TODO

.gitignore

@@ -2,7 +2,6 @@
 /.venv/
 /PFERD.egg-info/
 __pycache__/
-/.vscode/
 
 # pyinstaller
 /pferd.spec

.vscode/settings.json

@@ -0,0 +1,8 @@
+{
+    "files.insertFinalNewline": true,
+    "files.trimFinalNewlines": true,
+    "python.formatting.provider": "autopep8",
+    "python.linting.enabled": true,
+    "python.linting.flake8Enabled": true,
+    "python.linting.mypyEnabled": true,
+}

CHANGELOG.md

@@ -26,14 +26,6 @@ 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

@@ -26,9 +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

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

@@ -47,8 +47,6 @@ 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 +72,6 @@ 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)

PFERD/cli/parser.py

@@ -215,11 +215,6 @@ 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 +233,6 @@ 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/crawler.py

@@ -9,7 +9,6 @@ from typing import Any, Callable, Dict, List, Optional, Sequence, Set, Tuple, Ty
 from ..auth import Authenticator
 from ..config import Config, Section
 from ..deduplicator import Deduplicator
-from ..limiter import Limiter
 from ..logging import ProgressBar, log
 from ..output_dir import FileSink, FileSinkToken, OnConflict, OutputDirectory, OutputDirError, Redownload
 from ..report import MarkConflictError, MarkDuplicateError, Report
@@ -98,10 +97,9 @@ def anoncritical(f: AWrapped) -> AWrapped:
 
 
 class CrawlToken(ReusableAsyncContextManager[ProgressBar]):
-    def __init__(self, limiter: Limiter, path: PurePath):
+    def __init__(self, path: PurePath):
         super().__init__()
 
-        self._limiter = limiter
         self._path = path
 
     @property
@@ -110,17 +108,15 @@ class CrawlToken(ReusableAsyncContextManager[ProgressBar]):
 
     async def _on_aenter(self) -> ProgressBar:
         self._stack.callback(lambda: log.status("[bold cyan]", "Crawled", fmt_path(self._path)))
-        await self._stack.enter_async_context(self._limiter.limit_crawl())
         bar = self._stack.enter_context(log.crawl_bar("[bold bright_cyan]", "Crawling", fmt_path(self._path)))
 
         return bar
 
 
 class DownloadToken(ReusableAsyncContextManager[Tuple[ProgressBar, FileSink]]):
-    def __init__(self, limiter: Limiter, fs_token: FileSinkToken, path: PurePath):
+    def __init__(self, fs_token: FileSinkToken, path: PurePath):
         super().__init__()
 
-        self._limiter = limiter
         self._fs_token = fs_token
         self._path = path
 
@@ -129,7 +125,6 @@ class DownloadToken(ReusableAsyncContextManager[Tuple[ProgressBar, FileSink]]):
         return self._path
 
     async def _on_aenter(self) -> Tuple[ProgressBar, FileSink]:
-        await self._stack.enter_async_context(self._limiter.limit_download())
         sink = await self._stack.enter_async_context(self._fs_token)
         # The "Downloaded ..." message is printed in the output dir, not here
         bar = self._stack.enter_context(log.download_bar("[bold bright_cyan]", "Downloading",
@@ -235,12 +230,6 @@ class Crawler(ABC):
         self.name = name
         self.error_free = True
 
-        self._limiter = Limiter(
-            task_limit=section.tasks(),
-            download_limit=section.downloads(),
-            task_delay=section.task_delay(),
-        )
-
         self._deduplicator = Deduplicator(section.windows_paths())
         self._transformer = Transformer(section.transform())
 
@@ -288,7 +277,7 @@ class Crawler(ABC):
             return None
 
         log.explain("Answer: Yes")
-        return CrawlToken(self._limiter, path)
+        return CrawlToken(path)
 
     async def download(
             self,
@@ -313,7 +302,7 @@ class Crawler(ABC):
             return None
 
         log.explain("Answer: Yes")
-        return DownloadToken(self._limiter, fs_token, path)
+        return DownloadToken(fs_token, path)
 
     async def _cleanup(self) -> None:
         log.explain_topic("Decision: Clean up files")

PFERD/crawl/http_crawler.py

@@ -1,12 +1,9 @@
 import asyncio
-import http.cookies
+from http.cookiejar import LWPCookieJar
-import ssl
 from pathlib import Path, PurePath
-from typing import Any, Dict, List, Optional
+from typing import Dict, List, Optional
 
-import aiohttp
+import requests
-import certifi
-from aiohttp.client import ClientTimeout
 
 from ..auth import Authenticator
 from ..config import Config
@@ -35,9 +32,9 @@ class HttpCrawler(Crawler):
 
         self._authentication_id = 0
         self._authentication_lock = asyncio.Lock()
-        self._request_count = 0
+        self._http_timeout = section.http_timeout()  # TODO Use or remove
-        self._http_timeout = section.http_timeout()
 
+        self._cookie_jar = LWPCookieJar()
         self._cookie_jar_path = self._output_dir.resolve(self.COOKIE_FILE)
         self._shared_cookie_jar_paths: Optional[List[Path]] = None
         self._shared_auth = shared_auth
@@ -57,7 +54,6 @@ class HttpCrawler(Crawler):
         # This should reduce the amount of requests we make: If an authentication is in progress
         # all future requests wait for authentication to complete.
         async with self._authentication_lock:
-            self._request_count += 1
             return self._authentication_id
 
     async def authenticate(self, caller_auth_id: int) -> None:
@@ -106,32 +102,13 @@ class HttpCrawler(Crawler):
 
         self._shared_cookie_jar_paths.append(self._cookie_jar_path)
 
-    def _load_cookies_from_file(self, path: Path) -> None:
-        jar: Any = http.cookies.SimpleCookie()
-        with open(path, encoding="utf-8") as f:
-            for i, line in enumerate(f):
-                # Names of headers are case insensitive
-                if line[:11].lower() == "set-cookie:":
-                    jar.load(line[11:])
-                else:
-                    log.explain(f"Line {i} doesn't start with 'Set-Cookie:', ignoring it")
-        self._cookie_jar.update_cookies(jar)
-
-    def _save_cookies_to_file(self, path: Path) -> None:
-        jar: Any = http.cookies.SimpleCookie()
-        for morsel in self._cookie_jar:
-            jar[morsel.key] = morsel
-        with open(path, "w", encoding="utf-8") as f:
-            f.write(jar.output(sep="\n"))
-            f.write("\n")  # A trailing newline is just common courtesy
-
     def _load_cookies(self) -> None:
         log.explain_topic("Loading cookies")
 
         cookie_jar_path: Optional[Path] = None
 
         if self._shared_cookie_jar_paths is None:
-            log.explain("Not sharing any cookies")
+            log.explain("Not sharing cookies")
             cookie_jar_path = self._cookie_jar_path
         else:
             log.explain("Sharing cookies")
@@ -154,46 +131,38 @@ class HttpCrawler(Crawler):
 
         log.explain(f"Loading cookies from {fmt_real_path(cookie_jar_path)}")
         try:
-            self._load_cookies_from_file(cookie_jar_path)
+            self._cookie_jar.load(filename=str(cookie_jar_path))
         except Exception as e:
-            log.explain("Failed to load cookies")
+            log.explain(f"Failed to load cookies: {e}")
-            log.explain(str(e))
+            log.explain("Proceeding without cookies")
 
     def _save_cookies(self) -> None:
         log.explain_topic("Saving cookies")
 
         try:
             log.explain(f"Saving cookies to {fmt_real_path(self._cookie_jar_path)}")
-            self._save_cookies_to_file(self._cookie_jar_path)
+            self._cookie_jar.save(filename=str(self._cookie_jar_path))
         except Exception as e:
-            log.warn(f"Failed to save cookies to {fmt_real_path(self._cookie_jar_path)}")
+            log.warn(f"Failed to save cookies: {e}")
-            log.warn(str(e))
 
     async def run(self) -> None:
         self._request_count = 0
-        self._cookie_jar = aiohttp.CookieJar()
         self._load_cookies()
 
-        async with aiohttp.ClientSession(
+        self.session = requests.Session()
-                headers={"User-Agent": f"{NAME}/{VERSION}"},
+        self.session.headers["User-Agent"] = f"{NAME}/{VERSION}"
-                cookie_jar=self._cookie_jar,
+
-                connector=aiohttp.TCPConnector(ssl=ssl.create_default_context(cafile=certifi.where())),
+        # From the request docs: "All requests code should work out of the box
-                timeout=ClientTimeout(
+        # with externally provided instances of CookieJar, e.g. LWPCookieJar and
-                    # 30 minutes. No download in the history of downloads was longer than 30 minutes.
+        # FileCookieJar."
-                    # This is enough to transfer a 600 MB file over a 3 Mib/s connection.
+        # https://requests.readthedocs.io/en/latest/api/#requests.cookies.RequestsCookieJar
-                    # Allowing an arbitrary value could be annoying for overnight batch jobs
+        self.session.cookies = self._cookie_jar  # type: ignore
-                    total=15 * 60,
+
-                    connect=self._http_timeout,
+        with self.session:
-                    sock_connect=self._http_timeout,
-                    sock_read=self._http_timeout,
-                )
-        ) as session:
-            self.session = session
             try:
                 await super().run()
             finally:
                 del self.session
-        log.explain_topic(f"Total amount of HTTP requests: {self._request_count}")
 
         # They are saved in authenticate, but a final save won't hurt
         self._save_cookies()

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

@@ -22,7 +22,6 @@ class IliasElementType(Enum):
     FOLDER = "folder"
     FORUM = "forum"
     LINK = "link"
-    LEARNING_MODULE = "learning_module"
     BOOKING = "booking"
     MEETING = "meeting"
     SURVEY = "survey"
@@ -72,14 +71,6 @@ 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 +79,6 @@ 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 +126,6 @@ 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:
@@ -259,12 +212,6 @@ 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
 
@@ -855,9 +802,6 @@ 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]
 
@@ -129,13 +126,6 @@ def _iorepeat(attempts: int, name: str, failure_is_error: bool = False) -> Calla
     return decorator
 
 
-def _wrap_io_in_warning(name: str) -> Callable[[AWrapped], AWrapped]:
-    """
-    Wraps any I/O exception in a CrawlWarning.
-    """
-    return _iorepeat(1, name)
-
-
 # Crawler control flow:
 #
 #     crawl_desktop -+
@@ -229,114 +219,45 @@ instance's greatest bottleneck.
             return
         cl = maybe_cl  # Not mypy's fault, but explained here: https://github.com/python/mypy/issues/2608
 
-        elements: List[IliasPageElement] = []
+        def ensure_is_valid_course_id(parent: Optional[IliasPageElement], soup: BeautifulSoup) -> None:
-        # A list as variable redefinitions are not propagated to outer scopes
+            if parent is None and expected_id is not None:
-        description: List[BeautifulSoup] = []
+                perma_link_element: Tag = soup.find(id="current_perma_link")
+                if not perma_link_element or "crs_" not in perma_link_element.get("value"):
+                    raise CrawlError("Invalid course id? Didn't find anything looking like a course")
 
-        @_iorepeat(3, "crawling url")
+        await self._crawl_ilias_page(url, None, cl, ensure_is_valid_course_id)
-        async def gather_elements() -> None:
-            elements.clear()
-            async with cl:
-                next_stage_url: Optional[str] = url
-                current_parent = None
-
-                # Duplicated code, but the root page is special - we want to avoid fetching it twice!
-                while next_stage_url:
-                    soup = await self._get_page(next_stage_url, root_page_allowed=True)
-
-                    if current_parent is None and expected_id is not None:
-                        perma_link_element: Tag = soup.find(id="current_perma_link")
-                        if not perma_link_element or "crs_" not in perma_link_element.get("value"):
-                            raise CrawlError("Invalid course id? Didn't find anything looking like a course")
-
-                    log.explain_topic(f"Parsing HTML page for {fmt_path(cl.path)}")
-                    log.explain(f"URL: {next_stage_url}")
-                    page = IliasPage(soup, next_stage_url, current_parent)
-                    if next_element := page.get_next_stage_element():
-                        current_parent = next_element
-                        next_stage_url = next_element.url
-                    else:
-                        next_stage_url = None
-
-                elements.extend(page.get_child_elements())
-                if description_string := page.get_description():
-                    description.append(description_string)
-
-        # Fill up our task list with the found elements
-        await gather_elements()
-
-        if description:
-            await self._download_description(PurePath("."), description[0])
-
-        elements.sort(key=lambda e: e.id())
-
-        tasks: List[Awaitable[None]] = []
-        for element in elements:
-            if handle := await self._handle_ilias_element(PurePath("."), element):
-                tasks.append(asyncio.create_task(handle))
-
-        # And execute them
-        await self.gather(tasks)
-
-    async def _handle_ilias_page(
-        self,
-        url: str,
-        parent: IliasPageElement,
-        path: PurePath,
-    ) -> Optional[Coroutine[Any, Any, None]]:
-        maybe_cl = await self.crawl(path)
-        if not maybe_cl:
-            return None
-        return self._crawl_ilias_page(url, parent, maybe_cl)
 
     @anoncritical
     async def _crawl_ilias_page(
         self,
         url: str,
-        parent: IliasPageElement,
+        parent: Optional[IliasPageElement],
         cl: CrawlToken,
+        next_stage_hook: Callable[[Optional[IliasPageElement], BeautifulSoup], None] = lambda a, b: None
     ) -> None:
-        elements: List[IliasPageElement] = []
+        async with cl:
-        # A list as variable redefinitions are not propagated to outer scopes
+            next_stage_url: Optional[str] = url
-        description: List[BeautifulSoup] = []
+            current_parent = parent
 
-        @_iorepeat(3, "crawling folder")
+            while next_stage_url:
-        async def gather_elements() -> None:
+                soup = await self._get_page(next_stage_url)
-            elements.clear()
+                log.explain_topic(f"Parsing HTML page for {fmt_path(cl.path)}")
-            async with cl:
+                log.explain(f"URL: {next_stage_url}")
-                next_stage_url: Optional[str] = url
-                current_parent = parent
 
-                while next_stage_url:
+                next_stage_hook(current_parent, soup)
-                    soup = await self._get_page(next_stage_url)
-                    log.explain_topic(f"Parsing HTML page for {fmt_path(cl.path)}")
-                    log.explain(f"URL: {next_stage_url}")
-                    page = IliasPage(soup, next_stage_url, current_parent)
-                    if next_element := page.get_next_stage_element():
-                        current_parent = next_element
-                        next_stage_url = next_element.url
-                    else:
-                        next_stage_url = None
 
-                elements.extend(page.get_child_elements())
+                page = IliasPage(soup, next_stage_url, current_parent)
-                if description_string := page.get_description():
+                if next_element := page.get_next_stage_element():
-                    description.append(description_string)
+                    current_parent = next_element
+                    next_stage_url = next_element.url
+                else:
+                    next_stage_url = None
 
-        # Fill up our task list with the found elements
+        for element in sorted(page.get_child_elements(), key=lambda e: e.id()):
-        await gather_elements()
+            await self._handle_ilias_element(cl.path, element)
 
-        if description:
+        if description_string := page.get_description():
-            await self._download_description(cl.path, description[0])
+            await self._download_description(cl.path, description_string)
-
-        elements.sort(key=lambda e: e.id())
-
-        tasks: List[Awaitable[None]] = []
-        for element in elements:
-            if handle := await self._handle_ilias_element(cl.path, element):
-                tasks.append(asyncio.create_task(handle))
-
-        # And execute them
-        await self.gather(tasks)
 
     # These decorators only apply *to this method* and *NOT* to the returned
     # awaitables!
@@ -348,7 +269,7 @@ instance's greatest bottleneck.
         self,
         parent_path: PurePath,
         element: IliasPageElement,
-    ) -> Optional[Coroutine[Any, Any, None]]:
+    ) -> None:
         if element.url in self._visited_urls:
             raise CrawlWarning(
                 f"Found second path to element {element.name!r} at {element.url!r}. "
@@ -370,7 +291,7 @@ instance's greatest bottleneck.
                 return None
 
         if element.type == IliasElementType.FILE:
-            return await self._handle_file(element, element_path)
+            await self._handle_file(element, element_path)
         elif element.type == IliasElementType.FORUM:
             if not self._forums:
                 log.status(
@@ -380,7 +301,7 @@ instance's greatest bottleneck.
                     "[bright_black](enable with option 'forums')"
                 )
                 return None
-            return await self._handle_forum(element, element_path)
+            await self._handle_forum(element, element_path)
         elif element.type == IliasElementType.TEST:
             log.status(
                 "[bold bright_black]",
@@ -397,18 +318,19 @@ 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)
+            await self._handle_link(element, element_path)
         elif element.type == IliasElementType.BOOKING:
-            return await self._handle_booking(element, element_path)
+            await self._handle_booking(element, element_path)
         elif element.type == IliasElementType.VIDEO:
-            return await self._handle_file(element, element_path)
+            await self._handle_file(element, element_path)
         elif element.type == IliasElementType.VIDEO_PLAYER:
-            return await self._handle_video(element, element_path)
+            await self._handle_video(element, element_path)
         elif element.type in _DIRECTORY_PAGES:
-            return await self._handle_ilias_page(element.url, element, element_path)
+            maybe_cl = await self.crawl(element_path)
+            if not maybe_cl:
+                return None
+            await self._crawl_ilias_page(element.url, element, maybe_cl)
         else:
             # This will retry it a few times, failing everytime. It doesn't make any network
             # requests, so that's fine.
@@ -418,7 +340,7 @@ instance's greatest bottleneck.
         self,
         element: IliasPageElement,
         element_path: PurePath,
-    ) -> Optional[Coroutine[Any, Any, None]]:
+    ) -> None:
         log.explain_topic(f"Decision: Crawl Link {fmt_path(element_path)}")
         log.explain(f"Links type is {self._links}")
 
@@ -435,7 +357,7 @@ instance's greatest bottleneck.
         if not maybe_dl:
             return None
 
-        return self._download_link(element, link_template_maybe, maybe_dl)
+        await self._download_link(element, link_template_maybe, maybe_dl)
 
     @anoncritical
     @_iorepeat(3, "resolving link")
@@ -527,7 +449,7 @@ instance's greatest bottleneck.
         self,
         element: IliasPageElement,
         element_path: PurePath,
-    ) -> Optional[Coroutine[Any, Any, None]]:
+    ) -> None:
         # Copy old mapping as it is likely still relevant
         if self.prev_report:
             self.report.add_custom_value(
@@ -553,7 +475,7 @@ instance's greatest bottleneck.
 
             return None
 
-        return self._download_video(element_path, element, maybe_dl)
+        await self._download_video(element_path, element, maybe_dl)
 
     def _previous_contained_videos(self, video_path: PurePath) -> List[PurePath]:
         if not self.prev_report:
@@ -635,11 +557,11 @@ instance's greatest bottleneck.
         self,
         element: IliasPageElement,
         element_path: PurePath,
-    ) -> Optional[Coroutine[Any, Any, None]]:
+    ) -> None:
         maybe_dl = await self.download(element_path, mtime=element.mtime)
         if not maybe_dl:
             return None
-        return self._download_file(element, maybe_dl)
+        await self._download_file(element, maybe_dl)
 
     @anoncritical
     @_iorepeat(3, "downloading file")
@@ -682,11 +604,11 @@ instance's greatest bottleneck.
         self,
         element: IliasPageElement,
         element_path: PurePath,
-    ) -> Optional[Coroutine[Any, Any, None]]:
+    ) -> None:
         maybe_cl = await self.crawl(element_path)
         if not maybe_cl:
             return None
-        return self._crawl_forum(element, maybe_cl)
+        await self._crawl_forum(element, maybe_cl)
 
     @_iorepeat(3, "crawling forum")
     @anoncritical
@@ -744,141 +666,12 @@ 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 +680,14 @@ 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)
+                return soup
         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]]]
-    ) -> bytes:
+    ) -> BeautifulSoup:
         auth_id = await self._current_auth_id()
 
         form_data = aiohttp.FormData()
@@ -926,22 +707,6 @@ 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 List, Optional, Pattern, Set, Tuple, Union
 from urllib.parse import urljoin
 
 from bs4 import BeautifulSoup, Tag
@@ -64,42 +64,37 @@ class KitIpdCrawler(HttpCrawler):
         self._file_regex = section.link_regex()
 
     async def _run(self) -> None:
-        maybe_cl = await self.crawl(PurePath("."))
+        cl = await self.crawl(PurePath("."))
-        if not maybe_cl:
+        if not cl:
             return
 
-        tasks: List[Awaitable[None]] = []
+        async with cl:
-
-        async with maybe_cl:
             for item in await self._fetch_items():
                 if isinstance(item, KitIpdFolder):
-                    tasks.append(self._crawl_folder(item))
+                    await self._crawl_folder(item)
                 else:
                     # Orphan files are placed in the root folder
-                    tasks.append(self._download_file(PurePath("."), item))
+                    await self._download_file(PurePath("."), item)
-
-        await self.gather(tasks)
 
     async def _crawl_folder(self, folder: KitIpdFolder) -> None:
         path = PurePath(folder.name)
         if not await self.crawl(path):
             return
 
-        tasks = [self._download_file(path, file) for file in folder.files]
+        for file in folder.files:
-
+            await self._download_file(path, file)
-        await self.gather(tasks)
 
     async def _download_file(self, parent: PurePath, file: KitIpdFile) -> None:
         element_path = parent / file.name
-        maybe_dl = await self.download(element_path)
+        dl = await self.download(element_path)
-        if not maybe_dl:
+        if not dl:
             return
 
-        async with maybe_dl as (bar, sink):
+        async with dl as (bar, sink):
             await self._stream_from_url(file.url, sink, bar)
 
     async def _fetch_items(self) -> Set[Union[KitIpdFile, KitIpdFolder]]:
-        page, url = await self.get_page()
+        page, url = await self._get_page()
         elements: List[Tag] = self._find_file_links(page)
         items: Set[Union[KitIpdFile, KitIpdFolder]] = set()
 
@@ -159,12 +154,12 @@ class KitIpdCrawler(HttpCrawler):
 
             sink.done()
 
-    async def get_page(self) -> Tuple[BeautifulSoup, str]:
+    async def _get_page(self) -> Tuple[BeautifulSoup, str]:
-        async with self.session.get(self._url) as request:
+        response = self.session.get(self._url)
-            # The web page for Algorithmen für Routenplanung contains some
+
-            # weird comments that beautifulsoup doesn't parse correctly. This
+        # The web page for Algorithmen für Routenplanung contains some
-            # hack enables those pages to be crawled, and should hopefully not
+        # weird comments that beautifulsoup doesn't parse correctly. This
-            # cause issues on other pages.
+        # hack enables those pages to be crawled, and should hopefully not
-            content = (await request.read()).decode("utf-8")
+        # cause issues on other pages.
-            content = re.sub(r"<!--.*?-->", "", content)
+        content = re.sub(r"<!--.*?-->", "", response.text)
-            return soupify(content.encode("utf-8")), str(request.url)
+        return soupify(content.encode("utf-8")), str(request.url)

PFERD/crawl/local_crawler.py

@@ -71,8 +71,6 @@ class LocalCrawler(Crawler):
         if not cl:
             return
 
-        tasks = []
-
         async with cl:
             await asyncio.sleep(random.uniform(
                 0.5 * self._crawl_delay,
@@ -81,9 +79,7 @@ class LocalCrawler(Crawler):
 
             for child in path.iterdir():
                 pure_child = cl.path / child.name
-                tasks.append(self._crawl_path(child, pure_child))
+                await self._crawl_path(child, pure_child)
-
-        await self.gather(tasks)
 
     async def _crawl_file(self, path: Path, pure: PurePath) -> None:
         stat = path.stat()

PFERD/limiter.py

@@ -1,97 +0,0 @@
-import asyncio
-import time
-from contextlib import asynccontextmanager
-from dataclasses import dataclass
-from typing import AsyncIterator, Optional
-
-
-@dataclass
-class Slot:
-    active: bool = False
-    last_left: Optional[float] = None
-
-
-class Limiter:
-    def __init__(
-            self,
-            task_limit: int,
-            download_limit: int,
-            task_delay: float
-    ):
-        if task_limit <= 0:
-            raise ValueError("task limit must be at least 1")
-        if download_limit <= 0:
-            raise ValueError("download limit must be at least 1")
-        if download_limit > task_limit:
-            raise ValueError("download limit can't be greater than task limit")
-        if task_delay < 0:
-            raise ValueError("Task delay must not be negative")
-
-        self._slots = [Slot() for _ in range(task_limit)]
-        self._downloads = download_limit
-        self._delay = task_delay
-
-        self._condition = asyncio.Condition()
-
-    def _acquire_slot(self) -> Optional[Slot]:
-        for slot in self._slots:
-            if not slot.active:
-                slot.active = True
-                return slot
-
-        return None
-
-    async def _wait_for_slot_delay(self, slot: Slot) -> None:
-        if slot.last_left is not None:
-            delay = slot.last_left + self._delay - time.time()
-            if delay > 0:
-                await asyncio.sleep(delay)
-
-    def _release_slot(self, slot: Slot) -> None:
-        slot.last_left = time.time()
-        slot.active = False
-
-    @asynccontextmanager
-    async def limit_crawl(self) -> AsyncIterator[None]:
-        slot: Slot
-        async with self._condition:
-            while True:
-                if found_slot := self._acquire_slot():
-                    slot = found_slot
-                    break
-                await self._condition.wait()
-
-        await self._wait_for_slot_delay(slot)
-
-        try:
-            yield
-        finally:
-            async with self._condition:
-                self._release_slot(slot)
-                self._condition.notify_all()
-
-    @asynccontextmanager
-    async def limit_download(self) -> AsyncIterator[None]:
-        slot: Slot
-        async with self._condition:
-            while True:
-                if self._downloads <= 0:
-                    await self._condition.wait()
-                    continue
-
-                if found_slot := self._acquire_slot():
-                    slot = found_slot
-                    self._downloads -= 1
-                    break
-
-                await self._condition.wait()
-
-        await self._wait_for_slot_delay(slot)
-
-        try:
-            yield
-        finally:
-            async with self._condition:
-                self._release_slot(slot)
-                self._downloads += 1
-                self._condition.notify_all()

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/utils.py

@@ -92,17 +92,32 @@ def url_set_query_params(url: str, params: Dict[str, str]) -> str:
 
 
 def str_path(path: PurePath) -> str:
+    """
+    Turn a path into a string, in a platform-independent way.
+
+    This function always uses "/" as path separator, even on Windows.
+    """
     if not path.parts:
         return "."
     return "/".join(path.parts)
 
 
 def fmt_path(path: PurePath) -> str:
+    """
+    Turn a path into a delimited string.
+
+    This is useful if file or directory names contain weird characters like
+    newlines, leading/trailing whitespace or unprintable characters. This way,
+    they are escaped and visible to the user.
+    """
     return repr(str_path(path))
 
 
 def fmt_real_path(path: Path) -> str:
-    return repr(str(path.absolute()))
+    """
+    Like fmt_path, but resolves the path before converting it to a string.
+    """
+    return fmt_path(path.absolute())
 
 
 class ReusableAsyncContextManager(ABC, Generic[T]):

scripts/setup

@@ -14,4 +14,4 @@ pip install --editable .
 
 # Installing tools and type hints
 pip install --upgrade mypy flake8 autopep8 isort pyinstaller
-pip install --upgrade types-chardet types-certifi
+mypy PFERD --install-types --non-interactive

setup.cfg

@@ -11,6 +11,7 @@ install_requires =
   rich>=11.0.0
   keyring>=23.5.0
   certifi>=2021.10.8
+  requests>=2.28.1
 
 [options.entry_points]
 console_scripts =