Bump version to 3.4.3

Thanks, burg113

CHANGELOG.md

@@ -22,6 +22,31 @@ 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
+- 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
 
 ### Added

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"
@@ -59,6 +60,7 @@ class IliasPageElement:
 class IliasDownloadForumData:
     url: str
     form_data: Dict[str, Union[str, List[str]]]
+    empty: bool
 
 
 @dataclass
@@ -130,24 +132,32 @@ class IliasPage:
             return None
         post_url = self._abs_url_from_relative(form["action"])
 
-        form_data: Dict[str, Union[str, List[ſtr]]] = {
-            "thread_ids[]": [f["value"] for f in form.find_all(attrs={"name": "thread_ids[]"})],
+        thread_ids = [f["value"] for f in form.find_all(attrs={"name": "thread_ids[]"})]
+
+        form_data: Dict[str, Union[str, List[str]]] = {
+            "thread_ids[]": thread_ids,
             "selected_cmd2": "html",
             "select_cmd2": "Ausführen",
             "selected_cmd": "",
         }
 
-        return IliasDownloadForumData(post_url, form_data)
+        return IliasDownloadForumData(url=post_url, form_data=form_data, empty=len(thread_ids) == 0)
 
     def get_next_stage_element(self) -> Optional[IliasPageElement]:
         if self._is_forum_page():
             if "trows=800" in self._page_url:
                 return None
+            log.explain("Requesting *all* forum threads")
             return self._get_show_max_forum_entries_per_page_url()
         if self._is_ilias_opencast_embedding():
+            log.explain("Unwrapping opencast embedding")
             return self.get_child_elements()[0]
         if self._page_type == IliasElementType.VIDEO_FOLDER_MAYBE_PAGINATED:
+            log.explain("Unwrapping video pagination")
             return self._find_video_entries_paginated()[0]
+        if self._contains_collapsed_future_meetings():
+            log.explain("Requesting *all* future meetings")
+            return self._uncollapse_future_meetings_url()
         return None
 
     def _is_forum_page(self) -> bool:
@@ -200,6 +210,16 @@ class IliasPage:
             return False
         return "target=copa_" in link.get("value")
 
+    def _contains_collapsed_future_meetings(self) -> bool:
+        return self._uncollapse_future_meetings_url() is not None
+
+    def _uncollapse_future_meetings_url(self) -> Optional[IliasPageElement]:
+        element = self._soup.find("a", attrs={"href": lambda x: x and "crs_next_sess=1" in x})
+        if not element:
+            return None
+        link = self._abs_url_from_link(element)
+        return IliasPageElement(IliasElementType.FOLDER, link, "show all meetings")
+
     def _player_to_video(self) -> List[IliasPageElement]:
         # Fetch the actual video page. This is a small wrapper page initializing a javscript
         # player. Sadly we can not execute that JS. The actual video stream url is nowhere
@@ -346,7 +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] = []
@@ -711,6 +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}")
@@ -790,6 +814,10 @@ class IliasPage:
         if img_tag is None:
             img_tag = found_parent.select_one("img.icon")
 
+        if img_tag is None and found_parent.find("a", attrs={"href": lambda x: x and "crs_next_sess=" in x}):
+            log.explain("Found session expansion button, skipping it as it has no content")
+            return None
+
         if img_tag is None:
             _unexpected_html_warning()
             log.warn_contd(f"Tried to figure out element type, but did not find an image for {url}")
@@ -937,6 +965,13 @@ def parse_ilias_forum_export(forum_export: BeautifulSoup) -> List[IliasForumThre
     for p in forum_export.select("body > p"):
         title_tag = p
         content_tag = p.find_next_sibling("ul")
+
+        if not content_tag:
+            # ILIAS allows users to delete the initial post while keeping the thread open
+            # This produces empty threads without *any* content.
+            # I am not sure why you would want this, but ILIAS makes it easy to do.
+            continue
+
         title = p.find("b").text
         if ":" in title:
             title = title[title.find(":") + 1:]

PFERD/crawl/ilias/kit_ilias_web_crawler.py

@@ -23,6 +23,12 @@ from .kit_ilias_html import (IliasElementType, IliasForumThread, IliasPage, Ilia
 
 TargetType = Union[str, int]
 
+_ILIAS_URL = "https://ilias.studium.kit.edu"
+
+
+class KitShibbolethBackgroundLoginSuccessful():
+    pass
+
 
 class KitIliasWebCrawlerSection(HttpCrawlerSection):
     def target(self) -> TargetType:
@@ -36,7 +42,7 @@ class KitIliasWebCrawlerSection(HttpCrawlerSection):
         if target == "desktop":
             # Full personal desktop
             return target
-        if target.startswith("https://ilias.studium.kit.edu"):
+        if target.startswith(_ILIAS_URL):
             # ILIAS URL
             return target
 
@@ -181,14 +187,14 @@ instance's greatest bottleneck.
             section.tfa_auth(authenticators),
         )
 
-        self._base_url = "https://ilias.studium.kit.edu"
+        self._base_url = _ILIAS_URL
 
         self._target = section.target()
         self._link_file_redirect_delay = section.link_redirect_delay()
         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):
@@ -228,19 +234,28 @@ instance's greatest bottleneck.
         async def gather_elements() -> None:
             elements.clear()
             async with cl:
-                soup = await self._get_page(url)
-
-                if 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")
+                next_stage_url: Optional[str] = url
+                current_parent = None
 
                 # Duplicated code, but the root page is special - we want to avoid fetching it twice!
-                log.explain_topic("Parsing root HTML page")
-                log.explain(f"URL: {url}")
-                page = IliasPage(soup, url, None)
-                elements.extend(page.get_child_elements())
+                while next_stage_url:
+                    soup = await self._get_page(next_stage_url)
 
+                    if current_parent is None and expected_id is not None:
+                        perma_link_element: Tag = soup.find(id="current_perma_link")
+                        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)
 
@@ -333,9 +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)
 
@@ -362,9 +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.explain("Tests contain no relevant files")
-            log.explain("Answer: No")
+            log.status(
+                "[bold bright_black]",
+                "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)
@@ -658,7 +686,7 @@ instance's greatest bottleneck.
     @_iorepeat(3, "crawling forum")
     @anoncritical
     async def _crawl_forum(self, element: IliasPageElement, cl: CrawlToken) -> None:
-        elements = []
+        elements: List[IliasForumThread] = []
 
         async with cl:
             next_stage_url = element.url
@@ -677,6 +705,10 @@ instance's greatest bottleneck.
             download_data = page.get_download_forum_data()
             if not download_data:
                 raise CrawlWarning("Failed to extract forum data")
+            if download_data.empty:
+                log.explain("Forum had no threads")
+                elements = []
+                return
             html = await self._post_authenticated(download_data.url, download_data.form_data)
             elements = parse_ilias_forum_export(soupify(html))
 
@@ -804,14 +836,17 @@ class KitShibbolethLogin:
 
         # Equivalent: Click on "Mit KIT-Account anmelden" button in
         # https://ilias.studium.kit.edu/login.php
-        url = "https://ilias.studium.kit.edu/shib_login.php"
+        url = f"{_ILIAS_URL}/shib_login.php"
         data = {
             "sendLogin": "1",
             "idp_selection": "https://idp.scc.kit.edu/idp/shibboleth",
             "il_target": "",
             "home_organization_selection": "Weiter",
         }
-        soup: BeautifulSoup = await _shib_post(sess, url, data)
+        soup: Union[BeautifulSoup, KitShibbolethBackgroundLoginSuccessful] = await _shib_post(sess, url, data)
+
+        if isinstance(soup, KitShibbolethBackgroundLoginSuccessful):
+            return
 
         # Attempt to login using credentials, if necessary
         while not self._login_successful(soup):
@@ -850,7 +885,7 @@ class KitShibbolethLogin:
         # (or clicking "Continue" if you have JS disabled)
         relay_state = soup.find("input", {"name": "RelayState"})
         saml_response = soup.find("input", {"name": "SAMLResponse"})
-        url = "https://ilias.studium.kit.edu/Shibboleth.sso/SAML2/POST"
+        url = f"{_ILIAS_URL}/Shibboleth.sso/SAML2/POST"
         data = {  # using the info obtained in the while loop above
             "RelayState": relay_state["value"],
             "SAMLResponse": saml_response["value"],
@@ -899,22 +934,35 @@ async def _post(session: aiohttp.ClientSession, url: str, data: Any) -> Beautifu
         return soupify(await response.read())
 
 
-async def _shib_post(session: aiohttp.ClientSession, url: str, data: Any) -> BeautifulSoup:
+async def _shib_post(
+    session: aiohttp.ClientSession,
+    url: str,
+    data: Any
+) -> Union[BeautifulSoup, KitShibbolethBackgroundLoginSuccessful]:
     """
     aiohttp unescapes '/' and ':' in URL query parameters which is not RFC compliant and rejected
     by Shibboleth. Thanks a lot. So now we unroll the requests manually, parse location headers and
     build encoded URL objects ourselves... Who thought mangling location header was a good idea??
     """
+    log.explain_topic("Shib login POST")
     async with session.post(url, data=data, allow_redirects=False) as response:
         location = response.headers.get("location")
+        log.explain(f"Got location {location!r}")
         if not location:
             raise CrawlWarning(f"Login failed (1), no location header present at {url}")
         correct_url = yarl.URL(location, encoded=True)
+        log.explain(f"Corrected location to {correct_url!r}")
+
+        if str(correct_url).startswith(_ILIAS_URL):
+            log.explain("ILIAS recognized our shib token and logged us in in the background, returning")
+            return KitShibbolethBackgroundLoginSuccessful()
 
         async with session.get(correct_url, allow_redirects=False) as response:
             location = response.headers.get("location")
+            log.explain(f"Redirected to {location!r} with status {response.status}")
             # If shib still still has a valid session, it will directly respond to the request
             if location is None:
+                log.explain("Shib recognized us, returning its response directly")
                 return soupify(await response.read())
 
             as_yarl = yarl.URL(response.url)
@@ -928,6 +976,7 @@ async def _shib_post(session: aiohttp.ClientSession, url: str, data: Any) -> Bea
                 path=location,
                 encoded=True
             )
+            log.explain(f"Corrected location to {correct_url!r}")
 
             async with session.get(correct_url, allow_redirects=False) as response:
                 return soupify(await response.read())

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:
-        url = self._abs_url_from_link(link)
+    def _extract_file(self, link: Tag, url: str) -> KitIpdFile:
+        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:
-        return urljoin(self._url, link_tag.get("href"))
+    def _abs_url_from_link(self, url: str, link_tag: Tag) -> str:
+        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).