Adjust release names

Add "Sync url" script from Christophe and release it automatically

.github/workflows/package.yml

@@ -0,0 +1,74 @@
+name: Package Application with Pyinstaller
+
+on:
+  push:
+    branches:
+      - "*"
+    tags:
+      - "v*"
+
+jobs:
+  build:
+
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, windows-latest, macos-latest]
+
+    steps:
+    - uses: actions/checkout@v2
+
+    - uses: actions/setup-python@v2
+      with:
+        python-version: '3.x'
+
+    - name: "Install dependencies"
+      run: "pip install setuptools pyinstaller rich requests beautifulsoup4 -f --upgrade"
+
+    - name: "Install sync_url.py"
+      run: "pyinstaller sync_url.py -F"
+
+    - name: "Move artifact"
+      run: "mv dist/sync_url* dist/sync_url-${{ matrix.os }}"
+
+    - uses: actions/upload-artifact@v2
+      with:
+        name: "Pferd Sync URL"
+        path: "dist/sync_url*"
+
+  release:
+    name: Release
+
+    needs: [build]
+    runs-on: ubuntu-latest
+    if: startsWith(github.ref, 'refs/tags/')
+
+    env:
+      GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+    steps:
+    - name: "Checkout"
+      uses: actions/checkout@v2
+
+    - name: "Download artifacts"
+      uses: actions/download-artifact@v2
+      with:
+        name: "Pferd Sync URL"
+
+    - name: "look at folder structure"
+      run: "ls -lah"
+
+    - name: "Rename releases"
+      run: "mv sync_url-macos-latest pferd_sync_url_mac && mv sync_url-ubuntu-latest pferd_sync_url_linux && mv sync_url-windows-latest pferd_sync_url.exe"
+
+    - name: "Create release"
+      uses: softprops/action-gh-release@v1
+
+    - name: "Upload release artifacts"
+      uses: softprops/action-gh-release@v1
+      with:
+        body: "Download the correct sync_url for your platform and run it in the terminal or CMD. You might need to make it executable on Linux/Mac with `chmod +x <file>`."
+        files: |
+          pferd_sync_url_mac
+          pferd_sync_url_linux
+          pferd_sync_url.exe

.gitignore

@@ -1,7 +1,14 @@
 __pycache__/
 .venv/
+venv/
+.idea/
+build/
 .mypy_cache/
 .tmp/
 .env
 .vscode
 ilias_cookies.txt
+
+# PyInstaller
+sync_url.spec
+dist/

LICENSE

@@ -0,0 +1,18 @@
+Copyright 2019-2020 Garmelon, I-Al-Istannen, danstooamerican, pavelzw
+
+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
+the Software without restriction, including without limitation the rights to
+use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
+the Software, and to permit persons to whom the Software is furnished to do so,
+subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
+FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
+COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
+IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

PFERD/cookie_jar.py

@@ -22,7 +22,7 @@ class CookieJar:
         if cookie_file is None:
             self._cookies = LWPCookieJar()
         else:
-            self._cookies = LWPCookieJar(cookie_file)
+            self._cookies = LWPCookieJar(str(cookie_file.resolve()))
 
     @property
     def cookies(self) -> LWPCookieJar:

PFERD/download_summary.py

@@ -0,0 +1,69 @@
+"""
+Provides a summary that keeps track of new modified or deleted files.
+"""
+from pathlib import Path
+from typing import List
+
+
+class DownloadSummary:
+    """
+    Keeps track of all new, modified or deleted files and provides a summary.
+    """
+
+    def __init__(self) -> None:
+        self._new_files: List[Path] = []
+        self._modified_files: List[Path] = []
+        self._deleted_files: List[Path] = []
+
+    @property
+    def new_files(self) -> List[Path]:
+        """
+        Returns all new files.
+        """
+        return self._new_files.copy()
+
+    @property
+    def modified_files(self) -> List[Path]:
+        """
+        Returns all modified files.
+        """
+        return self._modified_files.copy()
+
+    @property
+    def deleted_files(self) -> List[Path]:
+        """
+        Returns all deleted files.
+        """
+        return self._deleted_files.copy()
+
+    def merge(self, summary: 'DownloadSummary') -> None:
+        """
+        Merges ourselves with the passed summary. Modifies this object, but not the passed one.
+        """
+        self._new_files += summary.new_files
+        self._modified_files += summary.modified_files
+        self._deleted_files += summary.deleted_files
+
+    def add_deleted_file(self, path: Path) -> None:
+        """
+        Registers a file as deleted.
+        """
+        self._deleted_files.append(path)
+
+    def add_modified_file(self, path: Path) -> None:
+        """
+        Registers a file as changed.
+        """
+        self._modified_files.append(path)
+
+    def add_new_file(self, path: Path) -> None:
+        """
+        Registers a file as new.
+        """
+        self._new_files.append(path)
+
+    def has_updates(self) -> bool:
+        """
+        Returns whether this summary has any updates.
+        """
+        return bool(self._new_files or self._modified_files or self._deleted_files)

PFERD/ilias/__init__.py

@@ -3,7 +3,8 @@ Synchronizing files from ILIAS instances (https://www.ilias.de/).
 """
 
 from .authenticators import IliasAuthenticator, KitShibbolethAuthenticator
-from .crawler import IliasCrawler, IliasDirectoryFilter, IliasDirectoryType
+from .crawler import (IliasCrawler, IliasCrawlerEntry, IliasDirectoryFilter,
+                      IliasElementType)
 from .downloader import (IliasDownloader, IliasDownloadInfo,
                          IliasDownloadStrategy, download_everything,
                          download_modified_or_new)

PFERD/ilias/authenticators.py

@@ -67,7 +67,7 @@ class KitShibbolethAuthenticator(IliasAuthenticator):
         while not self._login_successful(soup):
             # Searching the form here so that this fails before asking for
             # credentials rather than after asking.
-            form = soup.find("form", {"class": "form2", "method": "post"})
+            form = soup.find("form", {"class": "full content", "method": "post"})
             action = form["action"]
 
             # Equivalent: Enter credentials in

PFERD/ilias/crawler.py

@@ -8,7 +8,7 @@ import logging
 import re
 from enum import Enum
 from pathlib import Path
-from typing import Any, Callable, Dict, List, Optional
+from typing import Any, Callable, Dict, List, Optional, Union
 from urllib.parse import (parse_qs, urlencode, urljoin, urlparse, urlsplit,
                           urlunsplit)
 
@@ -26,16 +26,58 @@ LOGGER = logging.getLogger(__name__)
 PRETTY = PrettyLogger(LOGGER)
 
 
-class IliasDirectoryType(Enum):
+class IliasElementType(Enum):
     """
-    The type of an ilias directory.
+    The type of an ilias element.
     """
-    FOLDER = "FOLDER"
+    REGULAR_FOLDER = "REGULAR_FOLDER"
-    VIDEO = "VIDEO"
+    VIDEO_FOLDER = "VIDEO_FOLDER"
-    EXERCISE = "EXERCISE"
+    EXERCISE_FOLDER = "EXERCISE_FOLDER"
+    REGULAR_FILE = "REGULAR_FILE"
+    VIDEO_FILE = "VIDEO_FILE"
+    FORUM = "FORUM"
+    EXTERNAL_LINK = "EXTERNAL_LINK"
+
+    def is_folder(self) -> bool:
+        """
+        Returns whether this type is some kind of folder.
+        """
+        return "FOLDER" in str(self.name)
 
 
-IliasDirectoryFilter = Callable[[Path, IliasDirectoryType], bool]
+IliasDirectoryFilter = Callable[[Path, IliasElementType], bool]
+
+
+class IliasCrawlerEntry:
+    # pylint: disable=too-few-public-methods
+    """
+    An ILIAS crawler entry used internally to find, catalogue and recursively crawl elements.
+    """
+
+    def __init__(
+            self,
+            path: Path,
+            url: Union[str, Callable[[], Optional[str]]],
+            entry_type: IliasElementType,
+            modification_date: Optional[datetime.datetime]
+    ):
+        self.path = path
+        if isinstance(url, str):
+            str_url = url
+            self.url: Callable[[], Optional[str]] = lambda: str_url
+        else:
+            self.url = url
+        self.entry_type = entry_type
+        self.modification_date = modification_date
+
+    def to_download_info(self) -> Optional[IliasDownloadInfo]:
+        """
+        Converts this crawler entry to an IliasDownloadInfo, if possible.
+        This method will only succeed for *File* types.
+        """
+        if self.entry_type in [IliasElementType.REGULAR_FILE, IliasElementType.VIDEO_FILE]:
+            return IliasDownloadInfo(self.path, self.url, self.modification_date)
+        return None
 
 
 class IliasCrawler:
@@ -62,12 +104,6 @@ class IliasCrawler:
         self._authenticator = authenticator
         self.dir_filter = dir_filter
 
-    def _abs_url_from_link(self, link_tag: bs4.Tag) -> str:
-        """
-        Create an absolute url from an <a> tag.
-        """
-        return urljoin(self._base_url, link_tag.get("href"))
-
     @staticmethod
     def _url_set_query_param(url: str, param: str, value: str) -> str:
         """
@@ -80,6 +116,16 @@ class IliasCrawler:
 
         return urlunsplit((scheme, netloc, path, new_query_string, fragment))
 
+    def recursive_crawl_url(self, url: str) -> List[IliasDownloadInfo]:
+        """
+        Crawls a given url *and all reachable elements in it*.
+
+        Args:
+            url {str} -- the *full* url to crawl
+        """
+        start_entries: List[IliasCrawlerEntry] = self._crawl_folder(Path(""), url)
+        return self._iterate_entries_to_download_infos(start_entries)
+
     def crawl_course(self, course_id: str) -> List[IliasDownloadInfo]:
         """
         Starts the crawl process for a course, yielding a list of elements to (potentially)
@@ -98,15 +144,43 @@ class IliasCrawler:
 
         if not self._is_course_id_valid(root_url, course_id):
             raise FatalException(
-                "Invalid course id? The URL the server returned did not contain my id."
+                "Invalid course id? I didn't find anything looking like a course!"
             )
 
         # And treat it as a folder
-        return self._crawl_folder(Path(""), root_url)
+        entries: List[IliasCrawlerEntry] = self._crawl_folder(Path(""), root_url)
+        return self._iterate_entries_to_download_infos(entries)
 
     def _is_course_id_valid(self, root_url: str, course_id: str) -> bool:
         response: requests.Response = self._session.get(root_url)
-        return course_id in response.url
+        # We were redirected ==> Non-existant ID
+        if course_id not in response.url:
+            return False
+
+        link_element: bs4.Tag = self._get_page(root_url, {}).find(id="current_perma_link")
+        if not link_element:
+            return False
+        # It wasn't a course but a category list, forum, etc.
+        return "crs_" in link_element.get("value")
+
+    def find_course_name(self, course_id: str) -> Optional[str]:
+        """
+        Returns the name of a given course. None if it is not a valid course
+        or it could not be found.
+        """
+        course_url = self._url_set_query_param(
+            self._base_url + "/goto.php", "target", f"crs_{course_id}"
+        )
+        return self.find_element_name(course_url)
+
+    def find_element_name(self, url: str) -> Optional[str]:
+        """
+        Returns the name of the element at the given URL, if it can find one.
+        """
+        focus_element: bs4.Tag = self._get_page(url, {}).find(id="il_mhead_t_focus")
+        if not focus_element:
+            return None
+        return focus_element.text
 
     def crawl_personal_desktop(self) -> List[IliasDownloadInfo]:
         """
@@ -115,14 +189,101 @@ class IliasCrawler:
         Raises:
             FatalException: if an unrecoverable error occurs
         """
-        return self._crawl_folder(Path(""), self._base_url + "?baseClass=ilPersonalDesktopGUI")
+        entries: List[IliasCrawlerEntry] = self._crawl_folder(
+            Path(""), self._base_url + "?baseClass=ilPersonalDesktopGUI"
+        )
+        return self._iterate_entries_to_download_infos(entries)
 
-    def _switch_on_crawled_type(
+    def _iterate_entries_to_download_infos(
             self,
+            entries: List[IliasCrawlerEntry]
+    ) -> List[IliasDownloadInfo]:
+        result: List[IliasDownloadInfo] = []
+        entries_to_process: List[IliasCrawlerEntry] = entries.copy()
+        while len(entries_to_process) > 0:
+            entry = entries_to_process.pop()
+
+            if entry.entry_type == IliasElementType.EXTERNAL_LINK:
+                PRETTY.not_searching(entry.path, "external link")
+                continue
+            if entry.entry_type == IliasElementType.FORUM:
+                PRETTY.not_searching(entry.path, "forum")
+                continue
+
+            if entry.entry_type.is_folder() and not self.dir_filter(entry.path, entry.entry_type):
+                PRETTY.not_searching(entry.path, "user filter")
+                continue
+
+            download_info = entry.to_download_info()
+            if download_info is not None:
+                result.append(download_info)
+                continue
+
+            url = entry.url()
+
+            if url is None:
+                PRETTY.warning(f"Could not find url for {str(entry.path)!r}, skipping it")
+                continue
+
+            PRETTY.searching(entry.path)
+
+            if entry.entry_type == IliasElementType.EXERCISE_FOLDER:
+                entries_to_process += self._crawl_exercises(entry.path, url)
+                continue
+            if entry.entry_type == IliasElementType.REGULAR_FOLDER:
+                entries_to_process += self._crawl_folder(entry.path, url)
+                continue
+            if entry.entry_type == IliasElementType.VIDEO_FOLDER:
+                entries_to_process += self._crawl_video_directory(entry.path, url)
+                continue
+
+        return result
+
+    def _crawl_folder(self, folder_path: Path, url: str) -> List[IliasCrawlerEntry]:
+        """
+        Crawl all files in a folder-like element.
+        """
+        soup = self._get_page(url, {})
+
+        if soup.find(id="headerimage"):
+            element: bs4.Tag = soup.find(id="headerimage")
+            if "opencast" in element.attrs["src"].lower():
+                PRETTY.warning(f"Switched to crawling a video at {folder_path}")
+                if not self.dir_filter(folder_path, IliasElementType.VIDEO_FOLDER):
+                    PRETTY.not_searching(folder_path, "user filter")
+                    return []
+                return self._crawl_video_directory(folder_path, url)
+
+        result: List[IliasCrawlerEntry] = []
+
+        # Fetch all links and throw them to the general interpreter
+        links: List[bs4.Tag] = soup.select("a.il_ContainerItemTitle")
+        for link in links:
+            abs_url = self._abs_url_from_link(link)
+            element_path = Path(folder_path, link.getText().strip())
+            element_type = self._find_type_from_link(element_path, link, abs_url)
+
+            if element_type == IliasElementType.REGULAR_FILE:
+                result += self._crawl_file(folder_path, link, abs_url)
+            elif element_type is not None:
+                result += [IliasCrawlerEntry(element_path, abs_url, element_type, None)]
+            else:
+                PRETTY.warning(f"Found element without a type at {str(element_path)!r}")
+
+        return result
+
+    def _abs_url_from_link(self, link_tag: bs4.Tag) -> str:
+        """
+        Create an absolute url from an <a> tag.
+        """
+        return urljoin(self._base_url, link_tag.get("href"))
+
+    @staticmethod
+    def _find_type_from_link(
             path: Path,
             link_element: bs4.Tag,
             url: str
-    ) -> List[IliasDownloadInfo]:
+    ) -> Optional[IliasElementType]:
         """
         Decides which sub crawler to use for a given top level element.
         """
@@ -131,28 +292,64 @@ class IliasCrawler:
 
         # file URLs contain "target=file"
         if "target=file_" in parsed_url.query:
-            LOGGER.debug("Interpreted as file.")
+            return IliasElementType.REGULAR_FILE
-            return self._crawl_file(path, link_element, url)
 
         # Skip forums
         if "cmd=showThreads" in parsed_url.query:
-            LOGGER.debug("Skipping forum %r", url)
+            return IliasElementType.FORUM
-            return []
 
         # Everything with a ref_id can *probably* be opened to reveal nested things
         # video groups, directories, exercises, etc
         if "ref_id=" in parsed_url.query:
-            LOGGER.debug("Processing folder-like...")
+            return IliasCrawler._find_type_from_folder_like(link_element, url)
-            return self._switch_on_folder_like(path, link_element, url)
 
         PRETTY.warning(
-            "Got unkwarning element type in switch. I am not sure what horror I found on the"
+            "Got unknown element type in switch. I am not sure what horror I found on the"
             f" ILIAS page. The element was at {str(path)!r} and it is {link_element!r})"
         )
-        return []
+        return None
 
     @staticmethod
-    def _crawl_file(path: Path, link_element: bs4.Tag, url: str) -> List[IliasDownloadInfo]:
+    def _find_type_from_folder_like(link_element: bs4.Tag, url: str) -> Optional[IliasElementType]:
+        """
+        Try crawling something that looks like a folder.
+        """
+        # pylint: disable=too-many-return-statements
+
+        # We look for the outer div of our inner link, to find information around it
+        # (mostly the icon)
+        for parent in link_element.parents:
+            if "ilContainerListItemOuter" in parent["class"]:
+                found_parent = parent
+                break
+
+        if found_parent is None:
+            PRETTY.warning(f"Could not find element icon for {url!r}")
+            return None
+
+        # Find the small descriptive icon to figure out the type
+        img_tag: Optional[bs4.Tag] = found_parent.select_one("img.ilListItemIcon")
+
+        if img_tag is None:
+            PRETTY.warning(f"Could not find image tag for {url!r}")
+            return None
+
+        if "opencast" in str(img_tag["alt"]).lower():
+            return IliasElementType.VIDEO_FOLDER
+
+        if str(img_tag["src"]).endswith("icon_exc.svg"):
+            return IliasElementType.EXERCISE_FOLDER
+
+        if str(img_tag["src"]).endswith("icon_webr.svg"):
+            return IliasElementType.EXTERNAL_LINK
+
+        if str(img_tag["src"]).endswith("frm.svg"):
+            return IliasElementType.FORUM
+
+        return IliasElementType.REGULAR_FOLDER
+
+    @staticmethod
+    def _crawl_file(path: Path, link_element: bs4.Tag, url: str) -> List[IliasCrawlerEntry]:
         """
         Crawls a file.
         """
@@ -183,80 +380,11 @@ class IliasCrawler:
         name = link_element.getText()
         full_path = Path(path, name + "." + file_type)
 
-        return [IliasDownloadInfo(full_path, url, modification_date)]
+        return [
+            IliasCrawlerEntry(full_path, url, IliasElementType.REGULAR_FILE, modification_date)
+        ]
 
-    def _switch_on_folder_like(
+    def _crawl_video_directory(self, video_dir_path: Path, url: str) -> List[IliasCrawlerEntry]:
-            self,
-            parent_path: Path,
-            link_element: bs4.Tag,
-            url: str
-    ) -> List[IliasDownloadInfo]:
-        """
-        Try crawling something that looks like a folder.
-        """
-        # pylint: disable=too-many-return-statements
-
-        element_path = Path(parent_path, link_element.getText().strip())
-
-        found_parent: Optional[bs4.Tag] = None
-
-        # We look for the outer div of our inner link, to find information around it
-        # (mostly the icon)
-        for parent in link_element.parents:
-            if "ilContainerListItemOuter" in parent["class"]:
-                found_parent = parent
-                break
-
-        if found_parent is None:
-            PRETTY.warning(f"Could not find element icon for {url!r}")
-            return []
-
-        # Find the small descriptive icon to figure out the type
-        img_tag: Optional[bs4.Tag] = found_parent.select_one("img.ilListItemIcon")
-
-        if img_tag is None:
-            PRETTY.warning(f"Could not find image tag for {url!r}")
-            return []
-
-        directory_type = IliasDirectoryType.FOLDER
-
-        if "opencast" in str(img_tag["alt"]).lower():
-            directory_type = IliasDirectoryType.VIDEO
-
-        if str(img_tag["src"]).endswith("icon_exc.svg"):
-            directory_type = IliasDirectoryType.EXERCISE
-
-        if not self.dir_filter(element_path, directory_type):
-            PRETTY.not_searching(element_path, "user filter")
-            return []
-
-        PRETTY.searching(element_path)
-
-        # A forum
-        if str(img_tag["src"]).endswith("frm.svg"):
-            LOGGER.debug("Skipping forum at %r", url)
-            PRETTY.not_searching(element_path, "forum")
-            return []
-
-        # An exercise
-        if directory_type == IliasDirectoryType.EXERCISE:
-            LOGGER.debug("Crawling exercises at %r", url)
-            return self._crawl_exercises(element_path, url)
-
-        if str(img_tag["src"]).endswith("icon_webr.svg"):
-            LOGGER.debug("Skipping external link at %r", url)
-            PRETTY.not_searching(element_path, "external link")
-            return []
-
-        # Match the opencast video plugin
-        if directory_type == IliasDirectoryType.VIDEO:
-            LOGGER.debug("Found video site: %r", url)
-            return self._crawl_video_directory(element_path, url)
-
-        # Assume it is a folder
-        return self._crawl_folder(element_path, self._abs_url_from_link(link_element))
-
-    def _crawl_video_directory(self, video_dir_path: Path, url: str) -> List[IliasDownloadInfo]:
         """
         Crawl the video overview site.
         """
@@ -272,6 +400,71 @@ class IliasCrawler:
             {"limit": 800, "cmd": "asyncGetTableGUI", "cmdMode": "asynch"}
         )
 
+        # If we find a page selected, we probably need to respect pagination
+        if self._is_paginated_video_page(video_list_soup):
+            second_stage_url = self._abs_url_from_link(content_link)
+
+            return self._crawl_paginated_video_directory(
+                video_dir_path, video_list_soup, second_stage_url
+            )
+
+        return self._crawl_video_directory_second_stage(video_dir_path, video_list_soup)
+
+    @staticmethod
+    def _is_paginated_video_page(soup: bs4.BeautifulSoup) -> bool:
+        return soup.find(id=re.compile(r"tab_page_sel.+")) is not None
+
+    def _crawl_paginated_video_directory(
+            self,
+            video_dir_path: Path,
+            paged_video_list_soup: bs4.BeautifulSoup,
+            second_stage_url: str
+    ) -> List[IliasCrawlerEntry]:
+        LOGGER.info("Found paginated video page, trying 800 elements")
+
+        # Try to find the table id. This can be used to build the query parameter indicating
+        # you want 800 elements
+
+        table_element: bs4.Tag = paged_video_list_soup.find(
+            name="table", id=re.compile(r"tbl_xoct_.+")
+        )
+        if table_element is None:
+            PRETTY.warning(
+                "Could not increase elements per page (table not found)."
+                " Some might not be crawled!"
+            )
+            return self._crawl_video_directory_second_stage(video_dir_path, paged_video_list_soup)
+
+        match = re.match(r"tbl_xoct_(.+)", table_element.attrs["id"])
+        if match is None:
+            PRETTY.warning(
+                "Could not increase elements per page (table id not found)."
+                " Some might not be crawled!"
+            )
+            return self._crawl_video_directory_second_stage(video_dir_path, paged_video_list_soup)
+        table_id = match.group(1)
+
+        extended_video_page = self._get_page(
+            second_stage_url,
+            {f"tbl_xoct_{table_id}_trows": 800, "cmd": "asyncGetTableGUI", "cmdMode": "asynch"}
+        )
+
+        if self._is_paginated_video_page(extended_video_page):
+            PRETTY.warning(
+                "800 elements do not seem to be enough (or I failed to fetch that many)."
+                " I will miss elements."
+            )
+
+        return self._crawl_video_directory_second_stage(video_dir_path, extended_video_page)
+
+    def _crawl_video_directory_second_stage(
+            self,
+            video_dir_path: Path,
+            video_list_soup: bs4.BeautifulSoup
+    ) -> List[IliasCrawlerEntry]:
+        """
+        Crawls the "second stage" video page. This page contains the actual video urls.
+        """
         direct_download_links: List[bs4.Tag] = video_list_soup.findAll(
             name="a", text=re.compile(r"\s*Download\s*")
         )
@@ -281,10 +474,11 @@ class IliasCrawler:
             name="a", text=re.compile(r"\s*Abspielen\s*")
         )
 
-        results: List[IliasDownloadInfo] = []
+        results: List[IliasCrawlerEntry] = []
 
         # We can download everything directly!
-        if len(direct_download_links) == len(video_links):
+        # FIXME: Sadly the download button is currently broken, so never do that
+        if False and len(direct_download_links) == len(video_links):
             for link in direct_download_links:
                 results += self._crawl_single_video(video_dir_path, link, True)
         else:
@@ -298,7 +492,7 @@ class IliasCrawler:
             parent_path: Path,
             link: bs4.Tag,
             direct_download: bool
-    ) -> List[IliasDownloadInfo]:
+    ) -> List[IliasCrawlerEntry]:
         """
         Crawl a single video based on its "Abspielen" link from the video listing.
         """
@@ -316,46 +510,54 @@ class IliasCrawler:
 
         video_path: Path = Path(parent_path, title)
 
+        video_url = self._abs_url_from_link(link)
+
         # The video had a direct download button we can use instead
         if direct_download:
             LOGGER.debug("Using direct download for video %r", str(video_path))
-            return [IliasDownloadInfo(
+            return [IliasCrawlerEntry(
-                video_path,
+                video_path, video_url, IliasElementType.VIDEO_FILE, modification_time
-                self._abs_url_from_link(link),
-                modification_time
             )]
 
-        # Fetch the actual video page. This is a small wrapper page initializing a javscript
+        return [IliasCrawlerEntry(
-        # player. Sadly we can not execute that JS. The actual video stream url is nowhere
+            video_path,
-        # on the page, but defined in a JS object inside a script tag, passed to the player
+            self._crawl_video_url_from_play_link(video_url),
-        # library.
+            IliasElementType.VIDEO_FILE,
-        # We do the impossible and RegEx the stream JSON object out of the page's HTML source
+            modification_time
-        video_page_url = self._abs_url_from_link(link)
+        )]
-        video_page_soup = self._get_page(video_page_url, {})
-        regex: re.Pattern = re.compile(
-            r"({\"streams\"[\s\S]+?),\s*{\"paella_config_file", re.IGNORECASE
-        )
-        json_match = regex.search(str(video_page_soup))
 
-        if json_match is None:
+    def _crawl_video_url_from_play_link(self, play_url: str) -> Callable[[], Optional[str]]:
-            PRETTY.warning(f"Could not find json stream info for {video_page_url!r}")
+        def inner() -> Optional[str]:
-            return []
+            # Fetch the actual video page. This is a small wrapper page initializing a javscript
-        json_str = json_match.group(1)
+            # player. Sadly we can not execute that JS. The actual video stream url is nowhere
+            # on the page, but defined in a JS object inside a script tag, passed to the player
+            # library.
+            # We do the impossible and RegEx the stream JSON object out of the page's HTML source
+            video_page_soup = soupify(self._session.get(play_url))
+            regex: re.Pattern = re.compile(
+                r"({\"streams\"[\s\S]+?),\s*{\"paella_config_file", re.IGNORECASE
+            )
+            json_match = regex.search(str(video_page_soup))
 
-        # parse it
+            if json_match is None:
-        json_object = json.loads(json_str)
+                PRETTY.warning(f"Could not find json stream info for {play_url!r}")
-        # and fetch the video url!
+                return None
-        video_url = json_object["streams"][0]["sources"]["mp4"][0]["src"]
+            json_str = json_match.group(1)
 
-        return [IliasDownloadInfo(video_path, video_url, modification_time)]
+            # parse it
+            json_object = json.loads(json_str)
+            # and fetch the video url!
+            video_url = json_object["streams"][0]["sources"]["mp4"][0]["src"]
+            return video_url
+        return inner
 
-    def _crawl_exercises(self, element_path: Path, url: str) -> List[IliasDownloadInfo]:
+    def _crawl_exercises(self, element_path: Path, url: str) -> List[IliasCrawlerEntry]:
         """
         Crawl files offered for download in exercises.
         """
         soup = self._get_page(url, {})
 
-        results: List[IliasDownloadInfo] = []
+        results: List[IliasCrawlerEntry] = []
 
         # Each assignment is in an accordion container
         assignment_containers: List[bs4.Tag] = soup.select(".il_VAccordionInnerContainer")
@@ -382,30 +584,15 @@ class IliasCrawler:
 
                 LOGGER.debug("Found file %r at %r", file_name, url)
 
-                results.append(IliasDownloadInfo(
+                results.append(IliasCrawlerEntry(
                     Path(element_path, container_name, file_name),
                     url,
+                    IliasElementType.REGULAR_FILE,
                     None  # We do not have any timestamp
                 ))
 
         return results
 
-    def _crawl_folder(self, folder_path: Path, url: str) -> List[IliasDownloadInfo]:
-        """
-        Crawl all files in a folder-like element.
-        """
-        soup = self._get_page(url, {})
-
-        result: List[IliasDownloadInfo] = []
-
-        # Fetch all links and throw them to the general interpreter
-        links: List[bs4.Tag] = soup.select("a.il_ContainerItemTitle")
-        for link in links:
-            abs_url = self._abs_url_from_link(link)
-            result += self._switch_on_crawled_type(folder_path, link, abs_url)
-
-        return result
-
     def _get_page(self, url: str, params: Dict[str, Any]) -> bs4.BeautifulSoup:
         """
         Fetches a page from ILIAS, authenticating when needed.
@@ -416,8 +603,10 @@ class IliasCrawler:
         content_type = response.headers["content-type"]
 
         if not content_type.startswith("text/html"):
-            # TODO: Correct exception type
+            raise FatalException(
-            raise Exception(f"Invalid content type {content_type}")
+                f"Invalid content type {content_type} when crawling ilias page"
+                " {url!r} with {params!r}"
+            )
 
         soup = soupify(response)
 

PFERD/ilias/downloader.py

@@ -2,9 +2,10 @@
 
 import datetime
 import logging
-from dataclasses import dataclass
+import math
-from pathlib import Path
+import os
-from typing import Callable, List, Optional
+from pathlib import Path, PurePath
+from typing import Callable, List, Optional, Union
 
 import bs4
 import requests
@@ -24,15 +25,24 @@ class ContentTypeException(Exception):
     """Thrown when the content type of the ilias element can not be handled."""
 
 
-@dataclass
 class IliasDownloadInfo(Transformable):
     """
     This class describes a single file to be downloaded.
     """
 
-    url: str
+    def __init__(
-    modification_date: Optional[datetime.datetime]
+            self,
-    # parameters: Dict[str, Any] = field(default_factory=dict)
+            path: PurePath,
+            url: Union[str, Callable[[], Optional[str]]],
+            modifcation_date: Optional[datetime.datetime]
+    ):
+        super().__init__(path)
+        if isinstance(url, str):
+            string_url = url
+            self.url: Callable[[], Optional[str]] = lambda: string_url
+        else:
+            self.url = url
+        self.modification_date = modifcation_date
 
 
 IliasDownloadStrategy = Callable[[Organizer, IliasDownloadInfo], bool]
@@ -74,9 +84,13 @@ class IliasDownloader:
             session: requests.Session,
             authenticator: IliasAuthenticator,
             strategy: IliasDownloadStrategy,
+            timeout: int = 5
     ):
         """
         Create a new IliasDownloader.
+
+        The timeout applies to the download request only, as bwcloud uses IPv6
+        and requests has a problem with that: https://github.com/psf/requests/issues/5522
         """
 
         self._tmp_dir = tmp_dir
@@ -84,6 +98,7 @@ class IliasDownloader:
         self._session = session
         self._authenticator = authenticator
         self._strategy = strategy
+        self._timeout = timeout
 
     def download_all(self, infos: List[IliasDownloadInfo]) -> None:
         """
@@ -108,16 +123,30 @@ class IliasDownloader:
         tmp_file = self._tmp_dir.new_path()
 
         while not self._try_download(info, tmp_file):
+            LOGGER.info("Retrying download: %r", info)
             self._authenticator.authenticate(self._session)
 
-        self._organizer.accept_file(tmp_file, info.path)
+        dst_path = self._organizer.accept_file(tmp_file, info.path)
+        if dst_path and info.modification_date:
+            os.utime(
+                dst_path,
+                times=(
+                    math.ceil(info.modification_date.timestamp()),
+                    math.ceil(info.modification_date.timestamp())
+                )
+            )
 
     def _try_download(self, info: IliasDownloadInfo, target: Path) -> bool:
-        with self._session.get(info.url, stream=True) as response:
+        url = info.url()
-            content_type = response.headers["content-type"]
+        if url is None:
+            PRETTY.warning(f"Could not download {str(info.path)!r} as I got no URL :/")
+            return True
 
-            if content_type.startswith("text/html"):
+        with self._session.get(url, stream=True, timeout=self._timeout) as response:
-                # Dangit, we're probably not logged in.
+            content_type = response.headers["content-type"]
+            has_content_disposition = "content-disposition" in response.headers
+
+            if content_type.startswith("text/html") and not has_content_disposition:
                 if self._is_logged_in(soupify(response)):
                     raise ContentTypeException("Attempting to download a web page, not a file")
 

PFERD/logging.py

@@ -3,14 +3,18 @@ Contains a few logger utility functions and implementations.
 """
 
 import logging
-from typing import Optional
+from pathlib import Path
+from typing import List, Optional
 
+from rich import print as rich_print
 from rich._log_render import LogRender
 from rich.console import Console
+from rich.panel import Panel
 from rich.style import Style
 from rich.text import Text
 from rich.theme import Theme
 
+from .download_summary import DownloadSummary
 from .utils import PathLike, to_path
 
 STYLE = "{"
@@ -111,6 +115,15 @@ class PrettyLogger:
             f"[bold green]Created {self._format_path(path)}.[/bold green]"
         )
 
+    def deleted_file(self, path: PathLike) -> None:
+        """
+        A file has been deleted.
+        """
+
+        self.logger.info(
+            f"[bold red]Deleted {self._format_path(path)}.[/bold red]"
+        )
+
     def ignored_file(self, path: PathLike, reason: str) -> None:
         """
         File was not downloaded or modified.
@@ -138,6 +151,23 @@ class PrettyLogger:
             f"([/dim]{reason}[dim]).[/dim]"
         )
 
+    def summary(self, download_summary: DownloadSummary) -> None:
+        """
+        Prints a download summary.
+        """
+        self.logger.info("")
+        self.logger.info("[bold cyan]Download Summary[/bold cyan]")
+        if not download_summary.has_updates():
+            self.logger.info("[bold dim]Nothing changed![/bold dim]")
+            return
+
+        for new_file in download_summary.new_files:
+            self.new_file(new_file)
+        for modified_file in download_summary.modified_files:
+            self.modified_file(modified_file)
+        for deleted_files in download_summary.deleted_files:
+            self.deleted_file(deleted_files)
+
     def starting_synchronizer(
             self,
             target_directory: PathLike,

PFERD/organizer.py

@@ -5,10 +5,12 @@ A organizer is bound to a single directory.
 
 import filecmp
 import logging
+import os
 import shutil
 from pathlib import Path, PurePath
-from typing import List, Set
+from typing import List, Optional, Set
 
+from .download_summary import DownloadSummary
 from .location import Location
 from .logging import PrettyLogger
 from .utils import prompt_yes_no
@@ -32,10 +34,28 @@ class Organizer(Location):
         # Keep the root dir
         self._known_files.add(path.resolve())
 
-    def accept_file(self, src: Path, dst: PurePath) -> None:
+        self.download_summary = DownloadSummary()
-        """Move a file to this organizer and mark it."""
+
-        src_absolute = src.resolve()
+    def accept_file(self, src: Path, dst: PurePath) -> Optional[Path]:
-        dst_absolute = self.resolve(dst)
+        """
+        Move a file to this organizer and mark it.
+
+        Returns the path the file was moved to, to allow the caller to adjust the metadata.
+        As you might still need to adjust the metadata when the file was identical
+        (e.g. update the timestamp), the path is also returned in this case.
+        In all other cases (ignored, not overwritten, etc.) this method returns None.
+        """
+        # Windows limits the path length to 260 for *some* historical reason
+        # If you want longer paths, you will have to add the "\\?\" prefix in front of
+        # your path...
+        # See:
+        # https://docs.microsoft.com/en-us/windows/win32/fileio/naming-a-file#maximum-path-length-limitation
+        if os.name == 'nt':
+            src_absolute = Path("\\\\?\\" + str(src.resolve()))
+            dst_absolute = Path("\\\\?\\" + str(self.resolve(dst)))
+        else:
+            src_absolute = src.resolve()
+            dst_absolute = self.resolve(dst)
 
         if not src_absolute.exists():
             raise FileAcceptException("Source file does not exist")
@@ -49,7 +69,7 @@ class Organizer(Location):
             PRETTY.warning(f"File {str(dst_absolute)!r} was already written!")
             if not prompt_yes_no(f"Overwrite file?", default=False):
                 PRETTY.ignored_file(dst_absolute, "file was written previously")
-                return
+                return None
 
         # Destination file is directory
         if dst_absolute.exists() and dst_absolute.is_dir():
@@ -57,7 +77,7 @@ class Organizer(Location):
                 shutil.rmtree(dst_absolute)
             else:
                 PRETTY.warning(f"Could not add file {str(dst_absolute)!r}")
-                return
+                return None
 
         # Destination file exists
         if dst_absolute.exists() and dst_absolute.is_file():
@@ -65,10 +85,12 @@ class Organizer(Location):
                 # Bail out, nothing more to do
                 PRETTY.ignored_file(dst_absolute, "same file contents")
                 self.mark(dst)
-                return
+                return dst_absolute
 
+            self.download_summary.add_modified_file(dst_absolute)
             PRETTY.modified_file(dst_absolute)
         else:
+            self.download_summary.add_new_file(dst_absolute)
             PRETTY.new_file(dst_absolute)
 
         # Create parent dir if needed
@@ -80,6 +102,8 @@ class Organizer(Location):
 
         self.mark(dst)
 
+        return dst_absolute
+
     def mark(self, path: PurePath) -> None:
         """Mark a file as used so it will not get cleaned up."""
         absolute_path = self.resolve(path)
@@ -115,9 +139,9 @@ class Organizer(Location):
         if start_dir.resolve() not in self._known_files and dir_empty:
             start_dir.rmdir()
 
-    @staticmethod
+    def _delete_file_if_confirmed(self, path: Path) -> None:
-    def _delete_file_if_confirmed(path: Path) -> None:
         prompt = f"Do you want to delete {path}"
 
         if prompt_yes_no(prompt, False):
+            self.download_summary.add_deleted_file(path)
             path.unlink()

PFERD/pferd.py

@@ -9,6 +9,7 @@ from typing import Callable, List, Optional, Union
 from .cookie_jar import CookieJar
 from .diva import (DivaDownloader, DivaDownloadStrategy, DivaPlaylistCrawler,
                    diva_download_new)
+from .download_summary import DownloadSummary
 from .errors import FatalException, swallow_and_print_errors
 from .ilias import (IliasAuthenticator, IliasCrawler, IliasDirectoryFilter,
                     IliasDownloader, IliasDownloadInfo, IliasDownloadStrategy,
@@ -42,10 +43,10 @@ class Pferd(Location):
     ):
         super().__init__(Path(base_dir))
 
+        self._download_summary = DownloadSummary()
         self._tmp_dir = TmpDir(self.resolve(tmp_dir))
         self._test_run = test_run
 
-
     @staticmethod
     def enable_logging() -> None:
         """
@@ -54,7 +55,6 @@ class Pferd(Location):
 
         enable_logging()
 
-
     @staticmethod
     def _print_transformables(transformables: List[TF]) -> None:
         LOGGER.info("")
@@ -72,7 +72,8 @@ class Pferd(Location):
             dir_filter: IliasDirectoryFilter,
             transform: Transform,
             download_strategy: IliasDownloadStrategy,
-            clean: bool = True
+            timeout: int,
+            clean: bool = True,
     ) -> Organizer:
         # pylint: disable=too-many-locals
         cookie_jar = CookieJar(to_path(cookies) if cookies else None)
@@ -81,7 +82,8 @@ class Pferd(Location):
         organizer = Organizer(self.resolve(to_path(target)))
 
         crawler = IliasCrawler(base_url, session, authenticator, dir_filter)
-        downloader = IliasDownloader(tmp_dir, organizer, session, authenticator, download_strategy)
+        downloader = IliasDownloader(tmp_dir, organizer, session,
+                                     authenticator, download_strategy, timeout)
 
         cookie_jar.load_cookies()
         info = crawl_function(crawler)
@@ -112,6 +114,7 @@ class Pferd(Location):
             password: Optional[str] = None,
             download_strategy: IliasDownloadStrategy = download_modified_or_new,
             clean: bool = True,
+            timeout: int = 5,
     ) -> Organizer:
         """
         Synchronizes a folder with the ILIAS instance of the KIT.
@@ -137,11 +140,14 @@ class Pferd(Location):
                 be downloaded. Can save bandwidth and reduce the number of requests.
                 (default: {download_modified_or_new})
             clean {bool} -- Whether to clean up when the method finishes.
+            timeout {int} -- The download timeout for opencast videos. Sadly needed due to a
+                requests bug.
         """
         # This authenticator only works with the KIT ilias instance.
         authenticator = KitShibbolethAuthenticator(username=username, password=password)
         PRETTY.starting_synchronizer(target, "ILIAS", course_id)
-        return self._ilias(
+
+        organizer = self._ilias(
             target=target,
             base_url="https://ilias.studium.kit.edu/",
             crawl_function=lambda crawler: crawler.crawl_course(course_id),
@@ -151,8 +157,19 @@ class Pferd(Location):
             transform=transform,
             download_strategy=download_strategy,
             clean=clean,
+            timeout=timeout
         )
 
+        self._download_summary.merge(organizer.download_summary)
+
+        return organizer
+
+    def print_summary(self) -> None:
+        """
+        Prints the accumulated download summary.
+        """
+        PRETTY.summary(self._download_summary)
+
     @swallow_and_print_errors
     def ilias_kit_personal_desktop(
             self,
@@ -164,6 +181,7 @@ class Pferd(Location):
             password: Optional[str] = None,
             download_strategy: IliasDownloadStrategy = download_modified_or_new,
             clean: bool = True,
+            timeout: int = 5,
     ) -> Organizer:
         """
         Synchronizes a folder with the ILIAS instance of the KIT. This method will crawl the ILIAS
@@ -188,11 +206,14 @@ class Pferd(Location):
                 be downloaded. Can save bandwidth and reduce the number of requests.
                 (default: {download_modified_or_new})
             clean {bool} -- Whether to clean up when the method finishes.
+            timeout {int} -- The download timeout for opencast videos. Sadly needed due to a
+                requests bug.
         """
         # This authenticator only works with the KIT ilias instance.
         authenticator = KitShibbolethAuthenticator(username=username, password=password)
         PRETTY.starting_synchronizer(target, "ILIAS", "Personal Desktop")
-        return self._ilias(
+
+        organizer = self._ilias(
             target=target,
             base_url="https://ilias.studium.kit.edu/",
             crawl_function=lambda crawler: crawler.crawl_personal_desktop(),
@@ -202,8 +223,77 @@ class Pferd(Location):
             transform=transform,
             download_strategy=download_strategy,
             clean=clean,
+            timeout=timeout
         )
 
+        self._download_summary.merge(organizer.download_summary)
+
+        return organizer
+
+    @swallow_and_print_errors
+    def ilias_kit_folder(
+            self,
+            target: PathLike,
+            full_url: str,
+            dir_filter: IliasDirectoryFilter = lambda x, y: True,
+            transform: Transform = lambda x: x,
+            cookies: Optional[PathLike] = None,
+            username: Optional[str] = None,
+            password: Optional[str] = None,
+            download_strategy: IliasDownloadStrategy = download_modified_or_new,
+            clean: bool = True,
+            timeout: int = 5,
+    ) -> Organizer:
+        """
+        Synchronizes a folder with a given folder on the ILIAS instance of the KIT.
+
+        Arguments:
+            target {Path}  -- the target path to write the data to
+            full_url {str} -- the full url of the folder/videos/course to crawl
+
+        Keyword Arguments:
+            dir_filter {IliasDirectoryFilter} -- A filter for directories. Will be applied on the
+                crawler level, these directories and all of their content is skipped.
+                (default: {lambdax:True})
+            transform {Transform} -- A transformation function for the output paths. Return None
+                to ignore a file. (default: {lambdax:x})
+            cookies {Optional[Path]} -- The path to store and load cookies from.
+                (default: {None})
+            username {Optional[str]} -- The SCC username. If none is given, it will prompt
+                the user. (default: {None})
+            password {Optional[str]} -- The SCC password. If none is given, it will prompt
+                the user. (default: {None})
+            download_strategy {DownloadStrategy} -- A function to determine which files need to
+                be downloaded. Can save bandwidth and reduce the number of requests.
+                (default: {download_modified_or_new})
+            clean {bool} -- Whether to clean up when the method finishes.
+            timeout {int} -- The download timeout for opencast videos. Sadly needed due to a
+                requests bug.
+        """
+        # This authenticator only works with the KIT ilias instance.
+        authenticator = KitShibbolethAuthenticator(username=username, password=password)
+        PRETTY.starting_synchronizer(target, "ILIAS", "An ILIAS element by url")
+
+        if not full_url.startswith("https://ilias.studium.kit.edu"):
+            raise FatalException("Not a valid KIT ILIAS URL")
+
+        organizer = self._ilias(
+            target=target,
+            base_url="https://ilias.studium.kit.edu/",
+            crawl_function=lambda crawler: crawler.recursive_crawl_url(full_url),
+            authenticator=authenticator,
+            cookies=cookies,
+            dir_filter=dir_filter,
+            transform=transform,
+            download_strategy=download_strategy,
+            clean=clean,
+            timeout=timeout
+        )
+
+        self._download_summary.merge(organizer.download_summary)
+
+        return organizer
+
     @swallow_and_print_errors
     def diva_kit(
             self,

PFERD/progress.py

@@ -7,8 +7,7 @@ from types import TracebackType
 from typing import Optional, Type
 
 import requests
-from rich.console import Console, ConsoleOptions, Control, RenderResult
+from rich.console import Console
-from rich.live_render import LiveRender
 from rich.progress import (BarColumn, DownloadColumn, Progress, TaskID,
                            TextColumn, TimeRemainingColumn,
                            TransferSpeedColumn)
@@ -23,7 +22,8 @@ _progress: Progress = Progress(
     TransferSpeedColumn(),
     "•",
     TimeRemainingColumn(),
-    console=Console(file=sys.stdout)
+    console=Console(file=sys.stdout),
+    transient=True
 )
 
 
@@ -61,18 +61,6 @@ def progress_for(settings: Optional[ProgressSettings]) -> 'ProgressContextManage
     return ProgressContextManager(settings)
 
 
-class _OneLineUp(LiveRender):
-    """
-    Render a control code for moving one line upwards.
-    """
-
-    def __init__(self) -> None:
-        super().__init__("not rendered")
-
-    def __console__(self, console: Console, options: ConsoleOptions) -> RenderResult:
-        yield Control(f"\r\x1b[1A")
-
-
 class ProgressContextManager:
     """
     A context manager used for displaying progress.
@@ -113,9 +101,6 @@ class ProgressContextManager:
             _progress.stop()
             _progress.refresh()
 
-            # And we existed, so remove the line above (remove_task leaves one behind)
-            Console().print(_OneLineUp())
-
         return None
 
     def advance(self, amount: float) -> None:

README.md

@@ -2,35 +2,65 @@
 
 **P**rogramm zum **F**lotten, **E**infachen **R**unterladen von **D**ateien
 
+- [Quickstart with `sync_url`](#quickstart-with-sync_url)
+- [Installation](#installation)
+    - [Upgrading from 2.0.0 to 2.1.0+](#upgrading-from-200-to-210)
+- [Example setup](#example-setup)
+- [Usage](#usage)
+    - [General concepts](#general-concepts)
+    - [Constructing transforms](#constructing-transforms)
+        - [Transform creators](#transform-creators)
+        - [Transform combinators](#transform-combinators)
+    - [A short, but commented example](#a-short-but-commented-example)
+
+## Quickstart with `sync_url`
+
+The `sync_url` program allows you to just synchronize a given ILIAS URL (of a
+course, a folder, your personal desktop, etc.) without any extra configuration
+or setting up. Download the program, open ILIAS, copy the URL from the address
+bar and pass it to sync_url.
+
+It bundles everything it needs in one executable and is easy to
+use, but doesn't expose all the configuration options and tweaks a full install
+does.
+
+1. Download the `sync_url` binary from the [latest release](https://github.com/Garmelon/PFERD/releases/latest).
+2. Run the binary in your terminal (`./sync_url` or `sync_url.exe` in the CMD) to see the help and use it. I'd recommend using the `--cookies` option.  
+  If you are on **Linux/Mac**, you need to *make the file executable* using `chmod +x <file>`.  
+  If you are on **Mac**, you need to allow this unverified program to run (see e.g. [here](https://www.switchingtomac.com/tutorials/osx/how-to-run-unverified-apps-on-macos/))
+
 ## Installation
 
 Ensure that you have at least Python 3.8 installed.
 
 To install PFERD or update your installation to the latest version, run this
-wherever you want to install/have installed PFERD:
+wherever you want to install or have already installed PFERD:
 ```
-$ pip install git+https://github.com/Garmelon/PFERD@v2.0.0
+$ pip install git+https://github.com/Garmelon/PFERD@v2.4.1
 ```
 
-The use of [venv](https://docs.python.org/3/library/venv.html) is recommended.
+The use of [venv] is recommended.
+
+[venv]: https://docs.python.org/3/library/venv.html
+
+### Upgrading from 2.0.0 to 2.1.0+
+
+- The `IliasDirectoryType` type was renamed to `IliasElementType` and is now far more detailed.
+  The new values are: `REGULAR_FOLDER`, `VIDEO_FOLDER`, `EXERCISE_FOLDER`, `REGULAR_FILE`, `VIDEO_FILE`, `FORUM`, `EXTERNAL_LINK`.
+- Forums and external links are skipped automatically if you use the `kit_ilias` helper.
 
 ## Example setup
 
 In this example, `python3` refers to at least Python 3.8.
 
-If you just want to get started and crawl *your entire ILIAS Desktop* instead
-of a given set of courses, please replace `example_config.py` with
-`example_config_personal_desktop.py` in all of the instructions below (`curl` call and
-`python3` run command).
-
 A full example setup and initial use could look like:
 ```
 $ mkdir Vorlesungen
 $ cd Vorlesungen
 $ python3 -m venv .venv
 $ .venv/bin/activate
-$ pip install git+https://github.com/Garmelon/PFERD@v2.0.0
+$ pip install git+https://github.com/Garmelon/PFERD@v2.4.1
-$ curl -O https://raw.githubusercontent.com/Garmelon/PFERD/v2.0.0/example_config.py
+$ curl -O https://raw.githubusercontent.com/Garmelon/PFERD/v2.4.1/example_config.py
 $ python3 example_config.py
 $ deactivate
 ```
@@ -43,50 +73,93 @@ $ python3 example_config.py
 $ deactivate
 ```
 
+If you just want to get started and crawl *your entire ILIAS Desktop* instead
+of a given set of courses, please replace `example_config.py` with
+`example_config_personal_desktop.py` in all of the instructions below (`curl` call and
+`python3` run command).
+
 ## Usage
 
+### General concepts
+
 A PFERD config is a normal python file that starts multiple *synchronizers*
 which do all the heavy lifting. While you can create and wire them up manually,
 you are encouraged to use the helper methods provided in `PFERD.Pferd`.
 
 The synchronizers take some input arguments specific to their service and a
-*transformer*. The transformer receives the computed path of an element in
+*transform*. The transform receives the computed path of an element in ILIAS and
-ILIAS and can return either an output path (so you can rename files or move
+can return either an output path (so you can rename files or move them around as
-them around as you wish) or `None` if you do not want to save the given file.
+you wish) or `None` if you do not want to save the given file.
 
 Additionally the ILIAS synchronizer allows you to define a *crawl filter*. This
-filter also receives the computed path as the input, but is only called or
+filter also receives the computed path as the input, but is only called for
-*directoties*. If you return `True`, the directory will be crawled and
+*directories*. If you return `True`, the directory will be crawled and
 searched. If you return `False` the directory will be ignored and nothing in it
-will be passed to the transformer.
+will be passed to the transform.
 
-In order to help you with writing your own transformers and filters, PFERD
+### Constructing transforms
-ships with a few powerful building blocks:
 
-| Method | Description |
+While transforms are just normal python functions, writing them by hand can
-|--------|-------------|
+quickly become tedious. In order to help you with writing your own transforms
-| `glob`   | Returns a transform that returns `None` if the glob does not match and the unmodified path otherwise. |
+and filters, PFERD defines a few useful transform creators and combinators in
-| `predicate`   | Returns a transform that returns `None` if the predicate does not match the path and the unmodified path otherwise. |
+the `PFERD.transform` module:
-| `move_dir(source, target)`   | Returns a transform that moves all files from the `source` to the `target` dir. |
-| `move(source, target)`   | Returns a transform that moves the `source` file to `target`. |
-| `rename(old, new)`   | Renames a single file. |
-| `re_move(regex, sub)`   | Moves all files matching the given regular expression. The different captured groups are available under their index and can be used together with normal python format methods: `re_move(r"Blatt (\d+)\.pdf", "Blätter/Blatt_{1:0>2}.pdf"),`. |
-| `re_rename(old, new)`   | Same as `re_move` but operates on the path *names* instead of the full path. |
 
-And PFERD also offers a few combinator functions:
+#### Transform creators
 
-* **`keep`**  
+These methods let you create a few basic transform building blocks:
-  `keep` just returns the input path unchanged. It can be very useful as the
+
-  last argument in an `attempt` call, to leave everything not matching a rule
+- **`glob(glob)`**  
-  unchanged.
+  Creates a transform that returns the unchanged path if the glob matches the path and `None` otherwise.
-* **`optionally(transformer)`**  
+  See also [Path.match].  
-  Wraps a given transformer and returns its result if it is not `None`.
+  Example: `glob("Übung/*.pdf")`
+- **`predicate(pred)`**  
+  Creates a transform that returns the unchanged path if `pred(path)` returns a truthy value.
+  Returns `None` otherwise.  
+  Example: `predicate(lambda path: len(path.parts) == 3)`
+- **`move_dir(source, target)`**  
+  Creates a transform that moves all files from the `source` to the `target` directory.  
+  Example: `move_dir("Übung/", "Blätter/")`
+- **`move(source, target)`**  
+  Creates a transform that moves the `source` file to `target`.  
+  Example: `move("Vorlesung/VL02_Automten.pdf", "Vorlesung/VL02_Automaten.pdf")`
+- **`rename(source, target)`**  
+  Creates a transform that renames all files named `source` to `target`.
+  This transform works on the file names, not paths, and thus works no matter where the file is located.  
+  Example: `rename("VL02_Automten.pdf", "VL02_Automaten.pdf")`
+- **`re_move(regex, target)`**  
+  Creates a transform that moves all files matching `regex` to `target`.
+  The transform `str.format` on the `target` string with the contents of the capturing groups before returning it.
+  The capturing groups can be accessed via their index.
+  See also [Match.group].  
+  Example: `re_move(r"Übung/Blatt (\d+)\.pdf", "Blätter/Blatt_{1:0>2}.pdf")`
+- **`re_rename(regex, target)`**  
+  Creates a transform that renames all files matching `regex` to `target`.
+  This transform works on the file names, not paths, and thus works no matter where the file is located.  
+  Example: `re_rename(r"VL(\d+)(.*)\.pdf", "Vorlesung_Nr_{1}__{2}.pdf")`
+
+All movement or rename transforms above return `None` if a file doesn't match
+their movement or renaming criteria. This enables them to be used as building
+blocks to build up more complex transforms.
+
+In addition, `PFERD.transform` also defines the `keep` transform which returns its input path unchanged.
+This behaviour can be very useful when creating more complex transforms.
+See below for example usage.
+
+[Path.match]: https://docs.python.org/3/library/pathlib.html#pathlib.Path.match
+[Match.group]: https://docs.python.org/3/library/re.html#re.Match.group
+
+#### Transform combinators
+
+These methods let you combine transforms into more complex transforms:
+
+- **`optionally(transform)`**  
+  Wraps a given transform and returns its result if it is not `None`.
   Otherwise returns the input path unchanged.
-* **`do(transformers)`**  
+  See below for example usage.
-  `do` accepts a series of transformers and applies them in the given order to
+* **`do(transforms)`**  
-  the result of the previous one. If any transformer returns `None`, do
+  Accepts a series of transforms and applies them in the given order to the result of the previous one.
-  short-circuits and also returns `None`. This can be used to perform multiple
+  If any transform returns `None`, `do` short-circuits and also returns `None`.
-  renames in a row:
+  This can be used to perform multiple renames in a row:
   ```py
   do(
       # Move them
@@ -95,13 +168,12 @@ And PFERD also offers a few combinator functions:
       optionally(re_rename("(.*).m4v.mp4", "{1}.mp4")),
       # Remove the 'dbs' prefix (if they have any)
       optionally(re_rename("(?i)dbs-(.+)", "{1}")),
-  ),
+  )
   ```
-* **`attempt(transformers)`**  
+- **`attempt(transforms)`**  
-  `attempt` applies the passed transformers in the given order until it finds
+  Applies the passed transforms in the given order until it finds one that does not return `None`.
-  one that does not return `None`. If it does not find any, it returns `None`.
+  If it does not find any, it returns `None`.
-  This can be used to give a list of possible transformations and it will
+  This can be used to give a list of possible transformations and automatically pick the first one that fits:
-  automatically pick the first one that fits:
   ```py
   attempt(
       # Move all videos. If a video is passed in, this `re_move` will succeed
@@ -114,17 +186,26 @@ And PFERD also offers a few combinator functions:
   )
   ```
 
-All of these combinators are used in the provided example config, if you want
+All of these combinators are used in the provided example configs, if you want
-to see some more true-to-live usages.
+to see some more real-life usages.
 
 ### A short, but commented example
 
 ```py
-def filter_course(path: PurePath) -> bool:
+from pathlib import Path, PurePath
-    # Note that glob returns a Transformer
+from PFERD import Pferd
-    #  - a function from PurePath -> Optional[PurePath]
+from PFERD.ilias import IliasElementType
-    # So we need to apply the result of 'glob' to our input path.
+from PFERD.transform import *
-    # We need to crawl the 'Tutorien' folder as it contains the one we want.
+
+# This filter will later be used by the ILIAS crawler to decide whether it
+# should crawl a directory (or directory-like structure).
+def filter_course(path: PurePath, type: IliasElementType) -> bool:
+    # Note that glob returns a Transform, which is a function from PurePath ->
+    # Optional[PurePath]. Because of this, we need to apply the result of
+    # 'glob' to our input path. The returned value will be truthy (a Path) if
+    # the transform succeeded, or `None` if it failed.
+
+    # We need to crawl the 'Tutorien' folder as it contains one that we want.
     if glob("Tutorien/")(path):
         return True
     # If we found 'Tutorium 10', keep it!
@@ -137,21 +218,35 @@ def filter_course(path: PurePath) -> bool:
     # All other dirs (including subdirs of 'Tutorium 10') should be searched :)
     return True
 
-enable_logging() # needed once before calling a Pferd method
+
-# Create a Pferd instance rooted in the same directory as the script file
+# This transform will later be used to rename a few files. It can also be used
-# This is not a test run, so files will be downloaded (default, can be omitted)
+# to ignore some files.
+transform_course = attempt(
+    # We don't care about the other tuts and would instead prefer a cleaner
+    # directory structure.
+    move_dir("Tutorien/Tutorium 10/", "Tutorium/"),
+    # We don't want to modify any other files, so we're going to keep them
+    # exactly as they are.
+    keep
+)
+
+# Enable and configure the text output. Needs to be called before calling any
+# other PFERD methods.
+Pferd.enable_logging()
+# Create a Pferd instance rooted in the same directory as the script file. This
+# is not a test run, so files will be downloaded (default, can be omitted).
 pferd = Pferd(Path(__file__).parent, test_run=False)
 
 # Use the ilias_kit helper to synchronize an ILIAS course
 pferd.ilias_kit(
-    # The folder all of the course's content should be placed in
+    # The directory that all of the downloaded files should be placed in
-    Path("My cool course"),
+    "My_cool_course/",
     # The course ID (found in the URL when on the course page in ILIAS)
     "course id",
-    # A path to a cookie jar. If you synchronize multiple ILIAS courses, setting this
+    # A path to a cookie jar. If you synchronize multiple ILIAS courses,
-    # to a common value requires you to only login once.
+    # setting this to a common value requires you to only log in once.
     cookies=Path("ilias_cookies.txt"),
-    # A transform to apply to all found paths
+    # A transform can rename, move or filter out certain files
     transform=transform_course,
     # A crawl filter limits what paths the cralwer searches
     dir_filter=filter_course,

example_config.py

@@ -2,7 +2,7 @@ import argparse
 from pathlib import Path, PurePath
 
 from PFERD import Pferd
-from PFERD.ilias import IliasDirectoryType
+from PFERD.ilias import IliasElementType
 from PFERD.transform import (attempt, do, glob, keep, move, move_dir,
                              optionally, re_move, re_rename)
 
@@ -49,7 +49,7 @@ tf_ss_2020_pg = attempt(
 )
 
 
-def df_ss_2020_or1(path: PurePath, _type: IliasDirectoryType) -> bool:
+def df_ss_2020_or1(path: PurePath, _type: IliasElementType) -> bool:
     if glob("Tutorien/")(path):
         return True
     if glob("Tutorien/Tutorium 10, dienstags 15:45 Uhr/")(path):
@@ -124,6 +124,8 @@ def main() -> None:
             cookies="ilias_cookies.txt",
         )
 
+    # Prints a summary listing all new, modified or deleted files
+    pferd.print_summary()
 
 if __name__ == "__main__":
     main()

example_config_personal_desktop.py

@@ -30,6 +30,9 @@ def main() -> None:
         cookies="ilias_cookies.txt",
     )
 
+    # Prints a summary listing all new, modified or deleted files
+    pferd.print_summary()
+
 
 if __name__ == "__main__":
     main()

setup.py

@@ -2,12 +2,12 @@ from setuptools import find_packages, setup
 
 setup(
     name="PFERD",
-    version="2.0.0",
+    version="2.4.1",
     packages=find_packages(),
     install_requires=[
         "requests>=2.21.0",
         "beautifulsoup4>=4.7.1",
-        "rich>=1.0.0"
+        "rich>=2.1.0"
     ],
 )
 

sync_url.py

@@ -0,0 +1,67 @@
+#!/usr/bin/env python
+
+"""
+A simple script to download a course by name from ILIAS.
+"""
+
+import argparse
+from pathlib import Path
+from urllib.parse import urlparse
+
+from PFERD import Pferd
+from PFERD.cookie_jar import CookieJar
+from PFERD.ilias import (IliasCrawler, IliasElementType,
+                         KitShibbolethAuthenticator)
+from PFERD.utils import to_path
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--test-run", action="store_true")
+    parser.add_argument('-c', '--cookies', nargs='?', default=None, help="File to store cookies in")
+    parser.add_argument('--no-videos', nargs='?', default=None, help="Don't download videos")
+    parser.add_argument('url', help="URL to the course page")
+    parser.add_argument('folder', nargs='?', default=None, help="Folder to put stuff into")
+    args = parser.parse_args()
+
+    url = urlparse(args.url)
+
+    cookie_jar = CookieJar(to_path(args.cookies) if args.cookies else None)
+    session = cookie_jar.create_session()
+    authenticator = KitShibbolethAuthenticator()
+    crawler = IliasCrawler(url.scheme + '://' + url.netloc, session,
+                           authenticator, lambda x, y: True)
+
+    cookie_jar.load_cookies()
+
+    if args.folder is not None:
+        folder = args.folder
+        # Initialize pferd at the *parent of the passed folder*
+        # This is needed so Pferd's internal protections against escaping the working directory
+        # do not trigger (e.g. if somebody names a file in ILIAS '../../bad thing.txt')
+        pferd = Pferd(Path(Path(__file__).parent, folder).parent, test_run=args.test_run)
+    else:
+        # fetch course name from ilias
+        folder = crawler.find_element_name(args.url)
+        cookie_jar.save_cookies()
+
+        # Initialize pferd at the location of the script
+        pferd = Pferd(Path(__file__).parent, test_run=args.test_run)
+
+    def dir_filter(_: Path, element: IliasElementType) -> bool:
+        if args.no_videos:
+            return element not in [IliasElementType.VIDEO_FILE, IliasElementType.VIDEO_FOLDER]
+        return True
+
+    pferd.enable_logging()
+    # fetch
+    pferd.ilias_kit_folder(
+        target=folder,
+        full_url=args.url,
+        cookies=args.cookies,
+        dir_filter=dir_filter
+    )
+
+
+if __name__ == "__main__":
+    main()