Merge 77c1f1516c into e41a22149e

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

CHANGELOG.md

@@ -26,6 +26,14 @@ ambiguous situations.
 - Crawling of courses with the timeline view as the default tab
 - Crawling of file and custom opencast cards
 - Crawling of button cards without descriptions
+- Abort crawling when encountering an unexpected ilias root page redirect
+
+### 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
 

CONFIG.md

@@ -26,6 +26,9 @@ default values for the other sections.
   `Added ...`) while running a crawler. (Default: `yes`)
 - `report`: Whether PFERD should print a report of added, changed and deleted
    local files for all crawlers before exiting. (Default: `yes`)
+- `show_not_deleted`: Whether PFERD should print messages in status and report
+   when a local-only file wasn't deleted. Combines nicely with the
+   `no-delete-prompt-override` conflict resolution strategy.
 - `share_cookies`: Whether crawlers should share cookies where applicable. For
   example, some crawlers share cookies if they crawl the same website using the
   same account. (Default: `yes`)
@@ -75,6 +78,9 @@ common to all crawlers:
       using `prompt` and always choosing "yes".
     - `no-delete`: Never delete local files, but overwrite local files if the
       remote file is different.
+    - `no-delete-prompt-overwrite`: Never delete local files, but prompt to
+      overwrite local files if the remote file is different. Combines nicely
+      with the `show_not_deleted` option.
 - `transform`: Rules for renaming and excluding certain files and directories.
   For more details, see [this section](#transformation-rules). (Default: empty)
 - `tasks`: The maximum number of concurrent tasks (such as crawling or
@@ -86,6 +92,9 @@ 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
@@ -100,6 +109,7 @@ username = foo
 password = bar
 
 [crawl:something]
+aliases = [sth, some]
 type = some-complex-crawler
 auth = auth:example
 on_conflict = no-delete

LICENSE

@@ -1,5 +1,6 @@
 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

@@ -47,6 +47,8 @@ def configure_logging_from_args(args: argparse.Namespace) -> None:
         log.output_explain = args.explain
     if args.status is not None:
         log.output_status = args.status
+    if args.show_not_deleted is not None:
+        log.output_not_deleted = args.show_not_deleted
     if args.report is not None:
         log.output_report = args.report
 
@@ -72,6 +74,8 @@ def configure_logging_from_config(args: argparse.Namespace, config: Config) -> N
             log.output_status = config.default_section.status()
         if args.report is None:
             log.output_report = config.default_section.report()
+        if args.show_not_deleted is None:
+            log.output_not_deleted = config.default_section.show_not_deleted()
     except ConfigOptionError as e:
         log.error(str(e))
         sys.exit(1)

PFERD/cli/parser.py

@@ -215,6 +215,11 @@ PARSER.add_argument(
     action=BooleanOptionalAction,
     help="whether crawlers should share cookies where applicable"
 )
+PARSER.add_argument(
+    "--show-not-deleted",
+    action=BooleanOptionalAction,
+    help="print messages in status and report when PFERD did not delete a local only file"
+)
 
 
 def load_default_section(
@@ -233,6 +238,7 @@ 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

@@ -82,6 +82,9 @@ class DefaultSection(Section):
     def report(self) -> bool:
         return self.s.getboolean("report", fallback=True)
 
+    def show_not_deleted(self) -> bool:
+        return self.s.getboolean("show_not_deleted", fallback=True)
+
     def share_cookies(self) -> bool:
         return self.s.getboolean("share_cookies", fallback=True)
 

PFERD/crawl/ilias/file_templates.py

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

PFERD/crawl/ilias/ilias_html_cleaner.py

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

PFERD/crawl/ilias/kit_ilias_html.py

@@ -22,6 +22,7 @@ class IliasElementType(Enum):
     FOLDER = "folder"
     FORUM = "forum"
     LINK = "link"
+    LEARNING_MODULE = "learning_module"
     BOOKING = "booking"
     MEETING = "meeting"
     SURVEY = "survey"
@@ -71,6 +72,14 @@ 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]):
@@ -79,6 +88,16 @@ 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.
@@ -126,6 +145,34 @@ 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:
@@ -212,6 +259,12 @@ 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
 
@@ -802,6 +855,9 @@ 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

@@ -1,8 +1,11 @@
 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, Optional, Set, Union, cast
+from typing import Any, Callable, Dict, List, Literal, Optional, Set, Union, cast
+from urllib.parse import urljoin
 
 import aiohttp
 import yarl
@@ -16,10 +19,10 @@ 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
+from .file_templates import Links, learning_module_template
 from .ilias_html_cleaner import clean, insert_base_markup
-from .kit_ilias_html import (IliasElementType, IliasForumThread, IliasPage, IliasPageElement,
+from .kit_ilias_html import (IliasElementType, IliasForumThread, IliasLearningModulePage, IliasPage,
-                             _sanitize_path_name, parse_ilias_forum_export)
+                             IliasPageElement, _sanitize_path_name, parse_ilias_forum_export)
 
 TargetType = Union[str, int]
 
@@ -239,7 +242,7 @@ 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)
+                    soup = await self._get_page(next_stage_url, root_page_allowed=True)
 
                     if current_parent is None and expected_id is not None:
                         perma_link_element: Tag = soup.find(id="current_perma_link")
@@ -394,6 +397,8 @@ instance's greatest bottleneck.
                 "[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:
@@ -739,12 +744,141 @@ instance's greatest bottleneck.
             sink.file.write(content.encode("utf-8"))
             sink.done()
 
-    async def _get_page(self, url: str) -> BeautifulSoup:
+    async def _handle_learning_module(
+        self,
+        element: IliasPageElement,
+        element_path: PurePath,
+    ) -> Optional[Coroutine[Any, Any, None]]:
+        maybe_cl = await self.crawl(element_path)
+        if not maybe_cl:
+            return None
+        return self._crawl_learning_module(element, maybe_cl)
+
+    @_iorepeat(3, "crawling learning module")
+    @anoncritical
+    async def _crawl_learning_module(self, element: IliasPageElement, cl: CrawlToken) -> None:
+        elements: List[IliasLearningModulePage] = []
+
+        async with cl:
+            log.explain_topic(f"Parsing initial HTML page for {fmt_path(cl.path)}")
+            log.explain(f"URL: {element.url}")
+            soup = await self._get_page(element.url)
+            page = IliasPage(soup, element.url, 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 soup
+                return self._verify_page(soup, url, root_page_allowed)
 
         # We weren't authenticated, so try to do that
         await self.authenticate(auth_id)
@@ -753,14 +887,26 @@ instance's greatest bottleneck.
         async with self.session.get(url) as request:
             soup = soupify(await request.read())
             if self._is_logged_in(soup):
-                return 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
+
     async def _post_authenticated(
         self,
         url: str,
         data: dict[str, Union[str, List[str]]]
-    ) -> BeautifulSoup:
+    ) -> bytes:
         auth_id = await self._current_auth_id()
 
         form_data = aiohttp.FormData()
@@ -780,6 +926,22 @@ 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/logging.py

@@ -59,6 +59,7 @@ class Log:
         # Whether different parts of the output are enabled or disabled
         self.output_explain = False
         self.output_status = True
+        self.output_not_deleted = True
         self.output_report = True
 
     def _update_live(self) -> None:
@@ -207,6 +208,17 @@ 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.
@@ -215,6 +227,14 @@ directly or as a GitHub issue: https://github.com/Garmelon/PFERD/issues/new
         if self.output_report:
             self.print(text)
 
+    def report_not_deleted(self, text: str) -> None:
+        """
+        Print a report for a local only file that wasn't deleted after crawling. Allows markup.
+        """
+
+        if self.output_report and self.output_not_deleted:
+            self.print(text)
+
     @contextmanager
     def _bar(
             self,

PFERD/output_dir.py

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

PFERD/pferd.py

@@ -1,5 +1,5 @@
 from pathlib import Path
-from typing import Dict, List, Optional
+from typing import Dict, List, Optional, Set
 
 from rich.markup import escape
 
@@ -43,16 +43,24 @@ class Pferd:
 
         crawl_sections = [name for name, _ in config.crawl_sections()]
 
-        crawlers_to_run = []  # With crawl: prefix
+        crawlers_to_run = set()  # 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.append(section_name)
+                crawlers_to_run.add(section_name)
-            else:
+            # interprete name as alias of a crawler
-                log.explain(f"There's no crawler section named {section_name!r}")
+            alias_names = self._find_crawlers_by_alias(name, config)
+            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:
@@ -65,6 +73,14 @@ 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,
@@ -180,7 +196,7 @@ 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(f"  [bold bright_magenta]Not deleted[/] {fmt_path(path)}")
+                log.report_not_deleted(f"  [bold bright_magenta]Not deleted[/] {fmt_path(path)}")
 
             for warning in crawler.report.encountered_warnings:
                 something_changed = True