Fix video name deduplication

If set to `no`, PFERD won't print status or report messages for not deleted files

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

@@ -14,12 +14,12 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest, windows-latest, macos-latest]
-        python: ["3.8"]
+        python: ["3.9"]
     steps:
 
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
 
-      - uses: actions/setup-python@v2
+      - uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python }}
 
@@ -45,7 +45,7 @@ jobs:
         run: mv dist/pferd* dist/pferd-${{ matrix.os }}
 
       - name: Upload binary
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: Binaries
           path: dist/pferd-${{ matrix.os }}
@@ -57,7 +57,7 @@ jobs:
     steps:
 
       - name: Download binaries
-        uses: actions/download-artifact@v2
+        uses: actions/download-artifact@v3
         with:
           name: Binaries
 

.gitignore

@@ -3,6 +3,7 @@
 /PFERD.egg-info/
 __pycache__/
 /.vscode/
+/.idea/
 
 # pyinstaller
 /pferd.spec

CHANGELOG.md

@@ -22,6 +22,164 @@ ambiguous situations.
 
 ## Unreleased
 
+### Fixed
+- Video name deduplication
+
+## 3.5.0 - 2023-09-13
+
+### Added
+- `no-delete-prompt-override` conflict resolution strategy
+- Support for ILIAS learning modules
+- `show_not_deleted` option to stop printing the "Not Deleted" status or report
+  message. This combines nicely with the `no-delete-prompt-override` strategy,
+  causing PFERD to mostly ignore local-only files.
+- Support for mediacast video listings
+- Crawling of files in info tab
+
+### Changed
+- Remove size suffix for files in content pages
+
+### Fixed
+- Crawling of courses with the timeline view as the default tab
+- Crawling of file and custom opencast cards
+- Crawling of button cards without descriptions
+- Abort crawling when encountering an unexpected ilias root page redirect
+- Sanitize ascii control characters on Windows
+- Crawling of paginated past meetings
+- Ignore SCORM learning modules
+
+## 3.4.3 - 2022-11-29
+
+### Added
+- Missing documentation for `forums` option
+
+### Changed
+- Clear up error message shown when multiple paths are found to an element
+
+### Fixed
+- IPD crawler unnecessarily appending trailing slashes
+- Crawling opencast when ILIAS is set to English
+
+## 3.4.2 - 2022-10-26
+
+### Added
+- Recognize and crawl content pages in cards
+- Recognize and ignore surveys
+
+### Fixed
+- Forum crawling crashing when a thread has no messages at all
+- Forum crawling crashing when a forum has no threads at all
+- Ilias login failing in some cases
+- Crawling of paginated future meetings
+- IPD crawler handling of URLs without trailing slash
+
+## 3.4.1 - 2022-08-17
+
+### Added
+- Download of page descriptions
+- Forum download support
+- `pass` authenticator
+
+### Changed
+- Add `cpp` extension to default `link_regex` of IPD crawler
+- Mention hrefs in IPD crawler's `--explain` output for users of `link_regex` option
+- Simplify default IPD crawler `link_regex`
+
+### Fixed
+- IPD crawler crashes on some sites
+- Meeting name normalization for yesterday, today and tomorrow
+- Crawling of meeting file previews
+- Login with new login button html layout
+- Descriptions for courses are now placed in the correct subfolder when
+  downloading the whole desktop
+
+## 3.4.0 - 2022-05-01
+
+### Added
+- Message when Shibboleth entitlements need to be manually reviewed
+- Links to unofficial packages and repology in the readme
+
+### Changed
+- Increase minimum supported Python version to 3.9
+- Support video listings with more columns
+- Use UTF-8 when reading/writing the config file
+
+### Fixed
+- Crash during authentication when the Shibboleth session is still valid
+
+## 3.3.1 - 2022-01-15
+
+### Fixed
+- ILIAS login
+- Local video cache if `windows_paths` is enabled
+
+## 3.3.0 - 2022-01-09
+
+### Added
+- A KIT IPD crawler
+- Support for ILIAS cards
+- (Rudimentary) support for content pages
+- Support for multi-stream videos
+- Support for ILIAS 7
+
+### Removed
+- [Interpolation](https://docs.python.org/3/library/configparser.html#interpolation-of-values) in config file
+
+### Fixed
+- Crawling of recursive courses
+- Crawling files directly placed on the personal desktop
+- Ignore timestamps at the unix epoch as they crash on windows
+
+## 3.2.0 - 2021-08-04
+
+### Added
+- `--skip` command line option
+- Support for ILIAS booking objects
+
+### Changed
+- Using multiple path segments on left side of `-name->` now results in an
+  error. This was already forbidden by the documentation but silently accepted
+  by PFERD.
+- More consistent path printing in some `--explain` messages
+
+### Fixed
+- Nondeterministic name deduplication due to ILIAS reordering elements
+- More exceptions are handled properly
+
+## 3.1.0 - 2021-06-13
+
+If your config file doesn't do weird things with transforms, it should continue
+to work. If your `-re->` arrows behave weirdly, try replacing them with
+`-exact-re->` arrows. If you're on Windows, you might need to switch from `\`
+path separators to `/` in your regex rules.
+
+### Added
+- `skip` option for crawlers
+- Rules with `>>` instead of `>` as arrow head
+- `-exact-re->` arrow (behaves like `-re->` did previously)
+
+### Changed
+- The `-re->` arrow can now rename directories (like `-->`)
+- Use `/` instead of `\` as path separator for (regex) rules on Windows
+- Use the label to the left for exercises instead of the button name to
+  determine the folder name
+
+### Fixed
+- Video pagination handling in ILIAS crawler
+
+## 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

@@ -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] ([basic interpolation][2] is
+format, see the [configparser documentation][1] ([interpolation][2] is
-enabled).
+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#configparser.BasicInterpolation> "BasicInterpolation"
+[2]: <https://docs.python.org/3/library/configparser.html#interpolation-of-values> "Interpolation of values"
 
 ## The `DEFAULT` section
 
@@ -26,6 +26,9 @@ default values for the other sections.
   `Added ...`) while running a crawler. (Default: `yes`)
 - `report`: Whether PFERD should print a report of added, changed and deleted
    local files for all crawlers before exiting. (Default: `yes`)
+- `show_not_deleted`: Whether PFERD should print messages in status and report
+   when a local-only file wasn't deleted. Combines nicely with the
+   `no-delete-prompt-override` conflict resolution strategy.
 - `share_cookies`: Whether crawlers should share cookies where applicable. For
   example, some crawlers share cookies if they crawl the same website using the
   same account. (Default: `yes`)
@@ -36,7 +39,7 @@ Sections whose names start with `crawl:` are used to configure crawlers. The
 rest of the section name specifies the name of the crawler.
 
 A crawler synchronizes a remote resource to a local directory. There are
-different types of crawlers for different kinds of resources, e. g. ILIAS
+different types of crawlers for different kinds of resources, e.g. ILIAS
 courses or lecture websites.
 
 Each crawl section represents an instance of a specific type of crawler. The
@@ -49,8 +52,11 @@ see the type's [documentation](#crawler-types) below. The following options are
 common to all crawlers:
 
 - `type`: The available types are specified in [this section](#crawler-types).
+- `skip`: Whether the crawler should be skipped during normal execution. The
+  crawler can still be executed manually using the `--crawler` or `-C` flags.
+  (Default: `no`)
 - `output_dir`: The directory the crawler synchronizes files to. A crawler will
-  never place any files outside of this directory. (Default: the crawler's name)
+  never place any files outside this directory. (Default: the crawler's name)
 - `redownload`: When to download a file that is already present locally.
   (Default: `never-smart`)
     - `never`: If a file is present locally, it is not downloaded again.
@@ -72,6 +78,9 @@ common to all crawlers:
       using `prompt` and always choosing "yes".
     - `no-delete`: Never delete local files, but overwrite local files if the
       remote file is different.
+    - `no-delete-prompt-overwrite`: Never delete local files, but prompt to
+      overwrite local files if the remote file is different. Combines nicely
+      with the `show_not_deleted` option.
 - `transform`: Rules for renaming and excluding certain files and directories.
   For more details, see [this section](#transformation-rules). (Default: empty)
 - `tasks`: The maximum number of concurrent tasks (such as crawling or
@@ -133,6 +142,18 @@ crawler simulate a slower, network-based crawler.
   requests. (Default: `0.0`)
 - `download_speed`: Download speed (in bytes per second) to simulate. (Optional)
 
+### The `kit-ipd` 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
+requests is likely a good idea.
+
+- `target`: URL to a KIT-IPD page
+- `link_regex`: A regex that is matched against the `href` part of links. If it
+  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 `kit-ilias-web` crawler
 
 This crawler crawls the KIT ILIAS instance.
@@ -166,6 +187,7 @@ script once per day should be fine.
   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`)
 
@@ -180,6 +202,22 @@ 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.
+
+- `path`: Path to the credential file. (Required)
+
+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
@@ -192,6 +230,23 @@ is stored in the keyring.
 - `keyring_name`: The service name PFERD uses for storing credentials. (Default:
   `PFERD`)
 
+### 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.
+
+- `passname`: The name of the password to use (Required)
+- `username_prefixes`: A comma-separated list of username line prefixes
+  (Default: `login,username,user`)
+- `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"
+
 ### The `tfa` authenticator
 
 This authenticator prompts the user on the console for a two-factor
@@ -203,63 +258,94 @@ This authenticator does not support usernames.
 Transformation rules are rules for renaming and excluding files and directories.
 They are specified line-by-line in a crawler's `transform` option. When a
 crawler needs to apply a rule to a path, it goes through this list top-to-bottom
-and choose the first matching rule.
+and applies the first matching rule.
 
 To see this process in action, you can use the `--debug-transforms` or flag or
 the `--explain` flag.
 
-Each line has the format `SOURCE ARROW TARGET` where `TARGET` is optional.
+Each rule has the format `SOURCE ARROW TARGET` (e. g. `foo/bar --> foo/baz`).
-`SOURCE` is either a normal path without spaces (e. g. `foo/bar`), or a string
+The arrow specifies how the source and target are interpreted. The different
-literal delimited by `"` or `'` (e. g. `"foo\" bar/baz"`). Python's string
+kinds of arrows are documented below.
-escape syntax is supported. Trailing slashes are ignored. `TARGET` can be
-formatted like `SOURCE`, but it can also be a single exclamation mark without
-quotes (`!`). `ARROW` is one of `-->`, `-name->`, `-exact->`, `-re->` and
-`-name-re->`
 
-If a rule's target is `!`, this means that when the rule matches on a path, the
+`SOURCE` and `TARGET` are either a bunch of characters without spaces (e. g.
-corresponding file or directory is ignored. If a rule's target is missing, the
+`foo/bar`) or string literals (e. g, `"foo/b a r"`). The former syntax has no
-path is matched but not modified.
+concept of escaping characters, so the backslash is just another character. The
+string literals however support Python's escape syntax (e. g.
+`"foo\\bar\tbaz"`). This also means that in string literals, backslashes must be
+escaped.
+
+`TARGET` can additionally be a single exclamation mark `!` (*not* `"!"`). When a
+rule with a `!` as target matches a path, the corresponding file or directory is
+ignored by the crawler instead of renamed.
+
+`TARGET` can also be omitted entirely. When a rule without target matches a
+path, the path is returned unmodified. This is useful to prevent rules further
+down from matching instead.
+
+Each arrow's behaviour can be modified slightly by changing the arrow's head
+from `>` to `>>`. When a rule with a `>>` arrow head matches a path, it doesn't
+return immediately like a normal arrow. Instead, it replaces the current path
+with its output and continues on to the next rule. In effect, this means that
+multiple rules can be applied sequentially.
 
 ### The `-->` arrow
 
-The `-->` arrow is a basic renaming operation. If a path begins with `SOURCE`,
+The `-->` arrow is a basic renaming operation for files and directories. If a
-that part of the path is replaced with `TARGET`. This means that the rule
+path matches `SOURCE`, it is renamed to `TARGET`.
-`foo/bar --> baz` would convert `foo/bar` into `baz`, but also `foo/bar/xyz`
+
-into `baz/xyz`. The rule `foo --> !` would ignore a directory named `foo` as
+Example: `foo/bar --> baz`
-well as all its contents.
+- Doesn't match `foo`, `a/foo/bar` or `foo/baz`
+- Converts `foo/bar` into `baz`
+- Converts `foo/bar/wargl` into `baz/wargl`
+
+Example: `foo/bar --> !`
+- Doesn't match `foo`, `a/foo/bar` or `foo/baz`
+- Ignores `foo/bar` and any of its children
 
 ### The `-name->` arrow
 
 The `-name->` arrow lets you rename files and directories by their name,
 regardless of where they appear in the file tree. Because of this, its `SOURCE`
 must not contain multiple path segments, only a single name. This restriction
-does not apply to its `TARGET`. The `-name->` arrow is not applied recursively
+does not apply to its `TARGET`.
-to its own output to prevent infinite loops.
 
-For example, the rule `foo -name-> bar/baz` would convert `a/foo` into
+Example: `foo -name-> bar/baz`
-`a/bar/baz` and `a/foo/b/c/foo` into `a/bar/baz/b/c/bar/baz`. The rule `foo
+- Doesn't match `a/foobar/b` or `x/Foo/y/z`
--name-> !` would ignore all directories and files named `foo`.
+- Converts `hello/foo` into `hello/bar/baz`
+- Converts `foo/world` into `bar/baz/world`
+- Converts `a/foo/b/c/foo` into `a/bar/baz/b/c/bar/baz`
+
+Example: `foo -name-> !`
+- Doesn't match `a/foobar/b` or `x/Foo/y/z`
+- Ignores any path containing a segment `foo`
 
 ### The `-exact->` arrow
 
-The `-exact->` arrow requires the path to match `SOURCE` exactly. This means
+The `-exact->` arrow requires the path to match `SOURCE` exactly. The examples
-that the rule `foo/bar -exact-> baz` would still convert `foo/bar` into `baz`,
+below show why this is useful.
-but `foo/bar/xyz` would be unaffected. Also, `foo -exact-> !` would only ignore
+
-`foo`, but not its contents (if it has any). The examples below show why this is
+Example: `foo/bar -exact-> baz`
-useful.
+- Doesn't match `foo`, `a/foo/bar` or `foo/baz`
+- Converts `foo/bar` into `baz`
+- Doesn't match `foo/bar/wargl`
+
+Example: `foo/bar -exact-> !`
+- Doesn't match `foo`, `a/foo/bar` or `foo/baz`
+- Ignores only `foo/bar`, not its children
 
 ### The `-re->` arrow
 
-The `-re->` arrow uses regular expressions. `SOURCE` is a regular expression
+The `-re->` arrow is like the `-->` arrow but with regular expressions. `SOURCE`
-that must match the entire path. If this is the case, then the capturing groups
+is a regular expression and `TARGET` an f-string based template. If a path
-are available in `TARGET` for formatting.
+matches `SOURCE`, the output path is created using `TARGET` as template.
+`SOURCE` is automatically anchored.
 
-`TARGET` uses Python's [format string syntax][3]. The *n*-th capturing group can
+`TARGET` uses Python's [format string syntax][6]. The *n*-th capturing group can
-be referred to as `{g<n>}` (e. g. `{g3}`). `{g0}` refers to the original path.
+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
+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}`). If a
-capturing group is not present (e. g. when matching the string `cd` with the
+capturing group is not present (e.g. when matching the string `cd` with the
 regex `(ab)?cd`), the corresponding variables are not defined.
 
 Python's format string syntax has rich options for formatting its arguments. For
@@ -269,18 +355,37 @@ can use `{i3:05}`.
 PFERD even allows you to write entire expressions inside the curly braces, for
 example `{g2.lower()}` or `{g3.replace(' ', '_')}`.
 
-[3]: <https://docs.python.org/3/library/string.html#format-string-syntax> "Format String Syntax"
+Example: `f(oo+)/be?ar -re-> B{g1.upper()}H/fear`
+- Doesn't match `a/foo/bar`, `foo/abc/bar`, `afoo/bar` or `foo/bars`
+- Converts `foo/bar` into `BOOH/fear`
+- Converts `fooooo/bear` into `BOOOOOH/fear`
+- Converts `foo/bar/baz` into `BOOH/fear/baz`
+
+[6]: <https://docs.python.org/3/library/string.html#format-string-syntax> "Format String Syntax"
 
 ### The `-name-re->` arrow
 
 The `-name-re>` arrow is like a combination of the `-name->` and `-re->` arrows.
-Instead of the `SOURCE` being the name of a directory or file, it's a regex that
-is matched against the names of directories and files. `TARGET` works like the
-`-re->` arrow's target.
 
-For example, the arrow `(.*)\.jpeg -name-re-> {g1}.jpg` will rename all `.jpeg`
+Example: `(.*)\.jpeg -name-re-> {g1}.jpg`
-extensions into `.jpg`. The arrow `\..+ -name-re-> !` will ignore all files and
+- Doesn't match `foo/bar.png`, `baz.JPEG` or `hello,jpeg`
-directories starting with `.`.
+- Converts `foo/bar.jpeg` into `foo/bar.jpg`
+- Converts `foo.jpeg/bar/baz.jpeg` into `foo.jpg/bar/baz.jpg`
+
+Example: `\..+ -name-re-> !`
+- Doesn't match `.`, `test`, `a.b`
+- Ignores all files and directories starting with `.`.
+
+### The `-exact-re->` arrow
+
+The `-exact-re>` arrow is like a combination of the `-exact->` and `-re->`
+arrows.
+
+Example: `f(oo+)/be?ar -exactre-> B{g1.upper()}H/fear`
+- Doesn't match `a/foo/bar`, `foo/abc/bar`, `afoo/bar` or `foo/bars`
+- Converts `foo/bar` into `BOOH/fear`
+- Converts `fooooo/bear` into `BOOOOOH/fear`
+- Doesn't match `foo/bar/baz`
 
 ### Example: Tutorials
 
@@ -307,8 +412,7 @@ tutorials --> !
 The second rule is required for many crawlers since they use the rules to decide
 which directories to crawl. If it was missing when the crawler looks at
 `tutorials/`, the third rule would match. This means the crawler would not crawl
-the `tutorials/` directory and thus not discover that `tutorials/tut02/`
+the `tutorials/` directory and thus not discover that `tutorials/tut02/` exists.
-existed.
 
 Since the second rule is only relevant for crawling, the `TARGET` is left out.
 
@@ -333,9 +437,9 @@ To do this, you can use the most powerful of arrows: The regex arrow.
 
 Note the escaped backslashes on the `SOURCE` side.
 
-### Example: Crawl a python project
+### Example: Crawl a Python project
 
-You are crawling a python project and want to ignore all hidden files (files
+You are crawling a Python project and want to ignore all hidden files (files
 whose name starts with a `.`), all `__pycache__` directories and all markdown
 files (for some weird reason).
 
@@ -355,11 +459,21 @@ README.md
 ...
 ```
 
-For this task, the name arrows can be used. They are variants of the normal
+For this task, the name arrows can be used.
-arrows that only look at the file name instead of the entire path.
 
 ```
 \..*        -name-re-> !
 __pycache__ -name->    !
 .*\.md      -name-re-> !
 ```
+
+### Example: Clean up names
+
+You want to convert all paths into lowercase and replace spaces with underscores
+before applying any rules. This can be achieved using the `>>` arrow heads.
+
+```
+(.*) -re->> "{g1.lower().replace(' ', '_')}"
+
+<other rules go here>
+```

LICENSE

@@ -1,4 +1,6 @@
-Copyright 2019-2020 Garmelon, I-Al-Istannen, danstooamerican, pavelzw, TheChristophe, Scriptim
+Copyright 2019-2021 Garmelon, I-Al-Istannen, danstooamerican, pavelzw,
+                    TheChristophe, Scriptim, thelukasprobst, Toorero,
+                    Mr-Pine
 
 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/__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
@@ -14,7 +15,7 @@ from .transformer import RuleParseError
 
 def load_config_parser(args: argparse.Namespace) -> configparser.ConfigParser:
     log.explain_topic("Loading config")
-    parser = configparser.ConfigParser()
+    parser = configparser.ConfigParser(interpolation=None)
 
     if args.command is None:
         log.explain("No CLI command specified, loading config from file")
@@ -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:
@@ -43,6 +47,8 @@ def configure_logging_from_args(args: argparse.Namespace) -> None:
         log.output_explain = args.explain
     if args.status is not None:
         log.output_status = args.status
+    if args.show_not_deleted is not None:
+        log.output_not_deleted = args.show_not_deleted
     if args.report is not None:
         log.output_report = args.report
 
@@ -68,6 +74,8 @@ def configure_logging_from_config(args: argparse.Namespace, config: Config) -> N
             log.output_status = config.default_section.status()
         if args.report is None:
             log.output_report = config.default_section.report()
+        if args.show_not_deleted is None:
+            log.output_not_deleted = config.default_section.show_not_deleted()
     except ConfigOptionError as e:
         log.error(str(e))
         sys.exit(1)
@@ -112,7 +120,7 @@ def main() -> None:
         sys.exit()
 
     try:
-        pferd = Pferd(config, args.crawler)
+        pferd = Pferd(config, args.crawler, args.skip)
     except PferdLoadError as e:
         log.unlock()
         log.error(str(e))
@@ -131,7 +139,7 @@ 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)
@@ -143,7 +151,6 @@ def main() -> None:
         log.unlock()
         log.explain_topic("Interrupted, exiting immediately")
         log.explain("Open files and connections are left for the OS to clean up")
-        log.explain("Temporary files are not cleaned up")
         pferd.print_report()
         # TODO Clean up tmp files
         # And when those files *do* actually get cleaned up properly,
@@ -156,3 +163,7 @@ def main() -> None:
         sys.exit(1)
     else:
         pferd.print_report()
+
+
+if __name__ == "__main__":
+    main()

PFERD/auth/__init__.py

@@ -2,8 +2,10 @@ 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 .pass_ import PassAuthenticator, PassAuthSection
 from .simple import SimpleAuthenticator, SimpleAuthSection
 from .tfa import TfaAuthenticator
 
@@ -14,10 +16,14 @@ 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)),
+    "pass": lambda n, s, c:
+        PassAuthenticator(n, PassAuthSection(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

@@ -13,14 +13,15 @@ class AuthError(Exception):
 
 
 class AuthSection(Section):
-    pass
+    def type(self) -> str:
+        value = self.s.get("type")
+        if value is None:
+            self.missing_value("type")
+        return value
 
 
 class Authenticator(ABC):
-    def __init__(
+    def __init__(self, name: str) -> None:
-            self,
-            name: str
-    ) -> None:
         """
         Initialize an authenticator from its name and its section in the config
         file.

PFERD/auth/credential_file.py

@@ -0,0 +1,46 @@
+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, encoding="utf-8") as f:
+                lines = list(f)
+        except UnicodeDecodeError:
+            raise AuthLoadError(f"Credential file at {fmt_real_path(path)} is not encoded using UTF-8")
+        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__(
+    def __init__(self, name: str, section: KeyringAuthSection) -> None:
-            self,
-            name: str,
-            section: KeyringAuthSection,
-    ) -> None:
         super().__init__(name)
 
         self._username = section.username()

PFERD/auth/pass_.py

@@ -0,0 +1,98 @@
+import re
+import subprocess
+from typing import List, Tuple
+
+from ..logging import log
+from .authenticator import Authenticator, AuthError, AuthSection
+
+
+class PassAuthSection(AuthSection):
+    def passname(self) -> str:
+        if (value := self.s.get("passname")) is None:
+            self.missing_value("passname")
+        return value
+
+    def username_prefixes(self) -> List[str]:
+        value = self.s.get("username_prefixes", "login,username,user")
+        return [prefix.lower() for prefix in value.split(",")]
+
+    def password_prefixes(self) -> List[str]:
+        value = self.s.get("password_prefixes", "password,pass,secret")
+        return [prefix.lower() for prefix in value.split(",")]
+
+
+class PassAuthenticator(Authenticator):
+    PREFIXED_LINE_RE = r"([a-zA-Z]+):\s?(.*)"  # to be used with fullmatch
+
+    def __init__(self, name: str, section: PassAuthSection) -> None:
+        super().__init__(name)
+
+        self._passname = section.passname()
+        self._username_prefixes = section.username_prefixes()
+        self._password_prefixes = section.password_prefixes()
+
+    async def credentials(self) -> Tuple[str, str]:
+        log.explain_topic("Obtaining credentials from pass")
+
+        try:
+            log.explain(f"Calling 'pass show {self._passname}'")
+            result = subprocess.check_output(["pass", "show", self._passname], text=True)
+        except subprocess.CalledProcessError as e:
+            raise AuthError(f"Failed to get password info from {self._passname}: {e}")
+
+        prefixed = {}
+        unprefixed = []
+        for line in result.strip().splitlines():
+            if match := re.fullmatch(self.PREFIXED_LINE_RE, line):
+                prefix = match.group(1).lower()
+                value = match.group(2)
+                log.explain(f"Found prefixed line {line!r} with prefix {prefix!r}, value {value!r}")
+                if prefix in prefixed:
+                    raise AuthError(f"Prefix {prefix} specified multiple times")
+                prefixed[prefix] = value
+            else:
+                log.explain(f"Found unprefixed line {line!r}")
+                unprefixed.append(line)
+
+        username = None
+        for prefix in self._username_prefixes:
+            log.explain(f"Looking for username at prefix {prefix!r}")
+            if prefix in prefixed:
+                username = prefixed[prefix]
+                log.explain(f"Found username {username!r}")
+                break
+
+        password = None
+        for prefix in self._password_prefixes:
+            log.explain(f"Looking for password at prefix {prefix!r}")
+            if prefix in prefixed:
+                password = prefixed[prefix]
+                log.explain(f"Found password {password!r}")
+                break
+
+        if password is None and username is None:
+            log.explain("No username and password found so far")
+            log.explain("Using first unprefixed line as password")
+            log.explain("Using second unprefixed line as username")
+        elif password is None:
+            log.explain("No password found so far")
+            log.explain("Using first unprefixed line as password")
+        elif username is None:
+            log.explain("No username found so far")
+            log.explain("Using first unprefixed line as username")
+
+        if password is None:
+            if not unprefixed:
+                log.explain("Not enough unprefixed lines left")
+                raise AuthError("Password could not be determined")
+            password = unprefixed.pop(0)
+            log.explain(f"Found password {password!r}")
+
+        if username is None:
+            if not unprefixed:
+                log.explain("Not enough unprefixed lines left")
+                raise AuthError("Username could not be determined")
+            username = unprefixed.pop(0)
+            log.explain(f"Found username {username!r}")
+
+        return username, password

PFERD/auth/simple.py

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

PFERD/cli/__init__.py

@@ -1,11 +1,13 @@
 # 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 . 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_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),
@@ -55,6 +62,11 @@ GROUP.add_argument(
     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,
@@ -83,16 +95,26 @@ def load(
         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"]
-    auth_section["type"] = "simple"
+    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/command_kit_ipd.py

@@ -0,0 +1,54 @@
+import argparse
+import configparser
+from pathlib import Path
+
+from ..logging import log
+from .parser import CRAWLER_PARSER, SUBPARSERS, load_crawler
+
+SUBPARSER = SUBPARSERS.add_parser(
+    "kit-ipd",
+    parents=[CRAWLER_PARSER],
+)
+
+GROUP = SUBPARSER.add_argument_group(
+    title="kit ipd crawler arguments",
+    description="arguments for the 'kit-ipd' crawler",
+)
+GROUP.add_argument(
+    "--link-regex",
+    type=str,
+    metavar="REGEX",
+    help="href-matching regex to identify downloadable files"
+)
+GROUP.add_argument(
+    "target",
+    type=str,
+    metavar="TARGET",
+    help="url to crawl"
+)
+GROUP.add_argument(
+    "output",
+    type=Path,
+    metavar="OUTPUT",
+    help="output directory"
+)
+
+
+def load(
+        args: argparse.Namespace,
+        parser: configparser.ConfigParser,
+) -> None:
+    log.explain("Creating config for command 'kit-ipd'")
+
+    parser["crawl:kit-ipd"] = {}
+    section = parser["crawl:kit-ipd"]
+    load_crawler(args, section)
+
+    section["type"] = "kit-ipd"
+    section["target"] = str(args.target)
+    section["output_dir"] = str(args.output)
+    if args.link_regex:
+        section["link_regex"] = str(args.link_regex)
+
+
+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__(
@@ -177,6 +181,14 @@ PARSER.add_argument(
     help="only execute a single crawler."
     " Can be specified multiple times to execute multiple crawlers"
 )
+PARSER.add_argument(
+    "--skip", "-S",
+    action="append",
+    type=str,
+    metavar="NAME",
+    help="don't execute this particular crawler."
+    " Can be specified multiple times to skip multiple crawlers"
+)
 PARSER.add_argument(
     "--working-dir",
     type=Path,
@@ -203,6 +215,11 @@ PARSER.add_argument(
     action=BooleanOptionalAction,
     help="whether crawlers should share cookies where applicable"
 )
+PARSER.add_argument(
+    "--show-not-deleted",
+    action=BooleanOptionalAction,
+    help="print messages in status and report when PFERD did not delete a local only file"
+)
 
 
 def load_default_section(
@@ -221,6 +238,8 @@ def load_default_section(
         section["report"] = "yes" if args.report else "no"
     if args.share_cookies is not None:
         section["share_cookies"] = "yes" if args.share_cookies else "no"
+    if args.show_not_deleted is not None:
+        section["show_not_deleted"] = "yes" if args.show_not_deleted else "no"
 
 
 SUBPARSERS = PARSER.add_subparsers(title="crawlers")

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()
 
@@ -81,6 +82,9 @@ class DefaultSection(Section):
     def report(self) -> bool:
         return self.s.getboolean("report", fallback=True)
 
+    def show_not_deleted(self) -> bool:
+        return self.s.getboolean("show_not_deleted", fallback=True)
+
     def share_cookies(self) -> bool:
         return self.s.getboolean("share_cookies", fallback=True)
 
@@ -119,7 +123,7 @@ class Config:
         # Using config.read_file instead of config.read because config.read
         # would just ignore a missing file and carry on.
         try:
-            with open(path) as f:
+            with open(path, encoding="utf-8") as f:
                 parser.read_file(f, source=str(path))
         except FileNotFoundError:
             raise ConfigLoadError(path, "File does not exist")
@@ -127,6 +131,8 @@ class Config:
             raise ConfigLoadError(path, "That's a directory, not a file")
         except PermissionError:
             raise ConfigLoadError(path, "Insufficient permissions")
+        except UnicodeDecodeError:
+            raise ConfigLoadError(path, "File is not encoded using UTF-8")
 
     def dump(self, path: Optional[Path] = None) -> None:
         """
@@ -153,12 +159,12 @@ class Config:
             try:
                 # x = open for exclusive creation, failing if the file already
                 # exists
-                with open(path, "x") as f:
+                with open(path, "x", encoding="utf-8") as f:
                     self._parser.write(f)
             except FileExistsError:
                 print("That file already exists.")
                 if asyncio.run(prompt_yes_no("Overwrite it?", default=False)):
-                    with open(path, "w") as f:
+                    with open(path, "w", encoding="utf-8") as f:
                         self._parser.write(f)
                 else:
                     raise ConfigDumpError(path, "File already exists")

PFERD/crawl/__init__.py

@@ -3,8 +3,9 @@ from typing import Callable, Dict
 
 from ..auth import Authenticator
 from ..config import Config
-from .crawler import Crawler, CrawlError  # noqa: F401
+from .crawler import Crawler, CrawlError, CrawlerSection  # noqa: F401
 from .ilias import KitIliasWebCrawler, KitIliasWebCrawlerSection
+from .kit_ipd_crawler import KitIpdCrawler, KitIpdCrawlerSection
 from .local_crawler import LocalCrawler, LocalCrawlerSection
 
 CrawlerConstructor = Callable[[
@@ -19,4 +20,6 @@ CRAWLERS: Dict[str, CrawlerConstructor] = {
         LocalCrawler(n, LocalCrawlerSection(s), c),
     "kit-ilias-web": lambda n, s, c, a:
         KitIliasWebCrawler(n, KitIliasWebCrawlerSection(s), c, a),
+    "kit-ipd": lambda n, s, c, a:
+        KitIpdCrawler(n, KitIpdCrawlerSection(s), c),
 }

PFERD/crawl/crawler.py

@@ -1,9 +1,10 @@
 import asyncio
 import os
 from abc import ABC, abstractmethod
+from collections.abc import Awaitable, Coroutine
 from datetime import datetime
 from pathlib import Path, PurePath
-from typing import Any, Awaitable, Callable, Dict, List, Optional, Sequence, Set, Tuple, TypeVar
+from typing import Any, Callable, Dict, List, Optional, Sequence, Set, Tuple, TypeVar
 
 from ..auth import Authenticator
 from ..config import Config, Section
@@ -47,16 +48,18 @@ def noncritical(f: Wrapped) -> Wrapped:
         try:
             f(*args, **kwargs)
         except (CrawlWarning, OutputDirError, MarkDuplicateError, MarkConflictError) as e:
+            crawler.report.add_warning(str(e))
             log.warn(str(e))
             crawler.error_free = False
-        except:  # noqa: E722 do not use bare 'except'
+        except Exception as e:
             crawler.error_free = False
+            crawler.report.add_error(str(e))
             raise
 
     return wrapper  # type: ignore
 
 
-AWrapped = TypeVar("AWrapped", bound=Callable[..., Awaitable[None]])
+AWrapped = TypeVar("AWrapped", bound=Callable[..., Coroutine[Any, Any, Optional[Any]]])
 
 
 def anoncritical(f: AWrapped) -> AWrapped:
@@ -72,21 +75,25 @@ def anoncritical(f: AWrapped) -> AWrapped:
     Warning: Must only be applied to member functions of the Crawler class!
     """
 
-    async def wrapper(*args: Any, **kwargs: Any) -> None:
+    async def wrapper(*args: Any, **kwargs: Any) -> Optional[Any]:
         if not (args and isinstance(args[0], Crawler)):
             raise RuntimeError("@anoncritical must only applied to Crawler methods")
 
         crawler = args[0]
 
         try:
-            await f(*args, **kwargs)
+            return await f(*args, **kwargs)
         except (CrawlWarning, OutputDirError, MarkDuplicateError, MarkConflictError) as e:
             log.warn(str(e))
             crawler.error_free = False
-        except:  # noqa: E722 do not use bare 'except'
+            crawler.report.add_warning(str(e))
+        except Exception as e:
             crawler.error_free = False
+            crawler.report.add_error(str(e))
             raise
 
+        return None
+
     return wrapper  # type: ignore
 
 
@@ -132,6 +139,15 @@ class DownloadToken(ReusableAsyncContextManager[Tuple[ProgressBar, FileSink]]):
 
 
 class CrawlerSection(Section):
+    def type(self) -> str:
+        value = self.s.get("type")
+        if value is None:
+            self.missing_value("type")
+        return value
+
+    def skip(self) -> bool:
+        return self.s.getboolean("skip", fallback=False)
+
     def output_dir(self, name: str) -> Path:
         # TODO Use removeprefix() after switching to 3.9
         if name.startswith("crawl:"):
@@ -309,6 +325,7 @@ class Crawler(ABC):
             log.explain("Warnings or errors occurred during this run")
             log.explain("Answer: No")
 
+    @anoncritical
     async def run(self) -> None:
         """
         Start the crawling process. Call this function if you want to use a

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, encoding="utf-8") 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", encoding="utf-8") 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/file_templates.py

@@ -1,6 +1,10 @@
 from enum import Enum
 from typing import Optional
 
+import bs4
+
+from PFERD.utils import soupify
+
 _link_template_plain = "{{link}}"
 _link_template_fancy = """
 <!DOCTYPE html>
@@ -94,6 +98,71 @@ _link_template_internet_shortcut = """
 URL={{link}}
 """.strip()
 
+_learning_module_template = """
+<!DOCTYPE html>
+<html lang="en">
+    <head>
+        <meta charset="UTF-8">
+        <title>{{name}}</title>
+    </head>
+
+    <style>
+    * {
+        box-sizing: border-box;
+    }
+    .center-flex {
+        display: flex;
+        align-items: center;
+        justify-content: center;
+    }
+    .nav {
+        display: flex;
+        justify-content: space-between;
+    }
+    </style>
+    <body class="center-flex">
+{{body}}
+    </body>
+</html>
+"""
+
+
+def learning_module_template(body: bs4.Tag, name: str, prev: Optional[str], next: Optional[str]) -> str:
+    # Seems to be comments, ignore those.
+    for elem in body.select(".il-copg-mob-fullscreen-modal"):
+        elem.decompose()
+
+    nav_template = """
+        <div class="nav">
+            {{left}}
+            {{right}}
+        </div>
+    """
+    if prev and body.select_one(".ilc_page_lnav_LeftNavigation"):
+        text = body.select_one(".ilc_page_lnav_LeftNavigation").getText().strip()
+        left = f'<a href="{prev}">{text}</a>'
+    else:
+        left = "<span></span>"
+
+    if next and body.select_one(".ilc_page_rnav_RightNavigation"):
+        text = body.select_one(".ilc_page_rnav_RightNavigation").getText().strip()
+        right = f'<a href="{next}">{text}</a>'
+    else:
+        right = "<span></span>"
+
+    if top_nav := body.select_one(".ilc_page_tnav_TopNavigation"):
+        top_nav.replace_with(
+            soupify(nav_template.replace("{{left}}", left).replace("{{right}}", right).encode())
+        )
+
+    if bot_nav := body.select_one(".ilc_page_bnav_BottomNavigation"):
+        bot_nav.replace_with(soupify(nav_template.replace(
+            "{{left}}", left).replace("{{right}}", right).encode())
+        )
+
+    body = body.prettify()
+    return _learning_module_template.replace("{{body}}", body).replace("{{name}}", name)
+
 
 class Links(Enum):
     IGNORE = "ignore"
@@ -102,24 +171,24 @@ class Links(Enum):
     INTERNET_SHORTCUT = "internet-shortcut"
 
     def template(self) -> Optional[str]:
-        if self == self.FANCY:
+        if self == Links.FANCY:
             return _link_template_fancy
-        elif self == self.PLAINTEXT:
+        elif self == Links.PLAINTEXT:
             return _link_template_plain
-        elif self == self.INTERNET_SHORTCUT:
+        elif self == Links.INTERNET_SHORTCUT:
             return _link_template_internet_shortcut
-        elif self == self.IGNORE:
+        elif self == Links.IGNORE:
             return None
         raise ValueError("Missing switch case")
 
     def extension(self) -> Optional[str]:
-        if self == self.FANCY:
+        if self == Links.FANCY:
             return ".html"
-        elif self == self.PLAINTEXT:
+        elif self == Links.PLAINTEXT:
             return ".txt"
-        elif self == self.INTERNET_SHORTCUT:
+        elif self == Links.INTERNET_SHORTCUT:
             return ".url"
-        elif self == self.IGNORE:
+        elif self == Links.IGNORE:
             return None
         raise ValueError("Missing switch case")
 

PFERD/crawl/ilias/ilias_html_cleaner.py

@@ -0,0 +1,91 @@
+from bs4 import BeautifulSoup, Comment, Tag
+
+_STYLE_TAG_CONTENT = """
+    .ilc_text_block_Information {
+      background-color: #f5f7fa;
+    }
+    div.ilc_text_block_Standard {
+      margin-bottom: 10px;
+      margin-top: 10px;
+    }
+    span.ilc_text_inline_Strong {
+      font-weight: bold;
+    }
+
+    .accordion-head {
+      background-color: #f5f7fa;
+      padding: 0.5rem 0;
+    }
+
+    h3 {
+      margin-top: 0.5rem;
+      margin-bottom: 1rem;
+    }
+
+    br.visible-break {
+      margin-bottom: 1rem;
+    }
+
+    article {
+      margin: 0.5rem 0;
+    }
+
+    body {
+      padding: 1em;
+      grid-template-columns: 1fr min(60rem, 90%) 1fr;
+      line-height: 1.2;
+    }
+"""
+
+_ARTICLE_WORTHY_CLASSES = [
+    "ilc_text_block_Information",
+    "ilc_section_Attention",
+    "ilc_section_Link",
+]
+
+
+def insert_base_markup(soup: BeautifulSoup) -> BeautifulSoup:
+    head = soup.new_tag("head")
+    soup.insert(0, head)
+
+    simplecss_link: Tag = soup.new_tag("link")
+    # <link rel="stylesheet" href="https://cdn.simplecss.org/simple.css">
+    simplecss_link["rel"] = "stylesheet"
+    simplecss_link["href"] = "https://cdn.simplecss.org/simple.css"
+    head.append(simplecss_link)
+
+    # Basic style tags for compat
+    style: Tag = soup.new_tag("style")
+    style.append(_STYLE_TAG_CONTENT)
+    head.append(style)
+
+    return soup
+
+
+def clean(soup: BeautifulSoup) -> BeautifulSoup:
+    for block in soup.find_all(class_=lambda x: x in _ARTICLE_WORTHY_CLASSES):
+        block.name = "article"
+
+    for block in soup.find_all("h3"):
+        block.name = "div"
+
+    for block in soup.find_all("h1"):
+        block.name = "h3"
+
+    for block in soup.find_all(class_="ilc_va_ihcap_VAccordIHeadCap"):
+        block.name = "h3"
+        block["class"] += ["accordion-head"]
+
+    for dummy in soup.select(".ilc_text_block_Standard.ilc_Paragraph"):
+        children = list(dummy.children)
+        if not children:
+            dummy.decompose()
+        if len(children) > 1:
+            continue
+        if isinstance(type(children[0]), Comment):
+            dummy.decompose()
+
+    for hrule_imposter in soup.find_all(class_="ilc_section_Separator"):
+        hrule_imposter.insert(0, soup.new_tag("hr"))
+
+    return soup

PFERD/crawl/kit_ipd_crawler.py

@@ -0,0 +1,170 @@
+import os
+import re
+from dataclasses import dataclass
+from pathlib import PurePath
+from typing import Awaitable, List, Optional, Pattern, Set, Tuple, Union
+from urllib.parse import urljoin
+
+from bs4 import BeautifulSoup, Tag
+
+from ..config import Config
+from ..logging import ProgressBar, log
+from ..output_dir import FileSink
+from ..utils import soupify
+from .crawler import CrawlError
+from .http_crawler import HttpCrawler, HttpCrawlerSection
+
+
+class KitIpdCrawlerSection(HttpCrawlerSection):
+    def target(self) -> str:
+        target = self.s.get("target")
+        if not target:
+            self.missing_value("target")
+
+        if not target.startswith("https://"):
+            self.invalid_value("target", target, "Should be a URL")
+
+        return target
+
+    def link_regex(self) -> Pattern[str]:
+        regex = self.s.get("link_regex", r"^.*?[^/]+\.(pdf|zip|c|cpp|java)$")
+        return re.compile(regex)
+
+
+@dataclass(unsafe_hash=True)
+class KitIpdFile:
+    name: str
+    url: str
+
+
+@dataclass
+class KitIpdFolder:
+    name: str
+    files: List[KitIpdFile]
+
+    def explain(self) -> None:
+        log.explain_topic(f"Folder {self.name!r}")
+        for file in self.files:
+            log.explain(f"File {file.name!r} (href={file.url!r})")
+
+    def __hash__(self) -> int:
+        return self.name.__hash__()
+
+
+class KitIpdCrawler(HttpCrawler):
+
+    def __init__(
+            self,
+            name: str,
+            section: KitIpdCrawlerSection,
+            config: Config,
+    ):
+        super().__init__(name, section, config)
+        self._url = section.target()
+        self._file_regex = section.link_regex()
+
+    async def _run(self) -> None:
+        maybe_cl = await self.crawl(PurePath("."))
+        if not maybe_cl:
+            return
+
+        tasks: List[Awaitable[None]] = []
+
+        async with maybe_cl:
+            for item in await self._fetch_items():
+                if isinstance(item, KitIpdFolder):
+                    tasks.append(self._crawl_folder(item))
+                else:
+                    # Orphan files are placed in the root folder
+                    tasks.append(self._download_file(PurePath("."), item))
+
+        await self.gather(tasks)
+
+    async def _crawl_folder(self, folder: KitIpdFolder) -> None:
+        path = PurePath(folder.name)
+        if not await self.crawl(path):
+            return
+
+        tasks = [self._download_file(path, file) for file in folder.files]
+
+        await self.gather(tasks)
+
+    async def _download_file(self, parent: PurePath, file: KitIpdFile) -> None:
+        element_path = parent / file.name
+        maybe_dl = await self.download(element_path)
+        if not maybe_dl:
+            return
+
+        async with maybe_dl as (bar, sink):
+            await self._stream_from_url(file.url, sink, bar)
+
+    async def _fetch_items(self) -> Set[Union[KitIpdFile, KitIpdFolder]]:
+        page, url = await self.get_page()
+        elements: List[Tag] = self._find_file_links(page)
+        items: Set[Union[KitIpdFile, KitIpdFolder]] = set()
+
+        for element in elements:
+            folder_label = self._find_folder_label(element)
+            if folder_label:
+                folder = self._extract_folder(folder_label, url)
+                if folder not in items:
+                    items.add(folder)
+                    folder.explain()
+            else:
+                file = self._extract_file(element, url)
+                items.add(file)
+                log.explain_topic(f"Orphan file {file.name!r} (href={file.url!r})")
+                log.explain("Attributing it to root folder")
+
+        return items
+
+    def _extract_folder(self, folder_tag: Tag, url: str) -> KitIpdFolder:
+        files: List[KitIpdFile] = []
+        name = folder_tag.getText().strip()
+
+        container: Tag = folder_tag.findNextSibling(name="table")
+        for link in self._find_file_links(container):
+            files.append(self._extract_file(link, url))
+
+        return KitIpdFolder(name, files)
+
+    @staticmethod
+    def _find_folder_label(file_link: Tag) -> Optional[Tag]:
+        enclosing_table: Tag = file_link.findParent(name="table")
+        if enclosing_table is None:
+            return None
+        return enclosing_table.findPreviousSibling(name=re.compile("^h[1-6]$"))
+
+    def _extract_file(self, link: Tag, url: str) -> KitIpdFile:
+        url = self._abs_url_from_link(url, link)
+        name = os.path.basename(url)
+        return KitIpdFile(name, url)
+
+    def _find_file_links(self, tag: Union[Tag, BeautifulSoup]) -> List[Tag]:
+        return tag.findAll(name="a", attrs={"href": self._file_regex})
+
+    def _abs_url_from_link(self, url: str, link_tag: Tag) -> str:
+        return urljoin(url, link_tag.get("href"))
+
+    async def _stream_from_url(self, url: str, sink: FileSink, bar: ProgressBar) -> None:
+        async with self.session.get(url, allow_redirects=False) as resp:
+            if resp.status == 403:
+                raise CrawlError("Received a 403. Are you within the KIT network/VPN?")
+            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()
+
+    async def get_page(self) -> Tuple[BeautifulSoup, str]:
+        async with self.session.get(self._url) as request:
+            # The web page for Algorithmen für Routenplanung contains some
+            # weird comments that beautifulsoup doesn't parse correctly. This
+            # hack enables those pages to be crawled, and should hopefully not
+            # cause issues on other pages.
+            content = (await request.read()).decode("utf-8")
+            content = re.sub(r"<!--.*?-->", "", content)
+            return soupify(content.encode("utf-8")), str(request.url)

PFERD/deduplicator.py

@@ -14,7 +14,7 @@ def name_variants(path: PurePath) -> Iterator[PurePath]:
 
 
 class Deduplicator:
-    FORBIDDEN_CHARS = '<>:"/\\|?*'
+    FORBIDDEN_CHARS = '<>:"/\\|?*' + "".join([chr(i) for i in range(0, 32)])
     FORBIDDEN_NAMES = {
         "CON", "PRN", "AUX", "NUL",
         "COM1", "COM2", "COM3", "COM4", "COM5", "COM6", "COM7", "COM8", "COM9",
@@ -56,6 +56,12 @@ class Deduplicator:
             log.explain(f"Changed path to {fmt_path(new_path)} for windows compatibility")
         return new_path
 
+    def fixup_path(self, path: PurePath) -> PurePath:
+        """Fixes up the path for windows, if enabled. Returns the path unchanged otherwise."""
+        if self._windows_paths:
+            return self._fixup_for_windows(path)
+        return path
+
     def mark(self, path: PurePath) -> PurePath:
         if self._windows_paths:
             path = self._fixup_for_windows(path)

PFERD/logging.py

@@ -5,7 +5,7 @@ from contextlib import asynccontextmanager, contextmanager
 # TODO In Python 3.9 and above, ContextManager is deprecated
 from typing import AsyncIterator, ContextManager, Iterator, List, Optional
 
-from rich.console import Console, RenderGroup
+from rich.console import Console, Group
 from rich.live import Live
 from rich.markup import escape
 from rich.panel import Panel
@@ -59,6 +59,7 @@ class Log:
         # Whether different parts of the output are enabled or disabled
         self.output_explain = False
         self.output_status = True
+        self.output_not_deleted = True
         self.output_report = True
 
     def _update_live(self) -> None:
@@ -68,7 +69,7 @@ class Log:
         if self._download_progress.task_ids:
             elements.append(self._download_progress)
 
-        group = RenderGroup(*elements)  # type: ignore
+        group = Group(*elements)
         self._live.update(group)
 
     @contextmanager
@@ -197,7 +198,7 @@ directly or as a GitHub issue: https://github.com/Garmelon/PFERD/issues/new
         if self.output_explain:
             self.print(f"  {escape(text)}")
 
-    def status(self, style: str, action: str, text: str) -> None:
+    def status(self, style: str, action: str, text: str, suffix: str = "") -> None:
         """
         Print a status update while crawling. Allows markup in the "style"
         argument which will be applied to the "action" string.
@@ -205,7 +206,18 @@ directly or as a GitHub issue: https://github.com/Garmelon/PFERD/issues/new
 
         if self.output_status:
             action = escape(f"{action:<{self.STATUS_WIDTH}}")
-            self.print(f"{style}{action}[/] {escape(text)}")
+            self.print(f"{style}{action}[/] {escape(text)} {suffix}")
+
+    def not_deleted(self, style: str, action: str, text: str, suffix: str = "") -> None:
+        """
+        Print a message for a local only file that wasn't
+        deleted while crawling. Allows markup in the "style"
+        argument which will be applied to the "action" string.
+        """
+
+        if self.output_status and self.output_not_deleted:
+            action = escape(f"{action:<{self.STATUS_WIDTH}}")
+            self.print(f"{style}{action}[/] {escape(text)} {suffix}")
 
     def report(self, text: str) -> None:
         """
@@ -215,6 +227,14 @@ directly or as a GitHub issue: https://github.com/Garmelon/PFERD/issues/new
         if self.output_report:
             self.print(text)
 
+    def report_not_deleted(self, text: str) -> None:
+        """
+        Print a report for a local only file that wasn't deleted after crawling. Allows markup.
+        """
+
+        if self.output_report and self.output_not_deleted:
+            self.print(text)
+
     @contextmanager
     def _bar(
             self,

PFERD/output_dir.py

@@ -44,6 +44,7 @@ class OnConflict(Enum):
     LOCAL_FIRST = "local-first"
     REMOTE_FIRST = "remote-first"
     NO_DELETE = "no-delete"
+    NO_DELETE_PROMPT_OVERWRITE = "no-delete-prompt-overwrite"
 
     @staticmethod
     def from_string(string: str) -> "OnConflict":
@@ -51,7 +52,7 @@ class OnConflict(Enum):
             return OnConflict(string)
         except ValueError:
             raise ValueError("must be one of 'prompt', 'local-first',"
-                             " 'remote-first', 'no-delete'")
+                             " 'remote-first', 'no-delete', 'no-delete-prompt-overwrite'")
 
 
 @dataclass
@@ -231,7 +232,10 @@ class OutputDirectory:
         stat = local_path.stat()
 
         remote_newer = None
-        if mtime := heuristics.mtime:
+
+        # Python on Windows crashes when faced with timestamps around the unix epoch
+        if heuristics.mtime and (os.name != "nt" or heuristics.mtime.year > 1970):
+            mtime = heuristics.mtime
             remote_newer = mtime.timestamp() > stat.st_mtime
             if remote_newer:
                 log.explain("Remote file seems to be newer")
@@ -261,7 +265,7 @@ class OutputDirectory:
             on_conflict: OnConflict,
             path: PurePath,
     ) -> bool:
-        if on_conflict == OnConflict.PROMPT:
+        if on_conflict in {OnConflict.PROMPT, OnConflict.NO_DELETE_PROMPT_OVERWRITE}:
             async with log.exclusive_output():
                 prompt = f"Replace {fmt_path(path)} with remote file?"
                 return await prompt_yes_no(prompt, default=False)
@@ -280,7 +284,7 @@ class OutputDirectory:
             on_conflict: OnConflict,
             path: PurePath,
     ) -> bool:
-        if on_conflict == OnConflict.PROMPT:
+        if on_conflict in {OnConflict.PROMPT, OnConflict.NO_DELETE_PROMPT_OVERWRITE}:
             async with log.exclusive_output():
                 prompt = f"Recursively delete {fmt_path(path)} and replace with remote file?"
                 return await prompt_yes_no(prompt, default=False)
@@ -300,7 +304,7 @@ class OutputDirectory:
             path: PurePath,
             parent: PurePath,
     ) -> bool:
-        if on_conflict == OnConflict.PROMPT:
+        if on_conflict in {OnConflict.PROMPT, OnConflict.NO_DELETE_PROMPT_OVERWRITE}:
             async with log.exclusive_output():
                 prompt = f"Delete {fmt_path(parent)} so remote file {fmt_path(path)} can be downloaded?"
                 return await prompt_yes_no(prompt, default=False)
@@ -327,7 +331,7 @@ class OutputDirectory:
             return False
         elif on_conflict == OnConflict.REMOTE_FIRST:
             return True
-        elif on_conflict == OnConflict.NO_DELETE:
+        elif on_conflict in {OnConflict.NO_DELETE, OnConflict.NO_DELETE_PROMPT_OVERWRITE}:
             return False
 
         # This should never be reached
@@ -492,7 +496,7 @@ class OutputDirectory:
             except OSError:
                 pass
         else:
-            log.status("[bold bright_magenta]", "Not deleted", fmt_path(pure))
+            log.not_deleted("[bold bright_magenta]", "Not deleted", fmt_path(pure))
             self._report.not_delete_file(pure)
 
     def load_prev_report(self) -> None:
@@ -500,7 +504,7 @@ class OutputDirectory:
         try:
             self._prev_report = Report.load(self._report_path)
             log.explain("Loaded report successfully")
-        except (OSError, json.JSONDecodeError, ReportLoadError) as e:
+        except (OSError, UnicodeDecodeError, json.JSONDecodeError, ReportLoadError) as e:
             log.explain("Failed to load report")
             log.explain(str(e))
 

PFERD/pferd.py

@@ -3,9 +3,9 @@ from typing import Dict, List, Optional
 
 from rich.markup import escape
 
-from .auth import AUTHENTICATORS, Authenticator, AuthError
+from .auth import AUTHENTICATORS, Authenticator, AuthError, AuthSection
 from .config import Config, ConfigOptionError
-from .crawl import CRAWLERS, Crawler, CrawlError, KitIliasWebCrawler
+from .crawl import CRAWLERS, Crawler, CrawlError, CrawlerSection, KitIliasWebCrawler
 from .logging import log
 from .utils import fmt_path
 
@@ -15,30 +15,33 @@ class PferdLoadError(Exception):
 
 
 class Pferd:
-    def __init__(self, config: Config, cli_crawlers: Optional[List[str]]):
+    def __init__(self, config: Config, cli_crawlers: Optional[List[str]], cli_skips: Optional[List[str]]):
         """
         May throw PferdLoadError.
         """
 
         self._config = config
-        self._crawlers_to_run = self._find_crawlers_to_run(config, cli_crawlers)
+        self._crawlers_to_run = self._find_crawlers_to_run(config, cli_crawlers, cli_skips)
 
         self._authenticators: Dict[str, Authenticator] = {}
         self._crawlers: Dict[str, Crawler] = {}
 
-    def _find_crawlers_to_run(self, config: Config, cli_crawlers: Optional[List[str]]) -> List[str]:
+    def _find_config_crawlers(self, config: Config) -> List[str]:
-        log.explain_topic("Deciding which crawlers to run")
+        crawl_sections = []
-        crawl_sections = [name for name, _ in config.crawl_sections()]
 
-        if cli_crawlers is None:
+        for name, section in config.crawl_sections():
-            log.explain("No crawlers specified on CLI")
+            if CrawlerSection(section).skip():
-            log.explain("Running all crawlers specified in config")
+                log.explain(f"Skipping {name!r}")
-            return crawl_sections
+            else:
+                crawl_sections.append(name)
 
+        return crawl_sections
+
+    def _find_cli_crawlers(self, config: Config, cli_crawlers: List[str]) -> List[str]:
         if len(cli_crawlers) != len(set(cli_crawlers)):
             raise PferdLoadError("Some crawlers were selected multiple times")
 
-        log.explain("Crawlers specified on CLI")
+        crawl_sections = [name for name, _ in config.crawl_sections()]
 
         crawlers_to_run = []  # With crawl: prefix
         unknown_names = []  # Without crawl: prefix
@@ -62,10 +65,36 @@ class Pferd:
 
         return crawlers_to_run
 
+    def _find_crawlers_to_run(
+            self,
+            config: Config,
+            cli_crawlers: Optional[List[str]],
+            cli_skips: Optional[List[str]],
+    ) -> List[str]:
+        log.explain_topic("Deciding which crawlers to run")
+
+        crawlers: List[str]
+        if cli_crawlers is None:
+            log.explain("No crawlers specified on CLI")
+            log.explain("Running crawlers specified in config")
+            crawlers = self._find_config_crawlers(config)
+        else:
+            log.explain("Crawlers specified on CLI")
+            crawlers = self._find_cli_crawlers(config, cli_crawlers)
+
+        skips = {f"crawl:{name}" for name in cli_skips} if cli_skips else set()
+        for crawler in crawlers:
+            if crawler in skips:
+                log.explain(f"Skipping crawler {crawler!r}")
+        crawlers = [crawler for crawler in crawlers if crawler not in skips]
+
+        return crawlers
+
     def _load_authenticators(self) -> None:
         for name, section in self._config.auth_sections():
             log.print(f"[bold bright_cyan]Loading[/] {escape(name)}")
-            auth_type = section.get("type")
+
+            auth_type = AuthSection(section).type()
             authenticator_constructor = AUTHENTICATORS.get(auth_type)
             if authenticator_constructor is None:
                 raise ConfigOptionError(name, "type", f"Unknown authenticator type: {auth_type!r}")
@@ -80,7 +109,7 @@ class Pferd:
         for name, section in self._config.crawl_sections():
             log.print(f"[bold bright_cyan]Loading[/] {escape(name)}")
 
-            crawl_type = section.get("type")
+            crawl_type = CrawlerSection(section).type()
             crawler_constructor = CRAWLERS.get(crawl_type)
             if crawler_constructor is None:
                 raise ConfigOptionError(name, "type", f"Unknown crawler type: {crawl_type!r}")
@@ -151,7 +180,15 @@ class Pferd:
                 log.report(f"  [bold bright_magenta]Deleted[/] {fmt_path(path)}")
             for path in sorted(crawler.report.not_deleted_files):
                 something_changed = True
-                log.report(f"  [bold bright_magenta]Not deleted[/] {fmt_path(path)}")
+                log.report_not_deleted(f"  [bold bright_magenta]Not deleted[/] {fmt_path(path)}")
+
+            for warning in crawler.report.encountered_warnings:
+                something_changed = True
+                log.report(f"  [bold bright_red]Warning[/] {warning}")
+
+            for error in crawler.report.encountered_errors:
+                something_changed = True
+                log.report(f"  [bold bright_red]Error[/] {error}")
 
             if not something_changed:
                 log.report("  Nothing changed")

PFERD/report.py

@@ -1,6 +1,6 @@
 import json
 from pathlib import Path, PurePath
-from typing import Any, Dict, List, Set
+from typing import Any, Dict, List, Optional, Set
 
 
 class ReportLoadError(Exception):
@@ -68,6 +68,13 @@ class Report:
         # Files that should have been deleted by the cleanup but weren't
         self.not_deleted_files: Set[PurePath] = set()
 
+        # Custom crawler-specific data
+        self.custom: Dict[str, Any] = dict()
+
+        # Encountered errors and warnings
+        self.encountered_warnings: List[str] = []
+        self.encountered_errors: List[str] = []
+
     @staticmethod
     def _get_list_of_strs(data: Dict[str, Any], key: str) -> List[str]:
         result: Any = data.get(key, [])
@@ -81,13 +88,22 @@ class Report:
 
         return result
 
+    @staticmethod
+    def _get_str_dictionary(data: Dict[str, Any], key: str) -> Dict[str, Any]:
+        result: Dict[str, Any] = data.get(key, {})
+
+        if not isinstance(result, dict):
+            raise ReportLoadError(f"Incorrect format: {key!r} is not a dictionary")
+
+        return result
+
     @classmethod
     def load(cls, path: Path) -> "Report":
         """
-        May raise OSError, JsonDecodeError, ReportLoadError.
+        May raise OSError, UnicodeDecodeError, JsonDecodeError, ReportLoadError.
         """
 
-        with open(path) as f:
+        with open(path, encoding="utf-8") as f:
             data = json.load(f)
 
         if not isinstance(data, dict):
@@ -108,6 +124,9 @@ class Report:
             self.delete_file(PurePath(elem))
         for elem in self._get_list_of_strs(data, "not_deleted"):
             self.not_delete_file(PurePath(elem))
+        self.custom = self._get_str_dictionary(data, "custom")
+        self.encountered_errors = self._get_list_of_strs(data, "encountered_errors")
+        self.encountered_warnings = self._get_list_of_strs(data, "encountered_warnings")
 
         return self
 
@@ -124,9 +143,12 @@ class Report:
             "changed": [str(path) for path in sorted(self.changed_files)],
             "deleted": [str(path) for path in sorted(self.deleted_files)],
             "not_deleted": [str(path) for path in sorted(self.not_deleted_files)],
+            "custom": self.custom,
+            "encountered_warnings": self.encountered_warnings,
+            "encountered_errors": self.encountered_errors,
         }
 
-        with open(path, "w") as f:
+        with open(path, "w", encoding="utf-8") as f:
             json.dump(data, f, indent=2, sort_keys=True)
             f.write("\n")  # json.dump doesn't do this
 
@@ -190,3 +212,27 @@ class Report:
         """
 
         self.not_deleted_files.add(path)
+
+    def add_custom_value(self, key: str, value: Any) -> None:
+        """
+        Adds a custom value under the passed key, overwriting any existing
+        """
+        self.custom[key] = value
+
+    def get_custom_value(self, key: str) -> Optional[Any]:
+        """
+        Retrieves a custom value for the given key.
+        """
+        return self.custom.get(key)
+
+    def add_error(self, error: str) -> None:
+        """
+        Adds an error to this report's error list.
+        """
+        self.encountered_errors.append(error)
+
+    def add_warning(self, warning: str) -> None:
+        """
+        Adds a warning to this report's warning list.
+        """
+        self.encountered_warnings.append(warning)

PFERD/transformer.py

@@ -1,151 +1,166 @@
-# I'm sorry that this code has become a bit dense and unreadable. While
-# reading, it is important to remember what True and False mean. I'd love to
-# have some proper sum-types for the inputs and outputs, they'd make this code
-# a lot easier to understand.
-
 import ast
 import re
 from abc import ABC, abstractmethod
+from dataclasses import dataclass
+from enum import Enum
 from pathlib import PurePath
-from typing import Dict, Optional, Sequence, Union
+from typing import Callable, Dict, List, Optional, Sequence, TypeVar, Union
 
 from .logging import log
-from .utils import fmt_path
+from .utils import fmt_path, str_path
 
 
-class Rule(ABC):
+class ArrowHead(Enum):
+    NORMAL = 0
+    SEQUENCE = 1
+
+
+class Ignore:
+    pass
+
+
+class Empty:
+    pass
+
+
+RightSide = Union[str, Ignore, Empty]
+
+
+@dataclass
+class Transformed:
+    path: PurePath
+
+
+class Ignored:
+    pass
+
+
+TransformResult = Optional[Union[Transformed, Ignored]]
+
+
+@dataclass
+class Rule:
+    left: str
+    left_index: int
+    name: str
+    head: ArrowHead
+    right: RightSide
+    right_index: int
+
+    def right_result(self, path: PurePath) -> Union[str, Transformed, Ignored]:
+        if isinstance(self.right, str):
+            return self.right
+        elif isinstance(self.right, Ignore):
+            return Ignored()
+        elif isinstance(self.right, Empty):
+            return Transformed(path)
+        else:
+            raise RuntimeError(f"Right side has invalid type {type(self.right)}")
+
+
+class Transformation(ABC):
+    def __init__(self, rule: Rule):
+        self.rule = rule
+
     @abstractmethod
-    def transform(self, path: PurePath) -> Union[PurePath, bool]:
+    def transform(self, path: PurePath) -> TransformResult:
-        """
-        Try to apply this rule to the path. Returns another path if the rule
-        was successfully applied, True if the rule matched but resulted in an
-        exclamation mark, and False if the rule didn't match at all.
-        """
-
         pass
 
 
-# These rules all use a Union[T, bool] for their right side. They are passed a
+class ExactTf(Transformation):
-# T if the arrow's right side was a normal string, True if it was an
+    def transform(self, path: PurePath) -> TransformResult:
-# exclamation mark and False if it was missing entirely.
+        if path != PurePath(self.rule.left):
-
-class NormalRule(Rule):
-    def __init__(self, left: PurePath, right: Union[PurePath, bool]):
-
-        self._left = left
-        self._right = right
-
-    def _match_prefix(self, path: PurePath) -> Optional[PurePath]:
-        left_parts = list(reversed(self._left.parts))
-        path_parts = list(reversed(path.parts))
-
-        if len(left_parts) > len(path_parts):
             return None
 
-        while left_parts and path_parts:
+        right = self.rule.right_result(path)
-            left_part = left_parts.pop()
+        if not isinstance(right, str):
-            path_part = path_parts.pop()
+            return right
 
-            if left_part != path_part:
+        return Transformed(PurePath(right))
-                return None
 
-        if left_parts:
+
+class ExactReTf(Transformation):
+    def transform(self, path: PurePath) -> TransformResult:
+        match = re.fullmatch(self.rule.left, str_path(path))
+        if not match:
             return None
 
-        path_parts.reverse()
+        right = self.rule.right_result(path)
-        return PurePath(*path_parts)
+        if not isinstance(right, str):
+            return right
 
-    def transform(self, path: PurePath) -> Union[PurePath, bool]:
+        # For some reason, mypy thinks that "groups" has type List[str]. But
-        if rest := self._match_prefix(path):
+        # since elements of "match.groups()" can be None, mypy is wrong.
-            if isinstance(self._right, bool):
+        groups: Sequence[Optional[str]] = [match[0]] + list(match.groups())
-                return self._right or path
+
+        locals_dir: Dict[str, Union[str, int, float]] = {}
+        for i, group in enumerate(groups):
+            if group is None:
+                continue
+
+            locals_dir[f"g{i}"] = group
+
+            try:
+                locals_dir[f"i{i}"] = int(group)
+            except ValueError:
+                pass
+
+            try:
+                locals_dir[f"f{i}"] = float(group)
+            except ValueError:
+                pass
+
+        result = eval(f"f{right!r}", {}, locals_dir)
+        return Transformed(PurePath(result))
+
+
+class RenamingParentsTf(Transformation):
+    def __init__(self, sub_tf: Transformation):
+        super().__init__(sub_tf.rule)
+        self.sub_tf = sub_tf
+
+    def transform(self, path: PurePath) -> TransformResult:
+        for i in range(len(path.parts), -1, -1):
+            parent = PurePath(*path.parts[:i])
+            child = PurePath(*path.parts[i:])
+
+            transformed = self.sub_tf.transform(parent)
+            if not transformed:
+                continue
+            elif isinstance(transformed, Transformed):
+                return Transformed(transformed.path / child)
+            elif isinstance(transformed, Ignored):
+                return transformed
             else:
-                return self._right / rest
+                raise RuntimeError(f"Invalid transform result of type {type(transformed)}: {transformed}")
 
-        return False
+        return None
 
 
-class ExactRule(Rule):
+class RenamingPartsTf(Transformation):
-    def __init__(self, left: PurePath, right: Union[PurePath, bool]):
+    def __init__(self, sub_tf: Transformation):
-        self._left = left
+        super().__init__(sub_tf.rule)
-        self._right = right
+        self.sub_tf = sub_tf
 
-    def transform(self, path: PurePath) -> Union[PurePath, bool]:
+    def transform(self, path: PurePath) -> TransformResult:
-        if path == self._left:
-            if isinstance(self._right, bool):
-                return self._right or path
-            else:
-                return self._right
-
-        return False
-
-
-class NameRule(Rule):
-    def __init__(self, subrule: Rule):
-        self._subrule = subrule
-
-    def transform(self, path: PurePath) -> Union[PurePath, bool]:
-        matched = False
         result = PurePath()
-
+        any_part_matched = False
         for part in path.parts:
-            part_result = self._subrule.transform(PurePath(part))
+            transformed = self.sub_tf.transform(PurePath(part))
-            if isinstance(part_result, PurePath):
+            if not transformed:
-                matched = True
-                result /= part_result
-            elif part_result:
-                # If any subrule call ignores its path segment, the entire path
-                # should be ignored
-                return True
-            else:
-                # The subrule doesn't modify this segment, but maybe other
-                # segments
                 result /= part
+            elif isinstance(transformed, Transformed):
+                result /= transformed.path
+                any_part_matched = True
+            elif isinstance(transformed, Ignored):
+                return transformed
+            else:
+                raise RuntimeError(f"Invalid transform result of type {type(transformed)}: {transformed}")
 
-        if matched:
+        if any_part_matched:
-            return result
+            return Transformed(result)
         else:
-            # The subrule has modified no segments, so this name version of it
+            return None
-            # doesn't match
-            return False
-
-
-class ReRule(Rule):
-    def __init__(self, left: str, right: Union[str, bool]):
-        self._left = left
-        self._right = right
-
-    def transform(self, path: PurePath) -> Union[PurePath, bool]:
-        if match := re.fullmatch(self._left, str(path)):
-            if isinstance(self._right, bool):
-                return self._right or path
-
-            vars: Dict[str, Union[str, int, float]] = {}
-
-            # For some reason, mypy thinks that "groups" has type List[str].
-            # But since elements of "match.groups()" can be None, mypy is
-            # wrong.
-            groups: Sequence[Optional[str]] = [match[0]] + list(match.groups())
-            for i, group in enumerate(groups):
-                if group is None:
-                    continue
-
-                vars[f"g{i}"] = group
-
-                try:
-                    vars[f"i{i}"] = int(group)
-                except ValueError:
-                    pass
-
-                try:
-                    vars[f"f{i}"] = float(group)
-                except ValueError:
-                    pass
-
-            result = eval(f"f{self._right!r}", vars)
-            return PurePath(result)
-
-        return False
 
 
 class RuleParseError(Exception):
@@ -162,18 +177,15 @@ class RuleParseError(Exception):
         log.error_contd(f"{spaces}^--- {self.reason}")
 
 
+T = TypeVar("T")
+
+
 class Line:
     def __init__(self, line: str, line_nr: int):
         self._line = line
         self._line_nr = line_nr
         self._index = 0
 
-    def get(self) -> Optional[str]:
-        if self._index < len(self._line):
-            return self._line[self._index]
-
-        return None
-
     @property
     def line(self) -> str:
         return self._line
@@ -190,155 +202,196 @@ class Line:
     def index(self, index: int) -> None:
         self._index = index
 
-    def advance(self) -> None:
+    @property
-        self._index += 1
+    def rest(self) -> str:
+        return self.line[self.index:]
 
-    def expect(self, string: str) -> None:
+    def peek(self, amount: int = 1) -> str:
-        for char in string:
+        return self.rest[:amount]
-            if self.get() == char:
+
-                self.advance()
+    def take(self, amount: int = 1) -> str:
-            else:
+        string = self.peek(amount)
-                raise RuleParseError(self, f"Expected {char!r}")
+        self.index += len(string)
+        return string
+
+    def expect(self, string: str) -> str:
+        if self.peek(len(string)) == string:
+            return self.take(len(string))
+        else:
+            raise RuleParseError(self, f"Expected {string!r}")
+
+    def expect_with(self, string: str, value: T) -> T:
+        self.expect(string)
+        return value
+
+    def one_of(self, parsers: List[Callable[[], T]], description: str) -> T:
+        for parser in parsers:
+            index = self.index
+            try:
+                return parser()
+            except RuleParseError:
+                self.index = index
+
+        raise RuleParseError(self, description)
+
+
+# RULE = LEFT SPACE '-' NAME '-' HEAD (SPACE RIGHT)?
+# SPACE = ' '+
+# NAME = '' | 'exact' | 'name' | 're' | 'exact-re' | 'name-re'
+# HEAD = '>' | '>>'
+# LEFT = STR | QUOTED_STR
+# RIGHT = STR | QUOTED_STR | '!'
+
+
+def parse_zero_or_more_spaces(line: Line) -> None:
+    while line.peek() == " ":
+        line.take()
+
+
+def parse_one_or_more_spaces(line: Line) -> None:
+    line.expect(" ")
+    parse_zero_or_more_spaces(line)
+
+
+def parse_str(line: Line) -> str:
+    result = []
+    while c := line.peek():
+        if c == " ":
+            break
+        else:
+            line.take()
+            result.append(c)
+
+    if result:
+        return "".join(result)
+    else:
+        raise RuleParseError(line, "Expected non-space character")
 
 
 QUOTATION_MARKS = {'"', "'"}
 
 
-def parse_string_literal(line: Line) -> str:
+def parse_quoted_str(line: Line) -> str:
     escaped = False
 
     # Points to first character of string literal
     start_index = line.index
 
-    quotation_mark = line.get()
+    quotation_mark = line.peek()
     if quotation_mark not in QUOTATION_MARKS:
-        # This should never happen as long as this function is only called from
+        raise RuleParseError(line, "Expected quotation mark")
-        # parse_string.
+    line.take()
-        raise RuleParseError(line, "Invalid quotation mark")
-    line.advance()
 
-    while c := line.get():
+    while c := line.peek():
         if escaped:
             escaped = False
-            line.advance()
+            line.take()
         elif c == quotation_mark:
-            line.advance()
+            line.take()
             stop_index = line.index
             literal = line.line[start_index:stop_index]
-            return ast.literal_eval(literal)
+            try:
+                return ast.literal_eval(literal)
+            except SyntaxError as e:
+                line.index = start_index
+                raise RuleParseError(line, str(e)) from e
         elif c == "\\":
             escaped = True
-            line.advance()
+            line.take()
         else:
-            line.advance()
+            line.take()
 
     raise RuleParseError(line, "Expected end of string literal")
 
 
-def parse_until_space_or_eol(line: Line) -> str:
+def parse_left(line: Line) -> str:
-    result = []
+    if line.peek() in QUOTATION_MARKS:
-    while c := line.get():
+        return parse_quoted_str(line)
-        if c == " ":
-            break
-        result.append(c)
-        line.advance()
-
-    return "".join(result)
-
-
-def parse_string(line: Line) -> Union[str, bool]:
-    if line.get() in QUOTATION_MARKS:
-        return parse_string_literal(line)
     else:
-        string = parse_until_space_or_eol(line)
+        return parse_str(line)
+
+
+def parse_right(line: Line) -> Union[str, Ignore]:
+    c = line.peek()
+    if c in QUOTATION_MARKS:
+        return parse_quoted_str(line)
+    else:
+        string = parse_str(line)
         if string == "!":
-            return True
+            return Ignore()
         return string
 
 
-def parse_arrow(line: Line) -> str:
+def parse_arrow_name(line: Line) -> str:
-    line.expect("-")
+    return line.one_of([
-
+        lambda: line.expect("exact-re"),
-    name = []
+        lambda: line.expect("exact"),
-    while True:
+        lambda: line.expect("name-re"),
-        c = line.get()
+        lambda: line.expect("name"),
-        if not c:
+        lambda: line.expect("re"),
-            raise RuleParseError(line, "Expected rest of arrow")
+        lambda: line.expect(""),
-        elif c == "-":
+    ], "Expected arrow name")
-            line.advance()
-            c = line.get()
-            if not c:
-                raise RuleParseError(line, "Expected rest of arrow")
-            elif c == ">":
-                line.advance()
-                break  # End of arrow
-            else:
-                name.append("-")
-                continue
-        else:
-            name.append(c)
-
-        line.advance()
-
-    return "".join(name)
 
 
-def parse_whitespace(line: Line) -> None:
+def parse_arrow_head(line: Line) -> ArrowHead:
-    line.expect(" ")
+    return line.one_of([
-    while line.get() == " ":
+        lambda: line.expect_with(">>", ArrowHead.SEQUENCE),
-        line.advance()
+        lambda: line.expect_with(">", ArrowHead.NORMAL),
+    ], "Expected arrow head")
 
 
 def parse_eol(line: Line) -> None:
-    if line.get() is not None:
+    if line.peek():
         raise RuleParseError(line, "Expected end of line")
 
 
 def parse_rule(line: Line) -> Rule:
-    # Parse left side
+    parse_zero_or_more_spaces(line)
-    leftindex = line.index
+    left_index = line.index
-    left = parse_string(line)
+    left = parse_left(line)
-    if isinstance(left, bool):
-        line.index = leftindex
-        raise RuleParseError(line, "Left side can't be '!'")
-    leftpath = PurePath(left)
 
-    # Parse arrow
+    parse_one_or_more_spaces(line)
-    parse_whitespace(line)
-    arrowindex = line.index
-    arrowname = parse_arrow(line)
 
-    # Parse right side
+    line.expect("-")
-    if line.get():
+    name = parse_arrow_name(line)
-        parse_whitespace(line)
+    line.expect("-")
-        right = parse_string(line)
+    head = parse_arrow_head(line)
+
+    right_index = line.index
+    right: RightSide
+    try:
+        parse_zero_or_more_spaces(line)
+        parse_eol(line)
+        right = Empty()
+    except RuleParseError:
+        line.index = right_index
+        parse_one_or_more_spaces(line)
+        right = parse_right(line)
+        parse_eol(line)
+
+    return Rule(left, left_index, name, head, right, right_index)
+
+
+def parse_transformation(line: Line) -> Transformation:
+    rule = parse_rule(line)
+
+    if rule.name == "":
+        return RenamingParentsTf(ExactTf(rule))
+    elif rule.name == "exact":
+        return ExactTf(rule)
+    elif rule.name == "name":
+        if len(PurePath(rule.left).parts) > 1:
+            line.index = rule.left_index
+            raise RuleParseError(line, "Expected name, not multiple segments")
+        return RenamingPartsTf(ExactTf(rule))
+    elif rule.name == "re":
+        return RenamingParentsTf(ExactReTf(rule))
+    elif rule.name == "exact-re":
+        return ExactReTf(rule)
+    elif rule.name == "name-re":
+        return RenamingPartsTf(ExactReTf(rule))
     else:
-        right = False
+        raise RuntimeError(f"Invalid arrow name {rule.name!r}")
-    rightpath: Union[PurePath, bool]
-    if isinstance(right, bool):
-        rightpath = right
-    else:
-        rightpath = PurePath(right)
-
-    parse_eol(line)
-
-    # Dispatch
-    if arrowname == "":
-        return NormalRule(leftpath, rightpath)
-    elif arrowname == "name":
-        if len(leftpath.parts) > 1:
-            line.index = leftindex
-            raise RuleParseError(line, "SOURCE must be a single name, not multiple segments")
-        return NameRule(ExactRule(leftpath, rightpath))
-    elif arrowname == "exact":
-        return ExactRule(leftpath, rightpath)
-    elif arrowname == "re":
-        return ReRule(left, right)
-    elif arrowname == "name-re":
-        return NameRule(ReRule(left, right))
-    else:
-        line.index = arrowindex + 1  # For nicer error message
-        raise RuleParseError(line, f"Invalid arrow name {arrowname!r}")
 
 
 class Transformer:
@@ -347,32 +400,40 @@ class Transformer:
         May throw a RuleParseException.
         """
 
-        self._rules = []
+        self._tfs = []
         for i, line in enumerate(rules.split("\n")):
             line = line.strip()
             if line:
-                rule = parse_rule(Line(line, i))
+                tf = parse_transformation(Line(line, i))
-                self._rules.append((line, rule))
+                self._tfs.append((line, tf))
 
     def transform(self, path: PurePath) -> Optional[PurePath]:
-        for i, (line, rule) in enumerate(self._rules):
+        for i, (line, tf) in enumerate(self._tfs):
             log.explain(f"Testing rule {i+1}: {line}")
 
             try:
-                result = rule.transform(path)
+                result = tf.transform(path)
             except Exception as e:
                 log.warn(f"Error while testing rule {i+1}: {line}")
                 log.warn_contd(str(e))
                 continue
 
-            if isinstance(result, PurePath):
+            if not result:
-                log.explain(f"Match found, transformed path to {fmt_path(result)}")
-                return result
-            elif result:  # Exclamation mark
-                log.explain("Match found, path ignored")
-                return None
-            else:
                 continue
 
-        log.explain("No rule matched, path is unchanged")
+            if isinstance(result, Ignored):
+                log.explain("Match found, path ignored")
+                return None
+
+            if tf.rule.head == ArrowHead.NORMAL:
+                log.explain(f"Match found, transformed path to {fmt_path(result.path)}")
+                path = result.path
+                break
+            elif tf.rule.head == ArrowHead.SEQUENCE:
+                log.explain(f"Match found, updated path to {fmt_path(result.path)}")
+                path = result.path
+            else:
+                raise RuntimeError(f"Invalid transform result of type {type(result)}: {result}")
+
+        log.explain(f"Final result: {fmt_path(path)}")
         return path

PFERD/utils.py

@@ -91,8 +91,14 @@ def url_set_query_params(url: str, params: Dict[str, str]) -> str:
     return result
 
 
+def str_path(path: PurePath) -> str:
+    if not path.parts:
+        return "."
+    return "/".join(path.parts)
+
+
 def fmt_path(path: PurePath) -> str:
-    return repr(str(path))
+    return repr(str_path(path))
 
 
 def fmt_real_path(path: Path) -> str:

PFERD/version.py

@@ -1,2 +1,2 @@
 NAME = "PFERD"
-VERSION = "3.0.0"
+VERSION = "3.5.0"

README.md

@@ -17,7 +17,7 @@ Binaries for Linux, Windows and Mac can be downloaded directly from the
 
 ### With pip
 
-Ensure you have at least Python 3.8 installed. Run the following command to
+Ensure you have at least Python 3.9 installed. Run the following command to
 install PFERD or upgrade it to the latest version:
 
 ```
@@ -26,11 +26,22 @@ $ pip install --upgrade git+https://github.com/Garmelon/PFERD@latest
 
 The use of [venv](https://docs.python.org/3/library/venv.html) is recommended.
 
+### With package managers
+
+Unofficial packages are available for:
+- [AUR](https://aur.archlinux.org/packages/pferd)
+- [brew](https://formulae.brew.sh/formula/pferd)
+- [conda-forge](https://github.com/conda-forge/pferd-feedstock)
+- [nixpkgs](https://github.com/NixOS/nixpkgs/blob/master/pkgs/tools/misc/pferd/default.nix)
+- [PyPi](https://pypi.org/project/pferd)
+
+See also PFERD's [repology page](https://repology.org/project/pferd/versions).
+
 ## Basic usage
 
-PFERD can be run directly from the command line with no config file.
+PFERD can be run directly from the command line with no config file. Run `pferd
-Run `pferd -h` to get an overview of available commands and options.
+-h` to get an overview of available commands and options. Run `pferd <command>
-Run `pferd <command> -h` to see which options a command has.
+-h` to see which options a command has.
 
 For example, you can download your personal desktop from the KIT ILIAS like
 this:
@@ -116,17 +127,18 @@ transform =
   Online-Tests --> !
   Vorlesungswerbung --> !
 
+  # Rename folders
+  Lehrbücher --> Vorlesung
+  # Note the ">>" arrow head which lets us apply further rules to files moved to "Übung"
+  Übungsunterlagen -->> Übung
+
   # Move exercises to own folder. Rename them to "Blatt-XX.pdf" to make them sort properly
-  "Übungsunterlagen/(\d+). Übungsblatt.pdf" -re-> Blätter/Blatt-{i1:02}.pdf
+  "Übung/(\d+). Übungsblatt.pdf" -re-> Blätter/Blatt-{i1:02}.pdf
   # Move solutions to own folder. Rename them to "Blatt-XX-Lösung.pdf" to make them sort properly
-  "Übungsunterlagen/(\d+). Übungsblatt.*Musterlösung.pdf" -re-> Blätter/Blatt-{i1:02}-Lösung.pdf
+  "Übung/(\d+). Übungsblatt.*Musterlösung.pdf" -re-> Blätter/Blatt-{i1:02}-Lösung.pdf
 
   # The course has nested folders with the same name - flatten them
-  "Übungsunterlagen/(.+?)/\\1/(.*)" -re-> Übung/{g1}/{g2}
+  "Übung/(.+?)/\\1" -re-> Übung/{g1}
-
-  # Rename remaining folders
-  Übungsunterlagen --> Übung
-  Lehrbücher --> Vorlesung
 
 [crawl:Bar]
 type = kit-ilias-web

flake.lock

@@ -0,0 +1,27 @@
+{
+  "nodes": {
+    "nixpkgs": {
+      "locked": {
+        "lastModified": 1694499547,
+        "narHash": "sha256-R7xMz1Iia6JthWRHDn36s/E248WB1/je62ovC/dUVKI=",
+        "owner": "NixOS",
+        "repo": "nixpkgs",
+        "rev": "e5f018cf150e29aac26c61dac0790ea023c46b24",
+        "type": "github"
+      },
+      "original": {
+        "owner": "NixOS",
+        "ref": "nixos-23.05",
+        "repo": "nixpkgs",
+        "type": "github"
+      }
+    },
+    "root": {
+      "inputs": {
+        "nixpkgs": "nixpkgs"
+      }
+    }
+  },
+  "root": "root",
+  "version": 7
+}

flake.nix

@@ -0,0 +1,41 @@
+{
+  description = "Tool for downloading course-related files from ILIAS";
+
+  inputs = {
+    nixpkgs.url = "github:NixOS/nixpkgs/nixos-23.05";
+  };
+
+  outputs = { self, nixpkgs }:
+    let
+      # Helper function to generate an attrset '{ x86_64-linux = f "x86_64-linux"; ... }'.
+      forAllSystems = nixpkgs.lib.genAttrs nixpkgs.lib.systems.flakeExposed;
+    in
+    {
+      packages = forAllSystems (system:
+        let pkgs = import nixpkgs { inherit system; };
+        in
+        rec {
+          default = pkgs.python3Packages.buildPythonApplication rec {
+            pname = "pferd";
+            # Performing black magic
+            # Don't worry, I sacrificed enough goats for the next few years
+            version = (pkgs.lib.importTOML ./PFERD/version.py).VERSION;
+            format = "pyproject";
+
+            src = ./.;
+
+            nativeBuildInputs = with pkgs.python3Packages; [
+              setuptools
+            ];
+
+            propagatedBuildInputs = with pkgs.python3Packages; [
+              aiohttp
+              beautifulsoup4
+              rich
+              keyring
+              certifi
+            ];
+          };
+        });
+    };
+}

scripts/setup

@@ -12,6 +12,6 @@ pip install --upgrade setuptools
 # Installing PFERD itself
 pip install --editable .
 
-# Installing various tools
+# Installing tools and type hints
-pip install --upgrade mypy flake8 autopep8 isort
+pip install --upgrade mypy flake8 autopep8 isort pyinstaller
-pip install --upgrade pyinstaller
+pip install --upgrade types-chardet types-certifi

setup.cfg

@@ -4,13 +4,13 @@ version = attr: PFERD.version.VERSION
 
 [options]
 packages = find:
-python_requires = >=3.8
+python_requires = >=3.9
 install_requires =
-  aiohttp>=3.7.4.post0
+  aiohttp>=3.8.1
-  beautifulsoup4>=4.9.3
+  beautifulsoup4>=4.10.0
-  rich>=10.1.0
+  rich>=11.0.0
-  keyring>=23.0.1
+  keyring>=23.5.0
-  certifi>=2020.12.5
+  certifi>=2021.10.8
 
 [options.entry_points]
 console_scripts =