Bump version to 3.4.3

Thanks, burg113

CHANGELOG.md

@@ -22,9 +22,30 @@ ambiguous situations.
 
 ## Unreleased
 
+## 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
-- Forum crawling crashing when parsing empty (= 0 messages) threads
+- 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

@@ -181,6 +181,7 @@ script once per day should be fine.
   redirect to the actual URL. Set to a negative value to disable the automatic
   redirect. (Default: `-1`)
 - `videos`: Whether to download videos. (Default: `no`)
+- `forums`: Whether to download forum threads. (Default: `no`)
 - `http_timeout`: The timeout (in seconds) for all HTTP requests. (Default:
   `20.0`)
 
@@ -289,7 +290,7 @@ 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 `bar/wargl`
+- Converts `foo/bar/wargl` into `baz/wargl`
 
 Example: `foo/bar --> !`
 - Doesn't match `foo`, `a/foo/bar` or `foo/baz`

PFERD/crawl/ilias/kit_ilias_html.py

@@ -24,6 +24,7 @@ class IliasElementType(Enum):
     LINK = "link"
     BOOKING = "booking"
     MEETING = "meeting"
+    SURVEY = "survey"
     VIDEO = "video"
     VIDEO_PLAYER = "video_player"
     VIDEO_FOLDER = "video_folder"
@@ -133,7 +134,7 @@ 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",
@@ -365,7 +366,7 @@ 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\s*")
+            name="a", text=re.compile(r"\s*(Abspielen|Play)\s*")
         )
 
         results: List[IliasPageElement] = []
@@ -730,6 +731,10 @@ 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
 
         _unexpected_html_warning()
         log.warn_contd(f"Could not extract type from {icon} for card title {card_title}")

PFERD/crawl/ilias/kit_ilias_web_crawler.py

@@ -194,7 +194,7 @@ instance's greatest bottleneck.
         self._links = section.links()
         self._videos = section.videos()
         self._forums = section.forums()
-        self._visited_urls: Set[str] = set()
+        self._visited_urls: Dict[str, PurePath] = dict()
 
     async def _run(self) -> None:
         if isinstance(self._target, int):
@@ -348,9 +348,11 @@ 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}. Aborting subpath"
+                f"Found second path to element {element.name!r} at {element.url!r}. "
+                + f"First path: {fmt_path(self._visited_urls[element.url])}. "
+                + f"Second path: {fmt_path(parent_path)}."
             )
-        self._visited_urls.add(element.url)
+        self._visited_urls[element.url] = parent_path
 
         element_path = PurePath(parent_path, element.name)
 
@@ -377,9 +379,20 @@ instance's greatest bottleneck.
                 return None
             return await self._handle_forum(element, element_path)
         elif element.type == IliasElementType.TEST:
-            log.explain_topic(f"Decision: Crawl {fmt_path(element_path)}")
+            log.status(
-            log.explain("Tests contain no relevant files")
+                "[bold bright_black]",
-            log.explain("Answer: No")
+                "Ignored",
+                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.LINK:
             return await self._handle_link(element, element_path)

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, Union
+from typing import Awaitable, List, Optional, Pattern, Set, Tuple, 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 = await self.get_page()
+        page, url = await self.get_page()
         elements: List[Tag] = self._find_file_links(page)
         items: Set[Union[KitIpdFile, KitIpdFolder]] = set()
 
         for element in elements:
             folder_label = self._find_folder_label(element)
             if folder_label:
-                folder = self._extract_folder(folder_label)
+                folder = self._extract_folder(folder_label, url)
                 if folder not in items:
                     items.add(folder)
                     folder.explain()
             else:
-                file = self._extract_file(element)
+                file = self._extract_file(element, url)
                 items.add(file)
                 log.explain_topic(f"Orphan file {file.name!r} (href={file.url!r})")
                 log.explain("Attributing it to root folder")
 
         return items
 
-    def _extract_folder(self, folder_tag: Tag) -> KitIpdFolder:
+    def _extract_folder(self, folder_tag: Tag, url: str) -> KitIpdFolder:
         files: List[KitIpdFile] = []
         name = folder_tag.getText().strip()
 
         container: Tag = folder_tag.findNextSibling(name="table")
         for link in self._find_file_links(container):
-            files.append(self._extract_file(link))
+            files.append(self._extract_file(link, url))
 
         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) -> KitIpdFile:
+    def _extract_file(self, link: Tag, url: str) -> KitIpdFile:
-        url = self._abs_url_from_link(link)
+        url = self._abs_url_from_link(url, link)
         name = os.path.basename(url)
         return KitIpdFile(name, url)
 
     def _find_file_links(self, tag: Union[Tag, BeautifulSoup]) -> List[Tag]:
         return tag.findAll(name="a", attrs={"href": self._file_regex})
 
-    def _abs_url_from_link(self, link_tag: Tag) -> str:
+    def _abs_url_from_link(self, url: str, link_tag: Tag) -> str:
-        return urljoin(self._url, link_tag.get("href"))
+        return urljoin(url, link_tag.get("href"))
 
     async def _stream_from_url(self, url: str, sink: FileSink, bar: ProgressBar) -> None:
         async with self.session.get(url, allow_redirects=False) as resp:
@@ -159,7 +159,7 @@ class KitIpdCrawler(HttpCrawler):
 
             sink.done()
 
-    async def get_page(self) -> BeautifulSoup:
+    async def get_page(self) -> Tuple[BeautifulSoup, str]:
         async with self.session.get(self._url) as request:
             # The web page for Algorithmen für Routenplanung contains some
             # weird comments that beautifulsoup doesn't parse correctly. This
@@ -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"))
+            return soupify(content.encode("utf-8")), str(request.url)

PFERD/version.py

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

README.md

@@ -30,7 +30,10 @@ 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).