stage_element():
-                        current_parent = next_element
-                        next_stage_url = next_element.url
-                    else:
-                        next_stage_url = None
-
-                elements.extend(page.get_child_elements())
-                if description_string := page.get_description():
-                    description.append(description_string)
-
-        # Fill up our task list with the found elements
-        await gather_elements()
-
-        if description:
-            await self._download_description(cl.path, description[0])
-
-        elements.sort(key=lambda e: e.id())
-
-        tasks: List[Awaitable[None]] = []
-        for element in elements:
-            if handle := await self._handle_ilias_element(cl.path, element):
-                tasks.append(asyncio.create_task(handle))
-
-        # And execute them
-        await self.gather(tasks)
-
-    # These decorators only apply *to this method* and *NOT* to the returned
-    # awaitables!
-    # This method does not await the handlers but returns them instead.
-    # This ensures one level is handled at a time and name deduplication
-    # works correctly.
-    @anoncritical
-    async def _handle_ilias_element(
-        self,
-        parent_path: PurePath,
-        element: IliasPageElement,
-    ) -> Optional[Coroutine[Any, Any, None]]:
-        if element.url in self._visited_urls:
-            raise CrawlWarning(
-                f"Found second path to element {element.name!r} at {element.url!r}. "
-                + f"First path: {fmt_path(self._visited_urls[element.url])}. "
-                + f"Second path: {fmt_path(parent_path)}."
-            )
-        self._visited_urls[element.url] = parent_path
-
-        element_path = PurePath(parent_path, element.name)
-
-        if element.type in _VIDEO_ELEMENTS:
-            if not self._videos:
-                log.status(
-                    "[bold bright_black]",
-                    "Ignored",
-                    fmt_path(element_path),
-                    "[bright_black](enable with option 'videos')"
-                )
-                return None
-
-        if element.type == IliasElementType.FILE:
-            return await self._handle_file(element, element_path)
-        elif element.type == IliasElementType.FORUM:
-            if not self._forums:
-                log.status(
-                    "[bold bright_black]",
-                    "Ignored",
-                    fmt_path(element_path),
-                    "[bright_black](enable with option 'forums')"
-                )
-                return None
-            return await self._handle_forum(element, element_path)
-        elif element.type == IliasElementType.TEST:
-            log.status(
-                "[bold bright_black]",
-                "Ignored",
-                fmt_path(element_path),
-                "[bright_black](tests contain no relevant data)"
-            )
-            return None
-        elif element.type == IliasElementType.SURVEY:
-            log.status(
-                "[bold bright_black]",
-                "Ignored",
-                fmt_path(element_path),
-                "[bright_black](surveys contain no relevant data)"
-            )
-            return None
-        elif element.type == IliasElementType.SCORM_LEARNING_MODULE:
-            log.status(
-                "[bold bright_black]",
-                "Ignored",
-                fmt_path(element_path),
-                "[bright_black](scorm learning modules are not supported)"
-            )
-            return None
-        elif element.type == IliasElementType.LEARNING_MODULE:
-            return await self._handle_learning_module(element, element_path)
-        elif element.type == IliasElementType.LINK:
-            return await self._handle_link(element, element_path)
-        elif element.type == IliasElementType.BOOKING:
-            return await self._handle_booking(element, element_path)
-        elif element.type == IliasElementType.OPENCAST_VIDEO:
-            return await self._handle_file(element, element_path)
-        elif element.type == IliasElementType.OPENCAST_VIDEO_PLAYER:
-            return await self._handle_opencast_video(element, element_path)
-        elif element.type == IliasElementType.MEDIACAST_VIDEO:
-            return await self._handle_file(element, element_path)
-        elif element.type in _DIRECTORY_PAGES:
-            return await self._handle_ilias_page(element.url, element, element_path)
-        else:
-            # This will retry it a few times, failing everytime. It doesn't make any network
-            # requests, so that's fine.
-            raise CrawlWarning(f"Unknown element type: {element.type!r}")
-
-    async def _handle_link(
-        self,
-        element: IliasPageElement,
-        element_path: PurePath,
-    ) -> Optional[Coroutine[Any, Any, None]]:
-        log.explain_topic(f"Decision: Crawl Link {fmt_path(element_path)}")
-        log.explain(f"Links type is {self._links}")
-
-        link_template_maybe = self._links.template()
-        link_extension = self._links.extension()
-        if not link_template_maybe or not link_extension:
-            log.explain("Answer: No")
-            return None
-        else:
-            log.explain("Answer: Yes")
-        element_path = element_path.with_name(element_path.name + link_extension)
-
-        maybe_dl = await self.download(element_path, mtime=element.mtime)
-        if not maybe_dl:
-            return None
-
-        return self._download_link(element, link_template_maybe, maybe_dl)
-
-    @anoncritical
-    @_iorepeat(3, "resolving link")
-    async def _download_link(self, element: IliasPageElement, link_template: str, dl: DownloadToken) -> None:
-        async with dl as (bar, sink):
-            export_url = element.url.replace("cmd=calldirectlink", "cmd=exportHTML")
-            real_url = await self._resolve_link_target(export_url)
-            self._write_link_content(link_template, real_url, element.name, element.description, sink)
-
-    def _write_link_content(
-        self,
-        link_template: str,
-        url: str,
-        name: str,
-        description: Optional[str],
-        sink: FileSink,
-    ) -> None:
-        content = link_template
-        content = content.replace("{{link}}", url)
-        content = content.replace("{{name}}", name)
-        content = content.replace("{{description}}", str(description))
-        content = content.replace("{{redirect_delay}}", str(self._link_file_redirect_delay))
-        sink.file.write(content.encode("utf-8"))
-        sink.done()
-
-    async def _handle_booking(
-        self,
-        element: IliasPageElement,
-        element_path: PurePath,
-    ) -> Optional[Coroutine[Any, Any, None]]:
-        log.explain_topic(f"Decision: Crawl Booking Link {fmt_path(element_path)}")
-        log.explain(f"Links type is {self._links}")
-
-        link_template_maybe = self._links.template()
-        link_extension = self._links.extension()
-        if not link_template_maybe or not link_extension:
-            log.explain("Answer: No")
-            return None
-        else:
-            log.explain("Answer: Yes")
-        element_path = element_path.with_name(element_path.name + link_extension)
-
-        maybe_dl = await self.download(element_path, mtime=element.mtime)
-        if not maybe_dl:
-            return None
-
-        return self._download_booking(element, link_template_maybe, maybe_dl)
-
-    @anoncritical
-    @_iorepeat(1, "downloading description")
-    async def _download_description(self, parent_path: PurePath, description: BeautifulSoup) -> None:
-        path = parent_path / "Description.html"
-        dl = await self.download(path, redownload=Redownload.ALWAYS)
-        if not dl:
-            return
-
-        async with dl as (bar, sink):
-            description = clean(insert_base_markup(description))
-            sink.file.write(description.prettify().encode("utf-8"))
-            sink.done()
-
-    @anoncritical
-    @_iorepeat(3, "resolving booking")
-    async def _download_booking(
-        self,
-        element: IliasPageElement,
-        link_template: str,
-        dl: DownloadToken,
-    ) -> None:
-        async with dl as (bar, sink):
-            self._write_link_content(link_template, element.url, element.name, element.description, sink)
-
-    async def _resolve_link_target(self, export_url: str) -> str:
-        async with self.session.get(export_url, allow_redirects=False) as resp:
-            # No redirect means we were authenticated
-            if hdrs.LOCATION not in resp.headers:
-                return soupify(await resp.read()).select_one("a").get("href").strip()
-
-        await self._authenticate()
-
-        async with self.session.get(export_url, allow_redirects=False) as resp:
-            # No redirect means we were authenticated
-            if hdrs.LOCATION not in resp.headers:
-                return soupify(await resp.read()).select_one("a").get("href").strip()
-
-        raise CrawlError("resolve_link_target failed even after authenticating")
-
-    async def _handle_opencast_video(
-        self,
-        element: IliasPageElement,
-        element_path: PurePath,
-    ) -> Optional[Coroutine[Any, Any, None]]:
-        # Copy old mapping as it is likely still relevant
-        if self.prev_report:
-            self.report.add_custom_value(
-                _get_video_cache_key(element),
-                self.prev_report.get_custom_value(_get_video_cache_key(element))
-            )
-
-        # A video might contain other videos, so let's "crawl" the video first
-        # to ensure rate limits apply. This must be a download as *this token*
-        # is re-used if the video consists of a single stream. In that case the
-        # file name is used and *not* the stream name the ilias html parser reported
-        # to ensure backwards compatibility.
-        maybe_dl = await self.download(element_path, mtime=element.mtime, redownload=Redownload.ALWAYS)
-
-        # If we do not want to crawl it (user filter), we can move on
-        if not maybe_dl:
-            return None
-
-        # If we have every file from the cached mapping already, we can ignore this and bail
-        if self._all_opencast_videos_locally_present(element, maybe_dl.path):
-            # Mark all existing videos as known to ensure they do not get deleted during cleanup.
-            # We "downloaded" them, just without actually making a network request as we assumed
-            # they did not change.
-            contained = self._previous_contained_opencast_videos(element, maybe_dl.path)
-            if len(contained) > 1:
-                # Only do this if we threw away the original dl token,
-                # to not download single-stream videos twice
-                for video in contained:
-                    await self.download(video)
-
-            return None
-
-        return self._download_opencast_video(element, maybe_dl)
-
-    def _previous_contained_opencast_videos(
-        self, element: IliasPageElement, element_path: PurePath
-    ) -> List[PurePath]:
-        if not self.prev_report:
-            return []
-        custom_value = self.prev_report.get_custom_value(_get_video_cache_key(element))
-        if not custom_value:
-            return []
-        cached_value = cast(dict[str, Any], custom_value)
-        if "known_paths" not in cached_value or "own_path" not in cached_value:
-            log.explain(f"'known_paths' or 'own_path' missing from cached value: {cached_value}")
-            return []
-        transformed_own_path = self._transformer.transform(element_path)
-        if cached_value["own_path"] != str(transformed_own_path):
-            log.explain(
-                f"own_path '{transformed_own_path}' does not match cached value: '{cached_value['own_path']}"
-            )
-            return []
-        return [PurePath(name) for name in cached_value["known_paths"]]
-
-    def _all_opencast_videos_locally_present(self, element: IliasPageElement, element_path: PurePath) -> bool:
-        log.explain_topic(f"Checking local cache for video {fmt_path(element_path)}")
-        if contained_videos := self._previous_contained_opencast_videos(element, element_path):
-            log.explain(
-                f"The following contained videos are known: {','.join(map(fmt_path, contained_videos))}"
-            )
-            if all(self._output_dir.resolve(path).exists() for path in contained_videos):
-                log.explain("Found all known videos locally, skipping enumeration request")
-                return True
-            log.explain("Missing at least one video, continuing with requests!")
-        else:
-            log.explain("No local cache present")
-        return False
-
-    @anoncritical
-    @_iorepeat(3, "downloading video")
-    async def _download_opencast_video(self, element: IliasPageElement, dl: DownloadToken) -> None:
-        def add_to_report(paths: list[str]) -> None:
-            self.report.add_custom_value(
-                _get_video_cache_key(element),
-                {"known_paths": paths, "own_path": str(self._transformer.transform(dl.path))}
-            )
-
-        async with dl as (bar, sink):
-            page = IliasPage(await self._get_page(element.url), element.url, element)
-            stream_elements = page.get_child_elements()
-
-            if len(stream_elements) > 1:
-                log.explain(f"Found multiple video streams for {element.name}")
-            else:
-                log.explain(f"Using single video mode for {element.name}")
-                stream_element = stream_elements[0]
-
-                # We do not have a local cache yet
-                await self._stream_from_url(stream_element.url, sink, bar, is_video=True)
-                add_to_report([str(self._transformer.transform(dl.path))])
-                return
-
-        contained_video_paths: List[str] = []
-
-        for stream_element in stream_elements:
-            video_path = dl.path.parent / stream_element.name
-
-            maybe_dl = await self.download(video_path, mtime=element.mtime, redownload=Redownload.NEVER)
-            if not maybe_dl:
-                continue
-            async with maybe_dl as (bar, sink):
-                log.explain(f"Streaming video from real url {stream_element.url}")
-                contained_video_paths.append(str(self._transformer.transform(maybe_dl.path)))
-                await self._stream_from_url(stream_element.url, sink, bar, is_video=True)
-
-        add_to_report(contained_video_paths)
-
-    async def _handle_file(
-        self,
-        element: IliasPageElement,
-        element_path: PurePath,
-    ) -> Optional[Coroutine[Any, Any, None]]:
-        maybe_dl = await self.download(element_path, mtime=element.mtime)
-        if not maybe_dl:
-            return None
-        return self._download_file(element, maybe_dl)
-
-    @_iorepeat(3, "downloading file")
-    @anoncritical
-    async def _download_file(self, element: IliasPageElement, dl: DownloadToken) -> None:
-        assert dl  # The function is only reached when dl is not None
-        async with dl as (bar, sink):
-            await self._stream_from_url(element.url, sink, bar, is_video=False)
-
-    async def _stream_from_url(self, url: str, sink: FileSink, bar: ProgressBar, is_video: bool) -> None:
-        async def try_stream() -> bool:
-            next_url = url
-
-            # Normal files redirect to the magazine if we are not authenticated. As files could be HTML,
-            # we can not match on the content type here. Instead, we disallow redirects and inspect the
-            # new location. If we are redirected anywhere but the ILIAS 8 "sendfile" command, we assume
-            # our authentication expired.
-            if not is_video:
-                async with self.session.get(url, allow_redirects=False) as resp:
-                    # Redirect to anything except a "sendfile" means we weren't authenticated
-                    if hdrs.LOCATION in resp.headers:
-                        if "&cmd=sendfile" not in resp.headers[hdrs.LOCATION]:
-                            return False
-                        # Directly follow the redirect to not make a second, unnecessary request
-                        next_url = resp.headers[hdrs.LOCATION]
-
-            # Let's try this again and follow redirects
-            return await fetch_follow_redirects(next_url)
-
-        async def fetch_follow_redirects(file_url: str) -> bool:
-            async with self.session.get(file_url) as resp:
-                # We wanted a video but got HTML => Forbidden, auth expired. Logging in won't really
-                # solve that depending on the setup, but it is better than nothing.
-                if is_video and "html" in resp.content_type:
-                    return False
-
-                if resp.content_length:
-                    bar.set_total(resp.content_length)
-
-                async for data in resp.content.iter_chunked(1024):
-                    sink.file.write(data)
-                    bar.advance(len(data))
-
-                sink.done()
-            return True
-
-        auth_id = await self._current_auth_id()
-        if await try_stream():
-            return
-
-        await self.authenticate(auth_id)
-
-        if not await try_stream():
-            raise CrawlError("File streaming failed after authenticate()")
-
-    async def _handle_forum(
-        self,
-        element: IliasPageElement,
-        element_path: PurePath,
-    ) -> Optional[Coroutine[Any, Any, None]]:
-        maybe_cl = await self.crawl(element_path)
-        if not maybe_cl:
-            return None
-        return self._crawl_forum(element, maybe_cl)
-
-    @_iorepeat(3, "crawling forum")
-    @anoncritical
-    async def _crawl_forum(self, element: IliasPageElement, cl: CrawlToken) -> None:
-        elements: List[IliasForumThread] = []
-
-        async with cl:
-            next_stage_url = element.url
-            while next_stage_url:
-                log.explain_topic(f"Parsing HTML page for {fmt_path(cl.path)}")
-                log.explain(f"URL: {next_stage_url}")
-
-                soup = await self._get_page(next_stage_url)
-                page = IliasPage(soup, next_stage_url, element)
-
-                if next := page.get_next_stage_element():
-                    next_stage_url = next.url
-                else:
-                    break
-
-            download_data = page.get_download_forum_data()
-            if not download_data:
-                raise CrawlWarning("Failed to extract forum data")
-            if download_data.empty:
-                log.explain("Forum had no threads")
-                return
-            html = await self._post_authenticated(download_data.url, download_data.form_data)
-            elements = parse_ilias_forum_export(soupify(html))
-
-        elements.sort(key=lambda elem: elem.title)
-
-        tasks: List[Awaitable[None]] = []
-        for elem in elements:
-            tasks.append(asyncio.create_task(self._download_forum_thread(cl.path, elem)))
-
-        # And execute them
-        await self.gather(tasks)
-
-    @anoncritical
-    @_iorepeat(3, "saving forum thread")
-    async def _download_forum_thread(
-        self,
-        parent_path: PurePath,
-        element: IliasForumThread,
-    ) -> None:
-        path = parent_path / (_sanitize_path_name(element.title) + ".html")
-        maybe_dl = await self.download(path, mtime=element.mtime)
-        if not maybe_dl:
-            return
-
-        async with maybe_dl as (bar, sink):
-            content = element.title_tag.prettify()
-            content += element.content_tag.prettify()
-            sink.file.write(content.encode("utf-8"))
-            sink.done()
-
-    async def _handle_learning_module(
-        self,
-        element: IliasPageElement,
-        element_path: PurePath,
-    ) -> Optional[Coroutine[Any, Any, None]]:
-        maybe_cl = await self.crawl(element_path)
-        if not maybe_cl:
-            return None
-        return self._crawl_learning_module(element, maybe_cl)
-
-    @_iorepeat(3, "crawling learning module")
-    @anoncritical
-    async def _crawl_learning_module(self, element: IliasPageElement, cl: CrawlToken) -> None:
-        elements: List[IliasLearningModulePage] = []
-
-        async with cl:
-            log.explain_topic(f"Parsing initial HTML page for {fmt_path(cl.path)}")
-            log.explain(f"URL: {element.url}")
-            soup = await self._get_page(element.url)
-            page = IliasPage(soup, element.url, element)
-            if next := page.get_learning_module_data():
-                elements.extend(await self._crawl_learning_module_direction(
-                    cl.path, next.previous_url, "left", element
-                ))
-                elements.append(next)
-                elements.extend(await self._crawl_learning_module_direction(
-                    cl.path, next.next_url, "right", element
-                ))
-
-        # Reflect their natural ordering in the file names
-        for index, lm_element in enumerate(elements):
-            lm_element.title = f"{index:02}_{lm_element.title}"
-
-        tasks: List[Awaitable[None]] = []
-        for index, elem in enumerate(elements):
-            prev_url = elements[index - 1].title if index > 0 else None
-            next_url = elements[index + 1].title if index < len(elements) - 1 else None
-            tasks.append(asyncio.create_task(
-                self._download_learning_module_page(cl.path, elem, prev_url, next_url)
-            ))
-
-        # And execute them
-        await self.gather(tasks)
-
-    async def _crawl_learning_module_direction(
-        self,
-        path: PurePath,
-        start_url: Optional[str],
-        dir: Union[Literal["left"], Literal["right"]],
-        parent_element: IliasPageElement
-    ) -> List[IliasLearningModulePage]:
-        elements: List[IliasLearningModulePage] = []
-
-        if not start_url:
-            return elements
-
-        next_element_url: Optional[str] = start_url
-        counter = 0
-        while next_element_url:
-            log.explain_topic(f"Parsing HTML page for {fmt_path(path)} ({dir}-{counter})")
-            log.explain(f"URL: {next_element_url}")
-            soup = await self._get_page(next_element_url)
-            page = IliasPage(soup, next_element_url, parent_element)
-            if next := page.get_learning_module_data():
-                elements.append(next)
-                if dir == "left":
-                    next_element_url = next.previous_url
-                else:
-                    next_element_url = next.next_url
-            counter += 1
-
-        return elements
-
-    @anoncritical
-    @_iorepeat(3, "saving learning module page")
-    async def _download_learning_module_page(
-        self,
-        parent_path: PurePath,
-        element: IliasLearningModulePage,
-        prev: Optional[str],
-        next: Optional[str]
-    ) -> None:
-        path = parent_path / (_sanitize_path_name(element.title) + ".html")
-        maybe_dl = await self.download(path)
-        if not maybe_dl:
-            return
-        my_path = self._transformer.transform(maybe_dl.path)
-        if not my_path:
-            return
-
-        if prev:
-            prev_p = self._transformer.transform(parent_path / (_sanitize_path_name(prev) + ".html"))
-            if prev_p:
-                prev = os.path.relpath(prev_p, my_path.parent)
-            else:
-                prev = None
-        if next:
-            next_p = self._transformer.transform(parent_path / (_sanitize_path_name(next) + ".html"))
-            if next_p:
-                next = os.path.relpath(next_p, my_path.parent)
-            else:
-                next = None
-
-        async with maybe_dl as (bar, sink):
-            content = element.content
-            content = await self.internalize_images(content)
-            sink.file.write(learning_module_template(content, maybe_dl.path.name, prev, next).encode("utf-8"))
-            sink.done()
-
-    async def internalize_images(self, tag: Tag) -> Tag:
-        """
-        Tries to fetch ILIAS images and embed them as base64 data.
-        """
-        log.explain_topic("Internalizing images")
-        for elem in tag.find_all(recursive=True):
-            if not isinstance(elem, Tag):
-                continue
-            if elem.name == "img":
-                if src := elem.attrs.get("src", None):
-                    url = urljoin(_ILIAS_URL, src)
-                    if not url.startswith(_ILIAS_URL):
-                        continue
-                    log.explain(f"Internalizing {url!r}")
-                    img = await self._get_authenticated(url)
-                    elem.attrs["src"] = "data:;base64," + base64.b64encode(img).decode()
-            if elem.name == "iframe" and elem.attrs.get("src", "").startswith("//"):
-                # For unknown reasons the protocol seems to be stripped.
-                elem.attrs["src"] = "https:" + elem.attrs["src"]
-        return tag
-
-    async def _get_page(self, url: str, root_page_allowed: bool = False) -> BeautifulSoup:
-        auth_id = await self._current_auth_id()
-        async with self.session.get(url) as request:
-            soup = soupify(await request.read())
-            if IliasPage.is_logged_in(soup):
-                return self._verify_page(soup, url, root_page_allowed)
-
-        # We weren't authenticated, so try to do that
-        await self.authenticate(auth_id)
-
-        # Retry once after authenticating. If this fails, we will die.
-        async with self.session.get(url) as request:
-            soup = soupify(await request.read())
-            if IliasPage.is_logged_in(soup):
-                return self._verify_page(soup, url, root_page_allowed)
-        raise CrawlError(f"get_page failed even after authenticating on {url!r}")
-
-    @staticmethod
-    def _verify_page(soup: BeautifulSoup, url: str, root_page_allowed: bool) -> BeautifulSoup:
-        if IliasPage.is_root_page(soup) and not root_page_allowed:
-            raise CrawlError(
-                "Unexpectedly encountered ILIAS root page. "
-                "This usually happens because the ILIAS instance is broken. "
-                "If so, wait a day or two and try again. "
-                "It could also happen because a crawled element links to the ILIAS root page. "
-                "If so, use a transform with a ! as target to ignore the particular element. "
-                f"The redirect came from {url}"
-            )
-        return soup
-
-    async def _post_authenticated(
-        self,
-        url: str,
-        data: dict[str, Union[str, List[str]]]
-    ) -> bytes:
-        auth_id = await self._current_auth_id()
-
-        form_data = aiohttp.FormData()
-        for key, val in data.items():
-            form_data.add_field(key, val)
-
-        async with self.session.post(url, data=form_data(), allow_redirects=False) as request:
-            if request.status == 200:
-                return await request.read()
-
-        # We weren't authenticated, so try to do that
-        await self.authenticate(auth_id)
-
-        # Retry once after authenticating. If this fails, we will die.
-        async with self.session.post(url, data=data, allow_redirects=False) as request:
-            if request.status == 200:
-                return await request.read()
-        raise CrawlError("post_authenticated failed even after authenticating")
-
-    async def _get_authenticated(self, url: str) -> bytes:
-        auth_id = await self._current_auth_id()
-
-        async with self.session.get(url, allow_redirects=False) as request:
-            if request.status == 200:
-                return await request.read()
-
-        # We weren't authenticated, so try to do that
-        await self.authenticate(auth_id)
-
-        # Retry once after authenticating. If this fails, we will die.
-        async with self.session.get(url, allow_redirects=False) as request:
-            if request.status == 200:
-                return await request.read()
-        raise CrawlError("get_authenticated failed even after authenticating")
-
     # We repeat this as the login method in shibboleth doesn't handle I/O errors.
     # Shibboleth is quite reliable as well, the repeat is likely not critical here.
     @_iorepeat(3, "Login", failure_is_error=True)

PFERD/transformer.py

@@ -110,6 +110,10 @@ class ExactReTf(Transformation):
             except ValueError:
                 pass
 
+        named_groups: Dict[str, str] = match.groupdict()
+        for name, capture in named_groups.items():
+            locals_dir[name] = capture
+
         result = eval(f"f{right!r}", {}, locals_dir)
         return Transformed(PurePath(result))
 

PFERD/version.py

@@ -1,2 +1,2 @@
 NAME = "PFERD"
-VERSION = "3.5.2"
+VERSION = "3.6.0"

README.md

@@ -56,6 +56,17 @@ Also, you can download most ILIAS pages directly like this:
 $ pferd kit-ilias-web <url> <output_directory>
 ```
 
+PFERD supports other ILIAS instances as well, using the `ilias-web` crawler (see
+the [config section on `ilias-web`](CONFIG.md#the-ilias-web-crawler) for more
+detail on the `base-url` and `client-id` parameters):
+
+```
+$ pferd ilias-web \
+    --base-url https://ilias.my-university.example \
+    --client-id My_University desktop \
+    <output_directory>
+```
+
 However, the CLI only lets you download a single thing at a time, and the
 resulting command can grow long quite quickly. Because of this, PFERD can also
 be used with a config file.

mypy.ini

@@ -1,11 +0,0 @@
-[mypy]
-disallow_any_generics = True
-disallow_untyped_defs = True
-disallow_incomplete_defs = True
-no_implicit_optional = True
-warn_unused_ignores = True
-warn_unreachable = True
-show_error_context = True
-
-[mypy-rich.*,bs4,keyring]
-ignore_missing_imports = True

pyproject.toml

@@ -1,3 +1,42 @@
 [build-system]
 requires = ["setuptools", "wheel"]
 build-backend = "setuptools.build_meta"
+
+[project]
+name = "PFERD"
+dependencies = [
+  "aiohttp>=3.8.1",
+  "beautifulsoup4>=4.10.0",
+  "rich>=11.0.0",
+  "keyring>=23.5.0",
+  "certifi>=2021.10.8"
+]
+dynamic = ["version"]
+requires-python = ">=3.9"
+
+[project.scripts]
+pferd = "PFERD.__main__:main"
+
+[tool.setuptools.dynamic]
+version = {attr = "PFERD.version.VERSION"}
+
+[tool.flake8]
+max-line-length = 110
+
+[tool.isort]
+line_length = 110
+
+[tool.autopep8]
+max_line_length = 110
+in-place = true
+recursive = true
+
+[tool.mypy]
+disallow_any_generics = true
+disallow_untyped_defs = true
+disallow_incomplete_defs = true
+no_implicit_optional = true
+warn_unused_ignores = true
+warn_unreachable = true
+show_error_context = true
+ignore_missing_imports = true

scripts/bump-version

@@ -1,8 +1,8 @@
 #!/usr/bin/env python3
 
 import argparse
-import time
 import re
+import time
 from subprocess import run
 
 

scripts/check

@@ -2,5 +2,5 @@
 
 set -e
 
-mypy PFERD
+mypy .
 flake8 PFERD

scripts/format

@@ -2,5 +2,5 @@
 
 set -e
 
-autopep8 --recursive --in-place PFERD
-isort PFERD
+autopep8 .
+isort .

scripts/setup

@@ -13,5 +13,5 @@ pip install --upgrade setuptools
 pip install --editable .
 
 # Installing tools and type hints
-pip install --upgrade mypy flake8 autopep8 isort pyinstaller
+pip install --upgrade mypy flake8 flake8-pyproject autopep8 isort pyinstaller
 pip install --upgrade types-chardet types-certifi

setup.cfg

@@ -1,23 +0,0 @@
-[metadata]
-name = PFERD
-version = attr: PFERD.version.VERSION
-
-[options]
-packages = find:
-python_requires = >=3.9
-install_requires =
-  aiohttp>=3.8.1
-  beautifulsoup4>=4.10.0
-  rich>=11.0.0
-  keyring>=23.5.0
-  certifi>=2021.10.8
-
-[options.entry_points]
-console_scripts =
-  pferd = PFERD.__main__:main
-
-[flake8]
-max_line_length = 110
-
-[isort]
-line_length = 110