Ignore SCORM learning modules

CHANGELOG.md

@@ -28,6 +28,9 @@ ambiguous situations.
 - Crawling of button cards without descriptions
 - Abort crawling when encountering an unexpected ilias root page redirect
 - Remove size suffix for files in content pages
+- Sanitize ascii control characters on Windows
+- Crawling of paginated past meetings
+- Ignore SCORM learning modules
 
 ### Added
 - `no-delete-prompt-override` conflict resolution strategy
@@ -36,6 +39,7 @@ ambiguous situations.
   message. This combines nicely with the `no-delete-prompt-override` strategy,
   causing PFERD to mostly ignore local-only files.
 - support for mediacast video listings
+- crawling of files in info tab
 
 ## 3.4.3 - 2022-11-29
 

PFERD/crawl/ilias/kit_ilias_html.py

@@ -22,10 +22,12 @@ class IliasElementType(Enum):
     FOLDER = "folder"
     FORUM = "forum"
     LINK = "link"
+    INFO_TAB = "info_tab"
     LEARNING_MODULE = "learning_module"
     BOOKING = "booking"
     MEETING = "meeting"
     SURVEY = "survey"
+    SCORM_LEARNING_MODULE = "scorm_learning_module"
     MEDIACAST_VIDEO_FOLDER = "mediacast_video_folder"
     MEDIACAST_VIDEO = "mediacast_video"
     OPENCAST_VIDEO = "opencast_video"
@@ -120,9 +122,25 @@ class IliasPage:
         if self._is_content_page():
             log.explain("Page is a content page, searching for elements")
             return self._find_copa_entries()
+        if self._is_info_tab():
+            log.explain("Page is info tab, searching for elements")
+            return self._find_info_tab_entries()
         log.explain("Page is a normal folder, searching for elements")
         return self._find_normal_entries()
 
+    def get_info_tab(self) -> Optional[IliasPageElement]:
+        tab: Optional[Tag] = self._soup.find(
+            name="a",
+            attrs={"href": lambda x: x and "cmdClass=ilinfoscreengui" in x}
+        )
+        if tab is not None:
+            return IliasPageElement(
+                IliasElementType.INFO_TAB,
+                self._abs_url_from_link(tab),
+                "infos"
+            )
+        return None
+
     def get_description(self) -> Optional[BeautifulSoup]:
         def is_interesting_class(name: str) -> bool:
             return name in ["ilCOPageSection", "ilc_Paragraph", "ilc_va_ihcap_VAccordIHeadCap"]
@@ -209,7 +227,11 @@ class IliasPage:
             log.explain("Requesting *all* future meetings")
             return self._uncollapse_future_meetings_url()
         if not self._is_content_tab_selected():
-            return self._select_content_page_url()
+            if self._page_type != IliasElementType.INFO_TAB:
+                log.explain("Selecting content tab")
+                return self._select_content_page_url()
+            else:
+                log.explain("Crawling info tab, skipping content select")
         return None
 
     def _is_forum_page(self) -> bool:
@@ -272,7 +294,10 @@ class IliasPage:
         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})
+        element = self._soup.find(
+            "a",
+            attrs={"href": lambda x: x and ("crs_next_sess=1" in x or "crs_prev_sess=1" in x)}
+        )
         if not element:
             return None
         link = self._abs_url_from_link(element)
@@ -281,6 +306,10 @@ class IliasPage:
     def _is_content_tab_selected(self) -> bool:
         return self._select_content_page_url() is None
 
+    def _is_info_tab(self) -> bool:
+        might_be_info = self._soup.find("form", attrs={"name": lambda x: x == "formInfoScreen"}) is not None
+        return self._page_type == IliasElementType.INFO_TAB and might_be_info
+
     def _select_content_page_url(self) -> Optional[IliasPageElement]:
         tab = self._soup.find(
             id="tab_view_content",
@@ -389,6 +418,23 @@ class IliasPage:
 
         return items
 
+    def _find_info_tab_entries(self) -> List[IliasPageElement]:
+        items = []
+        links: List[Tag] = self._soup.select("a.il_ContainerItemCommand")
+
+        for link in links:
+            if "cmdClass=ilobjcoursegui" not in link["href"]:
+                continue
+            if "cmd=sendfile" not in link["href"]:
+                continue
+            items.append(IliasPageElement(
+                IliasElementType.FILE,
+                self._abs_url_from_link(link),
+                _sanitize_path_name(link.getText())
+            ))
+
+        return items
+
     def _find_opencast_video_entries(self) -> List[IliasPageElement]:
         # ILIAS has three stages for video pages
         # 1. The initial dummy page without any videos. This page contains the link to the listing
@@ -908,6 +954,9 @@ class IliasPage:
         if "baseClass=ilMediaCastHandlerGUI" in parsed_url.query:
             return IliasElementType.MEDIACAST_VIDEO_FOLDER
 
+        if "baseClass=ilSAHSPresentationGUI" in parsed_url.query:
+            return IliasElementType.SCORM_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.
 
@@ -949,7 +998,11 @@ 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}):
+        is_session_expansion_button = found_parent.find(
+            "a",
+            attrs={"href": lambda x: x and ("crs_next_sess=" in x or "crs_prev_sess=" in x)}
+        )
+        if img_tag is None and is_session_expansion_button:
             log.explain("Found session expansion button, skipping it as it has no content")
             return None
 
@@ -982,6 +1035,9 @@ class IliasPage:
         if str(img_tag["src"]).endswith("icon_mcst.svg"):
             return IliasElementType.MEDIACAST_VIDEO_FOLDER
 
+        if str(img_tag["src"]).endswith("icon_sahs.svg"):
+            return IliasElementType.SCORM_LEARNING_MODULE
+
         return IliasElementType.FOLDER
 
     @staticmethod

PFERD/crawl/ilias/kit_ilias_web_crawler.py

@@ -85,6 +85,7 @@ _DIRECTORY_PAGES: Set[IliasElementType] = set([
     IliasElementType.EXERCISE,
     IliasElementType.EXERCISE_FILES,
     IliasElementType.FOLDER,
+    IliasElementType.INFO_TAB,
     IliasElementType.MEETING,
     IliasElementType.MEDIACAST_VIDEO_FOLDER,
     IliasElementType.OPENCAST_VIDEO_FOLDER,
@@ -262,6 +263,8 @@ instance's greatest bottleneck.
                         next_stage_url = None
 
                 elements.extend(page.get_child_elements())
+                if info_tab := page.get_info_tab():
+                    elements.append(info_tab)
                 if description_string := page.get_description():
                     description.append(description_string)
 
@@ -400,6 +403,14 @@ instance's greatest bottleneck.
                 "[bright_black](surveys contain no relevant data)"
             )
             return None
+        elif element.type == IliasElementType.SCORM_LEARNING_MODULE:
+            log.status(
+                "[bold bright_black]",
+                "Ignored",
+                fmt_path(element_path),
+                "[bright_black](scorm learning modules are not supported)"
+            )
+            return None
         elif element.type == IliasElementType.LEARNING_MODULE:
             return await self._handle_learning_module(element, element_path)
         elif element.type == IliasElementType.LINK:
@@ -705,7 +716,7 @@ instance's greatest bottleneck.
                 log.explain(f"URL: {next_stage_url}")
 
                 soup = await self._get_page(next_stage_url)
-                page = IliasPage(soup, next_stage_url, None)
+                page = IliasPage(soup, next_stage_url, element)
 
                 if next := page.get_next_stage_element():
                     next_stage_url = next.url
@@ -768,14 +779,14 @@ instance's greatest bottleneck.
             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)
+            page = IliasPage(soup, element.url, element)
             if next := page.get_learning_module_data():
                 elements.extend(await self._crawl_learning_module_direction(
-                    cl.path, next.previous_url, "left"
+                    cl.path, next.previous_url, "left", element
                 ))
                 elements.append(next)
                 elements.extend(await self._crawl_learning_module_direction(
-                    cl.path, next.next_url, "right"
+                    cl.path, next.next_url, "right", element
                 ))
 
         # Reflect their natural ordering in the file names
@@ -797,7 +808,8 @@ instance's greatest bottleneck.
         self,
         path: PurePath,
         start_url: Optional[str],
-        dir: Union[Literal["left"], Literal["right"]]
+        dir: Union[Literal["left"], Literal["right"]],
+        parent_element: IliasPageElement
     ) -> List[IliasLearningModulePage]:
         elements: List[IliasLearningModulePage] = []
 
@@ -810,7 +822,7 @@ instance's greatest bottleneck.
             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)
+            page = IliasPage(soup, next_element_url, parent_element)
             if next := page.get_learning_module_data():
                 elements.append(next)
                 if dir == "left":
@@ -893,7 +905,7 @@ instance's greatest bottleneck.
             soup = soupify(await request.read())
             if self._is_logged_in(soup):
                 return self._verify_page(soup, url, root_page_allowed)
-        raise CrawlError("get_page failed even after authenticating")
+        raise CrawlError(f"get_page failed even after authenticating on {url!r}")
 
     def _verify_page(self, soup: BeautifulSoup, url: str, root_page_allowed: bool) -> BeautifulSoup:
         if IliasPage.is_root_page(soup) and not root_page_allowed:

PFERD/deduplicator.py

@@ -14,7 +14,7 @@ def name_variants(path: PurePath) -> Iterator[PurePath]:
 
 
 class Deduplicator:
-    FORBIDDEN_CHARS = '<>:"/\\|?*'
+    FORBIDDEN_CHARS = '<>:"/\\|?*' + "".join([chr(i) for i in range(0, 32)])
     FORBIDDEN_NAMES = {
         "CON", "PRN", "AUX", "NUL",
         "COM1", "COM2", "COM3", "COM4", "COM5", "COM6", "COM7", "COM8", "COM9",