Check for new versions at startup

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

@@ -17,9 +17,9 @@ jobs:
         python: ["3.9"]
     steps:
 
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v2
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v2
         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@v3
+        uses: actions/upload-artifact@v2
         with:
           name: Binaries
           path: dist/pferd-${{ matrix.os }}
@@ -57,7 +57,7 @@ jobs:
     steps:
 
       - name: Download binaries
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v2
         with:
           name: Binaries
 

CHANGELOG.md

@@ -23,42 +23,8 @@ ambiguous situations.
 ## Unreleased
 
 ### Fixed
-- Crawling of courses with the timeline view as the default tab
+- Forum crawling crashing when parsing empty (= 0 messages) threads
-- Crawling of file and custom opencast cards
-- Crawling of button cards without descriptions
-- Abort crawling when encountering an unexpected ilias root page redirect
-
-### 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.
-
-## 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
 

CONFIG.md

@@ -26,9 +26,6 @@ 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`)
@@ -78,9 +75,6 @@ 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
@@ -92,9 +86,6 @@ common to all crawlers:
   load for the crawl target. (Default: `0.0`)
 - `windows_paths`: Whether PFERD should find alternative names for paths that
   are invalid on Windows. (Default: `yes` on Windows, `no` otherwise)
-- `aliases`: List of strings that are considered as an alias when invoking with
-  the `--crawler` or `-C` flag. If there is more than one crawl section with
-  the same aliases all are selected. Thereby, you can group different crawlers.
 
 Some crawlers may also require credentials for authentication. To configure how
 the crawler obtains its credentials, the `auth` option is used. It is set to the
@@ -109,7 +100,6 @@ username = foo
 password = bar
 
 [crawl:something]
-aliases = [sth, some]
 type = some-complex-crawler
 auth = auth:example
 on_conflict = no-delete
@@ -191,7 +181,6 @@ 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`)
 
@@ -300,7 +289,7 @@ path matches `SOURCE`, it is renamed to `TARGET`.
 Example: `foo/bar --> baz`
 - Doesn't match `foo`, `a/foo/bar` or `foo/baz`
 - Converts `foo/bar` into `baz`
-- Converts `foo/bar/wargl` into `baz/wargl`
+- Converts `foo/bar/wargl` into `bar/wargl`
 
 Example: `foo/bar --> !`
 - Doesn't match `foo`, `a/foo/bar` or `foo/baz`

LICENSE

@@ -1,6 +1,5 @@
 Copyright 2019-2021 Garmelon, I-Al-Istannen, danstooamerican, pavelzw,
-                    TheChristophe, Scriptim, thelukasprobst, Toorero,
+                    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

@@ -5,6 +5,8 @@ import os
 import sys
 from pathlib import Path
 
+from PFERD.update import check_for_updates
+
 from .auth import AuthLoadError
 from .cli import PARSER, ParserLoadError, load_default_section
 from .config import Config, ConfigDumpError, ConfigLoadError, ConfigOptionError
@@ -47,8 +49,6 @@ 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
 
@@ -74,8 +74,6 @@ 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)
@@ -138,6 +136,11 @@ def main() -> None:
             loop.run_until_complete(asyncio.sleep(1))
             loop.close()
         else:
+            log.explain_topic("Checking for updates")
+            if not args.skip_update_check:
+                asyncio.run(check_for_updates())
+            else:
+                log.explain("Update check skipped due to configuration option")
             asyncio.run(pferd.run(args.debug_transforms))
     except (ConfigOptionError, AuthLoadError) as e:
         log.unlock()

PFERD/cli/parser.py

@@ -151,6 +151,11 @@ PARSER.add_argument(
     action="version",
     version=f"{NAME} {VERSION} (https://github.com/Garmelon/PFERD)",
 )
+PARSER.add_argument(
+    "--skip-update-check",
+    action="store_true",
+    help="disable automatic update checks at startup"
+)
 PARSER.add_argument(
     "--config", "-c",
     type=Path,
@@ -215,11 +220,6 @@ 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(
@@ -238,7 +238,6 @@ 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

@@ -82,9 +82,6 @@ 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)
 

PFERD/crawl/ilias/file_templates.py

@@ -1,10 +1,6 @@
 from enum import Enum
 from typing import Optional
 
-import bs4
-
-from PFERD.utils import soupify
-
 _link_template_plain = "{{link}}"
 _link_template_fancy = """
 <!DOCTYPE html>
@@ -98,71 +94,6 @@ _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"
@@ -171,24 +102,24 @@ class Links(Enum):
     INTERNET_SHORTCUT = "internet-shortcut"
 
     def template(self) -> Optional[str]:
-        if self == Links.FANCY:
+        if self == self.FANCY:
             return _link_template_fancy
-        elif self == Links.PLAINTEXT:
+        elif self == self.PLAINTEXT:
             return _link_template_plain
-        elif self == Links.INTERNET_SHORTCUT:
+        elif self == self.INTERNET_SHORTCUT:
             return _link_template_internet_shortcut
-        elif self == Links.IGNORE:
+        elif self == self.IGNORE:
             return None
         raise ValueError("Missing switch case")
 
     def extension(self) -> Optional[str]:
-        if self == Links.FANCY:
+        if self == self.FANCY:
             return ".html"
-        elif self == Links.PLAINTEXT:
+        elif self == self.PLAINTEXT:
             return ".txt"
-        elif self == Links.INTERNET_SHORTCUT:
+        elif self == self.INTERNET_SHORTCUT:
             return ".url"
-        elif self == Links.IGNORE:
+        elif self == self.IGNORE:
             return None
         raise ValueError("Missing switch case")
 

PFERD/crawl/ilias/ilias_html_cleaner.py

@@ -82,7 +82,7 @@ def clean(soup: BeautifulSoup) -> BeautifulSoup:
             dummy.decompose()
         if len(children) > 1:
             continue
-        if isinstance(type(children[0]), Comment):
+        if type(children[0]) == Comment:
             dummy.decompose()
 
     for hrule_imposter in soup.find_all(class_="ilc_section_Separator"):

PFERD/crawl/ilias/kit_ilias_html.py

@@ -22,10 +22,8 @@ class IliasElementType(Enum):
     FOLDER = "folder"
     FORUM = "forum"
     LINK = "link"
-    LEARNING_MODULE = "learning_module"
     BOOKING = "booking"
     MEETING = "meeting"
-    SURVEY = "survey"
     VIDEO = "video"
     VIDEO_PLAYER = "video_player"
     VIDEO_FOLDER = "video_folder"
@@ -72,14 +70,6 @@ class IliasForumThread:
     mtime: Optional[datetime]
 
 
-@dataclass
-class IliasLearningModulePage:
-    title: str
-    content: Tag
-    next_url: Optional[str]
-    previous_url: Optional[str]
-
-
 class IliasPage:
 
     def __init__(self, soup: BeautifulSoup, _page_url: str, source_element: Optional[IliasPageElement]):
@@ -88,16 +78,6 @@ class IliasPage:
         self._page_type = source_element.type if source_element else None
         self._source_name = source_element.name if source_element else ""
 
-    @staticmethod
-    def is_root_page(soup: BeautifulSoup) -> bool:
-        permalink = soup.find(id="current_perma_link")
-        if permalink is None:
-            return False
-        value = permalink.attrs.get("value")
-        if value is None:
-            return False
-        return "goto.php?target=root_" in value
-
     def get_child_elements(self) -> List[IliasPageElement]:
         """
         Return all child page elements you can find here.
@@ -145,34 +125,6 @@ class IliasPage:
 
         return BeautifulSoup(raw_html, "html.parser")
 
-    def get_learning_module_data(self) -> Optional[IliasLearningModulePage]:
-        if not self._is_learning_module_page():
-            return None
-        content = self._soup.select_one("#ilLMPageContent")
-        title = self._soup.select_one(".ilc_page_title_PageTitle").getText().strip()
-        return IliasLearningModulePage(
-            title=title,
-            content=content,
-            next_url=self._find_learning_module_next(),
-            previous_url=self._find_learning_module_prev()
-        )
-
-    def _find_learning_module_next(self) -> Optional[str]:
-        for link in self._soup.select("a.ilc_page_rnavlink_RightNavigationLink"):
-            url = self._abs_url_from_link(link)
-            if "baseClass=ilLMPresentationGUI" not in url:
-                continue
-            return url
-        return None
-
-    def _find_learning_module_prev(self) -> Optional[str]:
-        for link in self._soup.select("a.ilc_page_lnavlink_LeftNavigationLink"):
-            url = self._abs_url_from_link(link)
-            if "baseClass=ilLMPresentationGUI" not in url:
-                continue
-            return url
-        return None
-
     def get_download_forum_data(self) -> Optional[IliasDownloadForumData]:
         form = self._soup.find("form", attrs={"action": lambda x: x and "fallbackCmd=showThreads" in x})
         if not form:
@@ -181,7 +133,7 @@ class IliasPage:
 
         thread_ids = [f["value"] for f in form.find_all(attrs={"name": "thread_ids[]"})]
 
-        form_data: Dict[str, Union[str, List[str]]] = {
+        form_data: Dict[str, Union[str, List[ſtr]]] = {
             "thread_ids[]": thread_ids,
             "selected_cmd2": "html",
             "select_cmd2": "Ausführen",
@@ -205,8 +157,6 @@ class IliasPage:
         if self._contains_collapsed_future_meetings():
             log.explain("Requesting *all* future meetings")
             return self._uncollapse_future_meetings_url()
-        if not self._is_content_tab_selected():
-            return self._select_content_page_url()
         return None
 
     def _is_forum_page(self) -> bool:
@@ -259,12 +209,6 @@ class IliasPage:
             return False
         return "target=copa_" in link.get("value")
 
-    def _is_learning_module_page(self) -> bool:
-        link = self._soup.find(id="current_perma_link")
-        if not link:
-            return False
-        return "target=pg_" in link.get("value")
-
     def _contains_collapsed_future_meetings(self) -> bool:
         return self._uncollapse_future_meetings_url() is not None
 
@@ -275,27 +219,6 @@ class IliasPage:
         link = self._abs_url_from_link(element)
         return IliasPageElement(IliasElementType.FOLDER, link, "show all meetings")
 
-    def _is_content_tab_selected(self) -> bool:
-        return self._select_content_page_url() is None
-
-    def _select_content_page_url(self) -> Optional[IliasPageElement]:
-        tab = self._soup.find(
-            id="tab_view_content",
-            attrs={"class": lambda x: x is not None and "active" not in x}
-        )
-        # Already selected (or not found)
-        if not tab:
-            return None
-        link = tab.find("a")
-        if link:
-            link = self._abs_url_from_link(link)
-            return IliasPageElement(IliasElementType.FOLDER, link, "select content page")
-
-        _unexpected_html_warning()
-        log.warn_contd(f"Could not find content tab URL on {self._page_url!r}.")
-        log.warn_contd("PFERD might not find content on the course's main page.")
-        return None
-
     def _player_to_video(self) -> List[IliasPageElement]:
         # Fetch the actual video page. This is a small wrapper page initializing a javscript
         # player. Sadly we can not execute that JS. The actual video stream url is nowhere
@@ -442,7 +365,7 @@ class IliasPage:
         """
         # Video start links are marked with an "Abspielen" link
         video_links: List[Tag] = self._soup.findAll(
-            name="a", text=re.compile(r"\s*(Abspielen|Play)\s*")
+            name="a", text=re.compile(r"\s*Abspielen\s*")
         )
 
         results: List[IliasPageElement] = []
@@ -761,11 +684,7 @@ class IliasPage:
                 "div",
                 attrs={"class": lambda x: x and "caption" in x},
             )
-            caption_container = caption_parent.find_next_sibling("div")
+            description = caption_parent.find_next_sibling("div").getText().strip()
-            if caption_container:
-                description = caption_container.getText().strip()
-            else:
-                description = None
 
             if not type:
                 _unexpected_html_warning()
@@ -795,7 +714,7 @@ class IliasPage:
 
         icon: Tag = card_root.select_one(".il-card-repository-head .icon")
 
-        if "opencast" in icon["class"] or "xoct" in icon["class"]:
+        if "opencast" in icon["class"]:
             return IliasElementType.VIDEO_FOLDER_MAYBE_PAGINATED
         if "exc" in icon["class"]:
             return IliasElementType.EXERCISE
@@ -811,12 +730,6 @@ class IliasPage:
             return IliasElementType.TEST
         if "fold" in icon["class"]:
             return IliasElementType.FOLDER
-        if "copa" in icon["class"]:
-            return IliasElementType.FOLDER
-        if "svy" in icon["class"]:
-            return IliasElementType.SURVEY
-        if "file" in icon["class"]:
-            return IliasElementType.FILE
 
         _unexpected_html_warning()
         log.warn_contd(f"Could not extract type from {icon} for card title {card_title}")
@@ -855,9 +768,6 @@ class IliasPage:
         if "cmdClass=ilobjtestgui" in parsed_url.query:
             return IliasElementType.TEST
 
-        if "baseClass=ilLMPresentationGUI" in parsed_url.query:
-            return IliasElementType.LEARNING_MODULE
-
         # Booking and Meeting can not be detected based on the link. They do have a ref_id though, so
         # try to guess it from the image.
 

PFERD/crawl/ilias/kit_ilias_web_crawler.py

@@ -1,11 +1,8 @@
 import asyncio
-import base64
-import os
 import re
 from collections.abc import Awaitable, Coroutine
 from pathlib import PurePath
-from typing import Any, Callable, Dict, List, Literal, Optional, Set, Union, cast
+from typing import Any, Callable, Dict, List, Optional, Set, Union, cast
-from urllib.parse import urljoin
 
 import aiohttp
 import yarl
@@ -19,10 +16,10 @@ from ...output_dir import FileSink, Redownload
 from ...utils import fmt_path, soupify, url_set_query_param
 from ..crawler import AWrapped, CrawlError, CrawlToken, CrawlWarning, DownloadToken, anoncritical
 from ..http_crawler import HttpCrawler, HttpCrawlerSection
-from .file_templates import Links, learning_module_template
+from .file_templates import Links
 from .ilias_html_cleaner import clean, insert_base_markup
-from .kit_ilias_html import (IliasElementType, IliasForumThread, IliasLearningModulePage, IliasPage,
+from .kit_ilias_html import (IliasElementType, IliasForumThread, IliasPage, IliasPageElement,
-                             IliasPageElement, _sanitize_path_name, parse_ilias_forum_export)
+                             _sanitize_path_name, parse_ilias_forum_export)
 
 TargetType = Union[str, int]
 
@@ -197,7 +194,7 @@ instance's greatest bottleneck.
         self._links = section.links()
         self._videos = section.videos()
         self._forums = section.forums()
-        self._visited_urls: Dict[str, PurePath] = dict()
+        self._visited_urls: Set[str] = set()
 
     async def _run(self) -> None:
         if isinstance(self._target, int):
@@ -242,7 +239,7 @@ instance's greatest bottleneck.
 
                 # Duplicated code, but the root page is special - we want to avoid fetching it twice!
                 while next_stage_url:
-                    soup = await self._get_page(next_stage_url, root_page_allowed=True)
+                    soup = await self._get_page(next_stage_url)
 
                     if current_parent is None and expected_id is not None:
                         perma_link_element: Tag = soup.find(id="current_perma_link")
@@ -351,11 +348,9 @@ instance's greatest bottleneck.
     ) -> Optional[Coroutine[Any, Any, None]]:
         if element.url in self._visited_urls:
             raise CrawlWarning(
-                f"Found second path to element {element.name!r} at {element.url!r}. "
+                f"Found second path to element {element.name!r} at {element.url!r}. Aborting subpath"
-                + f"First path: {fmt_path(self._visited_urls[element.url])}. "
-                + f"Second path: {fmt_path(parent_path)}."
             )
-        self._visited_urls[element.url] = parent_path
+        self._visited_urls.add(element.url)
 
         element_path = PurePath(parent_path, element.name)
 
@@ -382,23 +377,10 @@ instance's greatest bottleneck.
                 return None
             return await self._handle_forum(element, element_path)
         elif element.type == IliasElementType.TEST:
-            log.status(
+            log.explain_topic(f"Decision: Crawl {fmt_path(element_path)}")
-                "[bold bright_black]",
+            log.explain("Tests contain no relevant files")
-                "Ignored",
+            log.explain("Answer: No")
-                fmt_path(element_path),
-                "[bright_black](tests contain no relevant data)"
-            )
             return None
-        elif element.type == IliasElementType.SURVEY:
-            log.status(
-                "[bold bright_black]",
-                "Ignored",
-                fmt_path(element_path),
-                "[bright_black](surveys contain no relevant data)"
-            )
-            return None
-        elif element.type == IliasElementType.LEARNING_MODULE:
-            return await self._handle_learning_module(element, element_path)
         elif element.type == IliasElementType.LINK:
             return await self._handle_link(element, element_path)
         elif element.type == IliasElementType.BOOKING:
@@ -744,141 +726,12 @@ instance's greatest bottleneck.
             sink.file.write(content.encode("utf-8"))
             sink.done()
 
-    async def _handle_learning_module(
+    async def _get_page(self, url: str) -> BeautifulSoup:
-        self,
-        element: IliasPageElement,
-        element_path: PurePath,
-    ) -> Optional[Coroutine[Any, Any, None]]:
-        maybe_cl = await self.crawl(element_path)
-        if not maybe_cl:
-            return None
-        return self._crawl_learning_module(element, maybe_cl)
-
-    @_iorepeat(3, "crawling learning module")
-    @anoncritical
-    async def _crawl_learning_module(self, element: IliasPageElement, cl: CrawlToken) -> None:
-        elements: List[IliasLearningModulePage] = []
-
-        async with cl:
-            log.explain_topic(f"Parsing initial HTML page for {fmt_path(cl.path)}")
-            log.explain(f"URL: {element.url}")
-            soup = await self._get_page(element.url)
-            page = IliasPage(soup, element.url, None)
-            if next := page.get_learning_module_data():
-                elements.extend(await self._crawl_learning_module_direction(
-                    cl.path, next.previous_url, "left"
-                ))
-                elements.append(next)
-                elements.extend(await self._crawl_learning_module_direction(
-                    cl.path, next.next_url, "right"
-                ))
-
-        # Reflect their natural ordering in the file names
-        for index, lm_element in enumerate(elements):
-            lm_element.title = f"{index:02}_{lm_element.title}"
-
-        tasks: List[Awaitable[None]] = []
-        for index, elem in enumerate(elements):
-            prev_url = elements[index - 1].title if index > 0 else None
-            next_url = elements[index + 1].title if index < len(elements) - 1 else None
-            tasks.append(asyncio.create_task(
-                self._download_learning_module_page(cl.path, elem, prev_url, next_url)
-            ))
-
-        # And execute them
-        await self.gather(tasks)
-
-    async def _crawl_learning_module_direction(
-        self,
-        path: PurePath,
-        start_url: Optional[str],
-        dir: Union[Literal["left"], Literal["right"]]
-    ) -> List[IliasLearningModulePage]:
-        elements: List[IliasLearningModulePage] = []
-
-        if not start_url:
-            return elements
-
-        next_element_url: Optional[str] = start_url
-        counter = 0
-        while next_element_url:
-            log.explain_topic(f"Parsing HTML page for {fmt_path(path)} ({dir}-{counter})")
-            log.explain(f"URL: {next_element_url}")
-            soup = await self._get_page(next_element_url)
-            page = IliasPage(soup, next_element_url, None)
-            if next := page.get_learning_module_data():
-                elements.append(next)
-                if dir == "left":
-                    next_element_url = next.previous_url
-                else:
-                    next_element_url = next.next_url
-            counter += 1
-
-        return elements
-
-    @anoncritical
-    @_iorepeat(3, "saving learning module page")
-    async def _download_learning_module_page(
-        self,
-        parent_path: PurePath,
-        element: IliasLearningModulePage,
-        prev: Optional[str],
-        next: Optional[str]
-    ) -> None:
-        path = parent_path / (_sanitize_path_name(element.title) + ".html")
-        maybe_dl = await self.download(path)
-        if not maybe_dl:
-            return
-        my_path = self._transformer.transform(maybe_dl.path)
-        if not my_path:
-            return
-
-        if prev:
-            prev_p = self._transformer.transform(parent_path / (_sanitize_path_name(prev) + ".html"))
-            if prev_p:
-                prev = os.path.relpath(prev_p, my_path.parent)
-            else:
-                prev = None
-        if next:
-            next_p = self._transformer.transform(parent_path / (_sanitize_path_name(next) + ".html"))
-            if next_p:
-                next = os.path.relpath(next_p, my_path.parent)
-            else:
-                next = None
-
-        async with maybe_dl as (bar, sink):
-            content = element.content
-            content = await self.internalize_images(content)
-            sink.file.write(learning_module_template(content, maybe_dl.path.name, prev, next).encode("utf-8"))
-            sink.done()
-
-    async def internalize_images(self, tag: Tag) -> Tag:
-        """
-        Tries to fetch ILIAS images and embed them as base64 data.
-        """
-        log.explain_topic("Internalizing images")
-        for elem in tag.find_all(recursive=True):
-            if not isinstance(elem, Tag):
-                continue
-            if elem.name == "img":
-                if src := elem.attrs.get("src", None):
-                    url = urljoin(_ILIAS_URL, src)
-                    if not url.startswith(_ILIAS_URL):
-                        continue
-                    log.explain(f"Internalizing {url!r}")
-                    img = await self._get_authenticated(url)
-                    elem.attrs["src"] = "data:;base64," + base64.b64encode(img).decode()
-            if elem.name == "iframe" and elem.attrs.get("src", "").startswith("//"):
-                # For unknown reasons the protocol seems to be stripped.
-                elem.attrs["src"] = "https:" + elem.attrs["src"]
-        return tag
-
-    async def _get_page(self, url: str, root_page_allowed: bool = False) -> BeautifulSoup:
         auth_id = await self._current_auth_id()
         async with self.session.get(url) as request:
             soup = soupify(await request.read())
             if self._is_logged_in(soup):
-                return self._verify_page(soup, url, root_page_allowed)
+                return soup
 
         # We weren't authenticated, so try to do that
         await self.authenticate(auth_id)
@@ -887,26 +740,14 @@ instance's greatest bottleneck.
         async with self.session.get(url) as request:
             soup = soupify(await request.read())
             if self._is_logged_in(soup):
-                return self._verify_page(soup, url, root_page_allowed)
-        raise CrawlError("get_page failed even after authenticating")
-
-    def _verify_page(self, soup: BeautifulSoup, url: str, root_page_allowed: bool) -> BeautifulSoup:
-        if IliasPage.is_root_page(soup) and not root_page_allowed:
-            raise CrawlError(
-                "Unexpectedly encountered ILIAS root page. "
-                "This usually happens because the ILIAS instance is broken. "
-                "If so, wait a day or two and try again. "
-                "It could also happen because a crawled element links to the ILIAS root page. "
-                "If so, use a transform with a ! as target to ignore the particular element. "
-                f"The redirect came from {url}"
-            )
                 return soup
+        raise CrawlError("get_page failed even after authenticating")
 
     async def _post_authenticated(
         self,
         url: str,
         data: dict[str, Union[str, List[str]]]
-    ) -> bytes:
+    ) -> BeautifulSoup:
         auth_id = await self._current_auth_id()
 
         form_data = aiohttp.FormData()
@@ -926,22 +767,6 @@ instance's greatest bottleneck.
                 return await request.read()
         raise CrawlError("post_authenticated failed even after authenticating")
 
-    async def _get_authenticated(self, url: str) -> bytes:
-        auth_id = await self._current_auth_id()
-
-        async with self.session.get(url, allow_redirects=False) as request:
-            if request.status == 200:
-                return await request.read()
-
-        # We weren't authenticated, so try to do that
-        await self.authenticate(auth_id)
-
-        # Retry once after authenticating. If this fails, we will die.
-        async with self.session.get(url, allow_redirects=False) as request:
-            if request.status == 200:
-                return await request.read()
-        raise CrawlError("get_authenticated failed even after authenticating")
-
     # We repeat this as the login method in shibboleth doesn't handle I/O errors.
     # Shibboleth is quite reliable as well, the repeat is likely not critical here.
     @ _iorepeat(3, "Login", failure_is_error=True)

PFERD/crawl/kit_ipd_crawler.py

@@ -2,7 +2,7 @@ import os
 import re
 from dataclasses import dataclass
 from pathlib import PurePath
-from typing import Awaitable, List, Optional, Pattern, Set, Tuple, Union
+from typing import Awaitable, List, Optional, Pattern, Set, Union
 from urllib.parse import urljoin
 
 from bs4 import BeautifulSoup, Tag
@@ -99,32 +99,32 @@ class KitIpdCrawler(HttpCrawler):
             await self._stream_from_url(file.url, sink, bar)
 
     async def _fetch_items(self) -> Set[Union[KitIpdFile, KitIpdFolder]]:
-        page, url = await self.get_page()
+        page = 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)
+                folder = self._extract_folder(folder_label)
                 if folder not in items:
                     items.add(folder)
                     folder.explain()
             else:
-                file = self._extract_file(element, url)
+                file = self._extract_file(element)
                 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:
+    def _extract_folder(self, folder_tag: Tag) -> 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))
+            files.append(self._extract_file(link))
 
         return KitIpdFolder(name, files)
 
@@ -135,16 +135,16 @@ class KitIpdCrawler(HttpCrawler):
             return None
         return enclosing_table.findPreviousSibling(name=re.compile("^h[1-6]$"))
 
-    def _extract_file(self, link: Tag, url: str) -> KitIpdFile:
+    def _extract_file(self, link: Tag) -> KitIpdFile:
-        url = self._abs_url_from_link(url, link)
+        url = self._abs_url_from_link(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:
+    def _abs_url_from_link(self, link_tag: Tag) -> str:
-        return urljoin(url, link_tag.get("href"))
+        return urljoin(self._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:
@@ -159,7 +159,7 @@ class KitIpdCrawler(HttpCrawler):
 
             sink.done()
 
-    async def get_page(self) -> Tuple[BeautifulSoup, str]:
+    async def get_page(self) -> BeautifulSoup:
         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
@@ -167,4 +167,4 @@ class KitIpdCrawler(HttpCrawler):
             # 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)
+            return soupify(content.encode("utf-8"))

PFERD/logging.py

@@ -59,7 +59,6 @@ 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:
@@ -208,17 +207,6 @@ directly or as a GitHub issue: https://github.com/Garmelon/PFERD/issues/new
             action = escape(f"{action:<{self.STATUS_WIDTH}}")
             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:
         """
         Print a report after crawling. Allows markup.
@@ -227,14 +215,6 @@ 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

@@ -44,7 +44,6 @@ 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":
@@ -52,7 +51,7 @@ class OnConflict(Enum):
             return OnConflict(string)
         except ValueError:
             raise ValueError("must be one of 'prompt', 'local-first',"
-                             " 'remote-first', 'no-delete', 'no-delete-prompt-overwrite'")
+                             " 'remote-first', 'no-delete'")
 
 
 @dataclass
@@ -265,7 +264,7 @@ class OutputDirectory:
             on_conflict: OnConflict,
             path: PurePath,
     ) -> bool:
-        if on_conflict in {OnConflict.PROMPT, OnConflict.NO_DELETE_PROMPT_OVERWRITE}:
+        if on_conflict == OnConflict.PROMPT:
             async with log.exclusive_output():
                 prompt = f"Replace {fmt_path(path)} with remote file?"
                 return await prompt_yes_no(prompt, default=False)
@@ -284,7 +283,7 @@ class OutputDirectory:
             on_conflict: OnConflict,
             path: PurePath,
     ) -> bool:
-        if on_conflict in {OnConflict.PROMPT, OnConflict.NO_DELETE_PROMPT_OVERWRITE}:
+        if on_conflict == OnConflict.PROMPT:
             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)
@@ -304,7 +303,7 @@ class OutputDirectory:
             path: PurePath,
             parent: PurePath,
     ) -> bool:
-        if on_conflict in {OnConflict.PROMPT, OnConflict.NO_DELETE_PROMPT_OVERWRITE}:
+        if on_conflict == OnConflict.PROMPT:
             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)
@@ -331,7 +330,7 @@ class OutputDirectory:
             return False
         elif on_conflict == OnConflict.REMOTE_FIRST:
             return True
-        elif on_conflict in {OnConflict.NO_DELETE, OnConflict.NO_DELETE_PROMPT_OVERWRITE}:
+        elif on_conflict == OnConflict.NO_DELETE:
             return False
 
         # This should never be reached
@@ -496,7 +495,7 @@ class OutputDirectory:
             except OSError:
                 pass
         else:
-            log.not_deleted("[bold bright_magenta]", "Not deleted", fmt_path(pure))
+            log.status("[bold bright_magenta]", "Not deleted", fmt_path(pure))
             self._report.not_delete_file(pure)
 
     def load_prev_report(self) -> None:

PFERD/pferd.py

@@ -1,5 +1,5 @@
 from pathlib import Path
-from typing import Dict, List, Optional, Set
+from typing import Dict, List, Optional
 
 from rich.markup import escape
 
@@ -43,24 +43,16 @@ class Pferd:
 
         crawl_sections = [name for name, _ in config.crawl_sections()]
 
-        crawlers_to_run = set()  # With crawl: prefix
+        crawlers_to_run = []  # With crawl: prefix
         unknown_names = []  # Without crawl: prefix
 
         for name in cli_crawlers:
             section_name = f"crawl:{name}"
             if section_name in crawl_sections:
                 log.explain(f"Crawler section named {section_name!r} exists")
-                crawlers_to_run.add(section_name)
+                crawlers_to_run.append(section_name)
-            # interprete name as alias of a crawler
+            else:
-            alias_names = self._find_crawlers_by_alias(name, config)
+                log.explain(f"There's no crawler section named {section_name!r}")
-            if alias_names:
-                crawlers_to_run.update(alias_names)
-                log.explain_topic(f"Crawler alias {name!r} found corresponding crawler sections:")
-                for alias_name in alias_names:
-                    log.explain(f"Crawler section named {alias_name!r} with alias {name!r} exists")
-
-            if not section_name in crawl_sections and not alias_names:
-                log.explain(f"There's neither a crawler section named {section_name!r} nor does a crawler with alias {name!r} exist.")
                 unknown_names.append(name)
 
         if unknown_names:
@@ -73,14 +65,6 @@ class Pferd:
 
         return crawlers_to_run
 
-    def _find_crawlers_by_alias(self, alias: str, config: Config) -> Set[str]:
-        alias_names = set()
-        for (section_name, section) in config.crawl_sections():
-            section_aliases = section.get("aliases", [])
-            if alias in section_aliases:
-                alias_names.add(section_name)
-        return alias_names
-
     def _find_crawlers_to_run(
             self,
             config: Config,
@@ -196,7 +180,7 @@ 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_not_deleted(f"  [bold bright_magenta]Not deleted[/] {fmt_path(path)}")
+                log.report(f"  [bold bright_magenta]Not deleted[/] {fmt_path(path)}")
 
             for warning in crawler.report.encountered_warnings:
                 something_changed = True

PFERD/update.py

@@ -0,0 +1,53 @@
+from dataclasses import dataclass
+import ssl
+from typing import Optional
+import aiohttp
+import certifi
+
+from .version import NAME, VERSION
+from .logging import log
+
+
+@dataclass
+class PferdUpdate:
+    release_url: str
+    version: str
+
+
+def _build_session() -> aiohttp.ClientSession:
+    return aiohttp.ClientSession(
+        headers={"User-Agent": f"{NAME}/{VERSION}"},
+        connector=aiohttp.TCPConnector(ssl=ssl.create_default_context(cafile=certifi.where())),
+        timeout=aiohttp.ClientTimeout(
+            total=15 * 60,
+            connect=10,
+            sock_connect=10,
+            sock_read=10,
+        )
+    )
+
+
+async def check_for_updates() -> None:
+    if new_version := await get_newer_version():
+        log.warn(
+            f"{NAME} version out of date. "
+            + f"You are running version {VERSION!r} but {new_version.version!r} was found on GitHub."
+        )
+        log.warn_contd(f"You can download it on GitHub: {new_version.release_url}")
+    else:
+        log.explain("No update found")
+
+
+async def get_newer_version() -> Optional[PferdUpdate]:
+    async with _build_session() as session:
+        async with session.get(
+            "https://api.github.com/repos/Garmelon/Pferd/releases/latest",
+            headers={"Accept": "application/vnd.github+json"}
+        ) as response:
+            release_information = await response.json()
+            tag_name: str = release_information["tag_name"]
+            tag_name = tag_name.removeprefix("v")
+            if VERSION == tag_name:
+                return None
+
+            return PferdUpdate(release_url=release_information["html_url"], version=tag_name)

PFERD/version.py

@@ -1,2 +1,2 @@
 NAME = "PFERD"
-VERSION = "3.4.3"
+VERSION = "3.4.1"

README.md

@@ -30,10 +30,7 @@ The use of [venv](https://docs.python.org/3/library/venv.html) is recommended.
 
 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).