2021-05-19 21:34:36 +02:00
|
|
|
import json
|
|
|
|
|
import re
|
|
|
|
|
from dataclasses import dataclass
|
|
|
|
|
from datetime import date, datetime, timedelta
|
|
|
|
|
from enum import Enum
|
2022-05-24 23:28:09 +02:00
|
|
|
from typing import Dict, List, Optional, Union
|
2021-05-19 21:34:36 +02:00
|
|
|
from urllib.parse import urljoin, urlparse
|
|
|
|
|
|
|
|
|
|
from bs4 import BeautifulSoup, Tag
|
|
|
|
|
|
2021-05-23 18:12:51 +02:00
|
|
|
from PFERD.logging import log
|
2021-05-19 21:34:36 +02:00
|
|
|
from PFERD.utils import url_set_query_params
|
|
|
|
|
|
|
|
|
|
TargetType = Union[str, int]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class IliasElementType(Enum):
|
|
|
|
|
EXERCISE = "exercise"
|
2021-05-24 16:22:51 +02:00
|
|
|
EXERCISE_FILES = "exercise_files" # own submitted files
|
2021-05-24 16:32:29 +02:00
|
|
|
TEST = "test" # an online test. Will be ignored currently.
|
2021-05-19 21:34:36 +02:00
|
|
|
FILE = "file"
|
|
|
|
|
FOLDER = "folder"
|
|
|
|
|
FORUM = "forum"
|
|
|
|
|
LINK = "link"
|
2021-07-06 16:13:23 +02:00
|
|
|
BOOKING = "booking"
|
2021-05-19 21:34:36 +02:00
|
|
|
MEETING = "meeting"
|
2022-10-24 18:36:34 +02:00
|
|
|
SURVEY = "survey"
|
2021-05-19 21:34:36 +02:00
|
|
|
VIDEO = "video"
|
|
|
|
|
VIDEO_PLAYER = "video_player"
|
|
|
|
|
VIDEO_FOLDER = "video_folder"
|
|
|
|
|
VIDEO_FOLDER_MAYBE_PAGINATED = "video_folder_maybe_paginated"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@dataclass
|
|
|
|
|
class IliasPageElement:
|
|
|
|
|
type: IliasElementType
|
|
|
|
|
url: str
|
|
|
|
|
name: str
|
|
|
|
|
mtime: Optional[datetime] = None
|
|
|
|
|
description: Optional[str] = None
|
|
|
|
|
|
2021-07-06 17:45:12 +02:00
|
|
|
def id(self) -> str:
|
2022-01-08 16:58:15 +01:00
|
|
|
regexes = [
|
|
|
|
|
r"eid=(?P<id>[0-9a-z\-]+)",
|
|
|
|
|
r"file_(?P<id>\d+)",
|
|
|
|
|
r"ref_id=(?P<id>\d+)",
|
|
|
|
|
r"target=[a-z]+_(?P<id>\d+)"
|
|
|
|
|
]
|
2021-07-06 17:45:12 +02:00
|
|
|
|
|
|
|
|
for regex in regexes:
|
|
|
|
|
if match := re.search(regex, self.url):
|
|
|
|
|
return match.groupdict()["id"]
|
|
|
|
|
|
|
|
|
|
# Fall back to URL
|
|
|
|
|
log.warn(f"Didn't find identity for {self.name} - {self.url}. Please report this.")
|
|
|
|
|
return self.url
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
|
2022-05-24 23:28:09 +02:00
|
|
|
@dataclass
|
|
|
|
|
class IliasDownloadForumData:
|
|
|
|
|
url: str
|
|
|
|
|
form_data: Dict[str, Union[str, List[str]]]
|
2022-10-24 13:09:29 +02:00
|
|
|
empty: bool
|
2022-05-24 23:28:09 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
@dataclass
|
|
|
|
|
class IliasForumThread:
|
|
|
|
|
title: str
|
|
|
|
|
title_tag: Tag
|
|
|
|
|
content_tag: Tag
|
|
|
|
|
mtime: Optional[datetime]
|
|
|
|
|
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
class IliasPage:
|
|
|
|
|
|
|
|
|
|
def __init__(self, soup: BeautifulSoup, _page_url: str, source_element: Optional[IliasPageElement]):
|
|
|
|
|
self._soup = soup
|
|
|
|
|
self._page_url = _page_url
|
|
|
|
|
self._page_type = source_element.type if source_element else None
|
|
|
|
|
self._source_name = source_element.name if source_element else ""
|
|
|
|
|
|
|
|
|
|
def get_child_elements(self) -> List[IliasPageElement]:
|
|
|
|
|
"""
|
|
|
|
|
Return all child page elements you can find here.
|
|
|
|
|
"""
|
|
|
|
|
if self._is_video_player():
|
2021-05-23 18:12:51 +02:00
|
|
|
log.explain("Page is a video player, extracting URL")
|
2021-05-19 21:34:36 +02:00
|
|
|
return self._player_to_video()
|
|
|
|
|
if self._is_video_listing():
|
2021-05-23 18:22:29 +02:00
|
|
|
log.explain("Page is a video listing, searching for elements")
|
2021-05-19 21:34:36 +02:00
|
|
|
return self._find_video_entries()
|
|
|
|
|
if self._is_exercise_file():
|
2021-05-23 18:22:29 +02:00
|
|
|
log.explain("Page is an exercise, searching for elements")
|
2021-05-19 21:34:36 +02:00
|
|
|
return self._find_exercise_entries()
|
2022-01-08 16:58:15 +01:00
|
|
|
if self._is_personal_desktop():
|
2022-01-08 20:47:35 +01:00
|
|
|
log.explain("Page is the personal desktop, searching for elements")
|
2022-01-08 16:58:15 +01:00
|
|
|
return self._find_personal_desktop_entries()
|
2022-01-08 20:47:35 +01:00
|
|
|
if self._is_content_page():
|
|
|
|
|
log.explain("Page is a content page, searching for elements")
|
|
|
|
|
return self._find_copa_entries()
|
2021-05-23 18:22:29 +02:00
|
|
|
log.explain("Page is a normal folder, searching for elements")
|
2021-05-19 21:34:36 +02:00
|
|
|
return self._find_normal_entries()
|
|
|
|
|
|
2022-05-11 21:16:09 +02:00
|
|
|
def get_description(self) -> Optional[BeautifulSoup]:
|
|
|
|
|
def is_interesting_class(name: str) -> bool:
|
|
|
|
|
return name in ["ilCOPageSection", "ilc_Paragraph", "ilc_va_ihcap_VAccordIHeadCap"]
|
|
|
|
|
|
|
|
|
|
paragraphs: List[Tag] = self._soup.findAll(class_=is_interesting_class)
|
|
|
|
|
if not paragraphs:
|
|
|
|
|
return None
|
|
|
|
|
|
|
|
|
|
# Extract bits and pieces into a string and parse it again.
|
|
|
|
|
# This ensures we don't miss anything and weird structures are resolved
|
|
|
|
|
# somewhat gracefully.
|
|
|
|
|
raw_html = ""
|
|
|
|
|
for p in paragraphs:
|
|
|
|
|
if p.find_parent(class_=is_interesting_class):
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
# Ignore special listings (like folder groupings)
|
|
|
|
|
if "ilc_section_Special" in p["class"]:
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
raw_html += str(p) + "\n"
|
|
|
|
|
raw_html = f"<body>\n{raw_html}\n</body>"
|
|
|
|
|
|
|
|
|
|
return BeautifulSoup(raw_html, "html.parser")
|
|
|
|
|
|
2022-05-24 23:28:09 +02:00
|
|
|
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:
|
|
|
|
|
return None
|
|
|
|
|
post_url = self._abs_url_from_relative(form["action"])
|
|
|
|
|
|
2022-10-24 13:09:29 +02:00
|
|
|
thread_ids = [f["value"] for f in form.find_all(attrs={"name": "thread_ids[]"})]
|
|
|
|
|
|
2022-10-29 14:08:29 +02:00
|
|
|
form_data: Dict[str, Union[str, List[str]]] = {
|
2022-10-24 13:09:29 +02:00
|
|
|
"thread_ids[]": thread_ids,
|
2022-05-24 23:28:09 +02:00
|
|
|
"selected_cmd2": "html",
|
|
|
|
|
"select_cmd2": "Ausführen",
|
|
|
|
|
"selected_cmd": "",
|
|
|
|
|
}
|
|
|
|
|
|
2022-10-24 13:09:29 +02:00
|
|
|
return IliasDownloadForumData(url=post_url, form_data=form_data, empty=len(thread_ids) == 0)
|
2022-05-24 23:28:09 +02:00
|
|
|
|
2021-06-13 16:50:29 +02:00
|
|
|
def get_next_stage_element(self) -> Optional[IliasPageElement]:
|
2022-05-24 23:28:09 +02:00
|
|
|
if self._is_forum_page():
|
|
|
|
|
if "trows=800" in self._page_url:
|
|
|
|
|
return None
|
2022-10-24 14:33:58 +02:00
|
|
|
log.explain("Requesting *all* forum threads")
|
2022-05-24 23:28:09 +02:00
|
|
|
return self._get_show_max_forum_entries_per_page_url()
|
2021-05-27 00:55:46 +02:00
|
|
|
if self._is_ilias_opencast_embedding():
|
2022-10-24 14:33:58 +02:00
|
|
|
log.explain("Unwrapping opencast embedding")
|
2021-06-13 16:50:29 +02:00
|
|
|
return self.get_child_elements()[0]
|
|
|
|
|
if self._page_type == IliasElementType.VIDEO_FOLDER_MAYBE_PAGINATED:
|
2022-10-24 14:33:58 +02:00
|
|
|
log.explain("Unwrapping video pagination")
|
2021-06-13 16:50:29 +02:00
|
|
|
return self._find_video_entries_paginated()[0]
|
2022-10-24 14:33:58 +02:00
|
|
|
if self._contains_collapsed_future_meetings():
|
|
|
|
|
log.explain("Requesting *all* future meetings")
|
|
|
|
|
return self._uncollapse_future_meetings_url()
|
2022-11-25 12:49:36 +01:00
|
|
|
if not self._is_content_tab_selected():
|
|
|
|
|
return self._select_content_page_url()
|
2021-05-27 00:55:46 +02:00
|
|
|
return None
|
|
|
|
|
|
2022-05-24 23:28:09 +02:00
|
|
|
def _is_forum_page(self) -> bool:
|
|
|
|
|
read_more_btn = self._soup.find(
|
|
|
|
|
"button",
|
|
|
|
|
attrs={"onclick": lambda x: x and "cmdClass=ilobjforumgui&cmd=markAllRead" in x}
|
|
|
|
|
)
|
|
|
|
|
return read_more_btn is not None
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
def _is_video_player(self) -> bool:
|
|
|
|
|
return "paella_config_file" in str(self._soup)
|
|
|
|
|
|
|
|
|
|
def _is_video_listing(self) -> bool:
|
2021-05-27 00:55:46 +02:00
|
|
|
if self._is_ilias_opencast_embedding():
|
|
|
|
|
return True
|
2021-05-19 21:34:36 +02:00
|
|
|
|
|
|
|
|
# Raw listing without ILIAS fluff
|
|
|
|
|
video_element_table: Tag = self._soup.find(
|
|
|
|
|
name="table", id=re.compile(r"tbl_xoct_.+")
|
|
|
|
|
)
|
|
|
|
|
return video_element_table is not None
|
|
|
|
|
|
2021-05-27 00:55:46 +02:00
|
|
|
def _is_ilias_opencast_embedding(self) -> bool:
|
|
|
|
|
# ILIAS fluff around the real opencast html
|
|
|
|
|
if self._soup.find(id="headerimage"):
|
|
|
|
|
element: Tag = self._soup.find(id="headerimage")
|
|
|
|
|
if "opencast" in element.attrs["src"].lower():
|
|
|
|
|
return True
|
|
|
|
|
return False
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
def _is_exercise_file(self) -> bool:
|
|
|
|
|
# we know it from before
|
|
|
|
|
if self._page_type == IliasElementType.EXERCISE:
|
|
|
|
|
return True
|
|
|
|
|
|
|
|
|
|
# We have no suitable parent - let's guesss
|
|
|
|
|
if self._soup.find(id="headerimage"):
|
|
|
|
|
element: Tag = self._soup.find(id="headerimage")
|
|
|
|
|
if "exc" in element.attrs["src"].lower():
|
|
|
|
|
return True
|
|
|
|
|
|
|
|
|
|
return False
|
|
|
|
|
|
2022-01-08 16:58:15 +01:00
|
|
|
def _is_personal_desktop(self) -> bool:
|
|
|
|
|
return self._soup.find("a", attrs={"href": lambda x: x and "block_type=pditems" in x})
|
|
|
|
|
|
2022-01-08 20:47:35 +01:00
|
|
|
def _is_content_page(self) -> bool:
|
|
|
|
|
link = self._soup.find(id="current_perma_link")
|
|
|
|
|
if not link:
|
|
|
|
|
return False
|
|
|
|
|
return "target=copa_" in link.get("value")
|
|
|
|
|
|
2022-10-24 14:33:58 +02:00
|
|
|
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")
|
|
|
|
|
|
2022-11-25 12:49:36 +01:00
|
|
|
def _is_content_tab_selected(self) -> bool:
|
|
|
|
|
return self._select_content_page_url() is None
|
|
|
|
|
|
|
|
|
|
def _select_content_page_url(self) -> Optional[IliasPageElement]:
|
|
|
|
|
tab = self._soup.find(
|
|
|
|
|
id="tab_view_content",
|
|
|
|
|
attrs={"class": lambda x: x is not None and "active" not in x}
|
|
|
|
|
)
|
|
|
|
|
# Already selected (or not found)
|
|
|
|
|
if not tab:
|
|
|
|
|
return None
|
|
|
|
|
link = tab.find("a")
|
|
|
|
|
if link:
|
|
|
|
|
link = self._abs_url_from_link(link)
|
|
|
|
|
return IliasPageElement(IliasElementType.FOLDER, link, "select content page")
|
|
|
|
|
|
|
|
|
|
_unexpected_html_warning()
|
|
|
|
|
log.warn_contd(f"Could not find content tab URL on {self._page_url!r}.")
|
|
|
|
|
log.warn_contd("PFERD might not find content on the course's main page.")
|
|
|
|
|
return None
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
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
|
|
|
|
|
# on the page, but defined in a JS object inside a script tag, passed to the player
|
|
|
|
|
# library.
|
|
|
|
|
# We do the impossible and RegEx the stream JSON object out of the page's HTML source
|
2022-01-08 17:14:40 +01:00
|
|
|
regex = re.compile(
|
2021-05-19 21:34:36 +02:00
|
|
|
r"({\"streams\"[\s\S]+?),\s*{\"paella_config_file", re.IGNORECASE
|
|
|
|
|
)
|
|
|
|
|
json_match = regex.search(str(self._soup))
|
|
|
|
|
|
|
|
|
|
if json_match is None:
|
2021-05-23 18:12:51 +02:00
|
|
|
log.warn("Could not find JSON stream info in video player. Ignoring video.")
|
2021-05-19 21:34:36 +02:00
|
|
|
return []
|
|
|
|
|
json_str = json_match.group(1)
|
|
|
|
|
|
|
|
|
|
# parse it
|
|
|
|
|
json_object = json.loads(json_str)
|
2022-01-08 00:27:34 +01:00
|
|
|
streams = [stream for stream in json_object["streams"]]
|
2021-10-30 18:12:29 +02:00
|
|
|
|
|
|
|
|
# and just fetch the lone video url!
|
|
|
|
|
if len(streams) == 1:
|
|
|
|
|
video_url = streams[0]["sources"]["mp4"][0]["src"]
|
|
|
|
|
return [IliasPageElement(IliasElementType.VIDEO, video_url, self._source_name)]
|
|
|
|
|
|
|
|
|
|
log.explain(f"Found multiple videos for stream at {self._source_name}")
|
|
|
|
|
items = []
|
|
|
|
|
for stream in sorted(streams, key=lambda stream: stream["content"]):
|
|
|
|
|
full_name = f"{self._source_name.replace('.mp4', '')} ({stream['content']}).mp4"
|
|
|
|
|
video_url = stream["sources"]["mp4"][0]["src"]
|
|
|
|
|
items.append(IliasPageElement(IliasElementType.VIDEO, video_url, full_name))
|
|
|
|
|
|
|
|
|
|
return items
|
2021-05-19 21:34:36 +02:00
|
|
|
|
2022-05-24 23:28:09 +02:00
|
|
|
def _get_show_max_forum_entries_per_page_url(self) -> Optional[IliasPageElement]:
|
|
|
|
|
correct_link = self._soup.find(
|
|
|
|
|
"a",
|
|
|
|
|
attrs={"href": lambda x: x and "trows=800" in x and "cmd=showThreads" in x}
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
if not correct_link:
|
|
|
|
|
return None
|
|
|
|
|
|
|
|
|
|
link = self._abs_url_from_link(correct_link)
|
|
|
|
|
|
|
|
|
|
return IliasPageElement(IliasElementType.FORUM, link, "show all forum threads")
|
|
|
|
|
|
2022-01-08 16:58:15 +01:00
|
|
|
def _find_personal_desktop_entries(self) -> List[IliasPageElement]:
|
|
|
|
|
items: List[IliasPageElement] = []
|
|
|
|
|
|
|
|
|
|
titles: List[Tag] = self._soup.select(".il-item-title")
|
|
|
|
|
for title in titles:
|
|
|
|
|
link = title.find("a")
|
|
|
|
|
name = _sanitize_path_name(link.text.strip())
|
|
|
|
|
url = self._abs_url_from_link(link)
|
|
|
|
|
|
|
|
|
|
type = self._find_type_from_link(name, link, url)
|
|
|
|
|
if not type:
|
|
|
|
|
_unexpected_html_warning()
|
|
|
|
|
log.warn_contd(f"Could not extract type for {link}")
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
log.explain(f"Found {name!r}")
|
2022-01-08 19:59:42 +01:00
|
|
|
|
|
|
|
|
if type == IliasElementType.FILE and "_download" not in url:
|
|
|
|
|
url = re.sub(r"(target=file_\d+)", r"\1_download", url)
|
|
|
|
|
log.explain("Rewired file URL to include download part")
|
|
|
|
|
|
2022-01-08 16:58:15 +01:00
|
|
|
items.append(IliasPageElement(type, url, name))
|
|
|
|
|
|
|
|
|
|
return items
|
|
|
|
|
|
2022-01-08 20:47:35 +01:00
|
|
|
def _find_copa_entries(self) -> List[IliasPageElement]:
|
|
|
|
|
items: List[IliasPageElement] = []
|
|
|
|
|
links: List[Tag] = self._soup.findAll(class_="ilc_flist_a_FileListItemLink")
|
|
|
|
|
|
|
|
|
|
for link in links:
|
|
|
|
|
url = self._abs_url_from_link(link)
|
|
|
|
|
name = _sanitize_path_name(link.getText().strip().replace("\t", ""))
|
|
|
|
|
|
|
|
|
|
if "file_id" not in url:
|
|
|
|
|
_unexpected_html_warning()
|
|
|
|
|
log.warn_contd(f"Found unknown content page item {name!r} with url {url!r}")
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
items.append(IliasPageElement(IliasElementType.FILE, url, name))
|
|
|
|
|
|
|
|
|
|
return items
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
def _find_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
|
|
|
|
|
# 2. The video listing which might be paginated
|
|
|
|
|
# 3. An unpaginated video listing (or at least one that includes 800 videos)
|
|
|
|
|
#
|
|
|
|
|
# We need to figure out where we are.
|
|
|
|
|
|
|
|
|
|
video_element_table: Tag = self._soup.find(
|
|
|
|
|
name="table", id=re.compile(r"tbl_xoct_.+")
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
if video_element_table is None:
|
|
|
|
|
# We are in stage 1
|
|
|
|
|
# The page is actually emtpy but contains the link to stage 2
|
|
|
|
|
content_link: Tag = self._soup.select_one("#tab_series a")
|
|
|
|
|
url: str = self._abs_url_from_link(content_link)
|
|
|
|
|
query_params = {"limit": "800", "cmd": "asyncGetTableGUI", "cmdMode": "asynch"}
|
|
|
|
|
url = url_set_query_params(url, query_params)
|
2021-05-27 17:59:22 +02:00
|
|
|
log.explain("Found ILIAS video frame page, fetching actual content next")
|
2021-05-19 21:34:36 +02:00
|
|
|
return [IliasPageElement(IliasElementType.VIDEO_FOLDER_MAYBE_PAGINATED, url, "")]
|
|
|
|
|
|
|
|
|
|
is_paginated = self._soup.find(id=re.compile(r"tab_page_sel.+")) is not None
|
|
|
|
|
|
|
|
|
|
if is_paginated and not self._page_type == IliasElementType.VIDEO_FOLDER:
|
|
|
|
|
# We are in stage 2 - try to break pagination
|
|
|
|
|
return self._find_video_entries_paginated()
|
|
|
|
|
|
|
|
|
|
return self._find_video_entries_no_paging()
|
|
|
|
|
|
|
|
|
|
def _find_video_entries_paginated(self) -> List[IliasPageElement]:
|
|
|
|
|
table_element: Tag = self._soup.find(name="table", id=re.compile(r"tbl_xoct_.+"))
|
|
|
|
|
|
|
|
|
|
if table_element is None:
|
2021-05-23 18:12:51 +02:00
|
|
|
log.warn("Couldn't increase elements per page (table not found). I might miss elements.")
|
2021-05-19 21:34:36 +02:00
|
|
|
return self._find_video_entries_no_paging()
|
|
|
|
|
|
|
|
|
|
id_match = re.match(r"tbl_xoct_(.+)", table_element.attrs["id"])
|
|
|
|
|
if id_match is None:
|
2021-05-23 18:12:51 +02:00
|
|
|
log.warn("Couldn't increase elements per page (table id not found). I might miss elements.")
|
2021-05-19 21:34:36 +02:00
|
|
|
return self._find_video_entries_no_paging()
|
|
|
|
|
|
|
|
|
|
table_id = id_match.group(1)
|
|
|
|
|
|
|
|
|
|
query_params = {f"tbl_xoct_{table_id}_trows": "800",
|
|
|
|
|
"cmd": "asyncGetTableGUI", "cmdMode": "asynch"}
|
|
|
|
|
url = url_set_query_params(self._page_url, query_params)
|
2021-05-23 18:12:51 +02:00
|
|
|
|
|
|
|
|
log.explain("Disabled pagination, retrying folder as a new entry")
|
2021-05-19 21:34:36 +02:00
|
|
|
return [IliasPageElement(IliasElementType.VIDEO_FOLDER, url, "")]
|
|
|
|
|
|
|
|
|
|
def _find_video_entries_no_paging(self) -> List[IliasPageElement]:
|
|
|
|
|
"""
|
|
|
|
|
Crawls the "second stage" video page. This page contains the actual video urls.
|
|
|
|
|
"""
|
|
|
|
|
# Video start links are marked with an "Abspielen" link
|
|
|
|
|
video_links: List[Tag] = self._soup.findAll(
|
2022-11-25 11:25:22 +01:00
|
|
|
name="a", text=re.compile(r"\s*(Abspielen|Play)\s*")
|
2021-05-19 21:34:36 +02:00
|
|
|
)
|
|
|
|
|
|
|
|
|
|
results: List[IliasPageElement] = []
|
|
|
|
|
|
|
|
|
|
for link in video_links:
|
|
|
|
|
results.append(self._listed_video_to_element(link))
|
|
|
|
|
|
|
|
|
|
return results
|
|
|
|
|
|
|
|
|
|
def _listed_video_to_element(self, link: Tag) -> IliasPageElement:
|
|
|
|
|
# The link is part of a table with multiple columns, describing metadata.
|
2022-01-18 22:32:43 +01:00
|
|
|
# 6th or 7th child (1 indexed) is the modification time string. Try to find it
|
|
|
|
|
# by parsing backwards from the end and finding something that looks like a date
|
|
|
|
|
modification_time = None
|
|
|
|
|
row: Tag = link.parent.parent.parent
|
|
|
|
|
column_count = len(row.select("td.std"))
|
|
|
|
|
for index in range(column_count, 0, -1):
|
|
|
|
|
modification_string = link.parent.parent.parent.select_one(
|
|
|
|
|
f"td.std:nth-child({index})"
|
|
|
|
|
).getText().strip()
|
|
|
|
|
if re.search(r"\d+\.\d+.\d+ - \d+:\d+", modification_string):
|
|
|
|
|
modification_time = datetime.strptime(modification_string, "%d.%m.%Y - %H:%M")
|
|
|
|
|
break
|
|
|
|
|
|
|
|
|
|
if modification_time is None:
|
|
|
|
|
log.warn(f"Could not determine upload time for {link}")
|
|
|
|
|
modification_time = datetime.now()
|
2021-05-19 21:34:36 +02:00
|
|
|
|
|
|
|
|
title = link.parent.parent.parent.select_one("td.std:nth-child(3)").getText().strip()
|
|
|
|
|
title += ".mp4"
|
|
|
|
|
|
|
|
|
|
video_name: str = _sanitize_path_name(title)
|
|
|
|
|
|
|
|
|
|
video_url = self._abs_url_from_link(link)
|
|
|
|
|
|
2021-05-27 17:59:22 +02:00
|
|
|
log.explain(f"Found video {video_name!r} at {video_url}")
|
2021-05-19 21:34:36 +02:00
|
|
|
return IliasPageElement(IliasElementType.VIDEO_PLAYER, video_url, video_name, modification_time)
|
|
|
|
|
|
|
|
|
|
def _find_exercise_entries(self) -> List[IliasPageElement]:
|
2021-05-24 16:22:51 +02:00
|
|
|
if self._soup.find(id="tab_submission"):
|
|
|
|
|
log.explain("Found submission tab. This is an exercise detail page")
|
|
|
|
|
return self._find_exercise_entries_detail_page()
|
|
|
|
|
log.explain("Found no submission tab. This is an exercise root page")
|
|
|
|
|
return self._find_exercise_entries_root_page()
|
|
|
|
|
|
|
|
|
|
def _find_exercise_entries_detail_page(self) -> List[IliasPageElement]:
|
|
|
|
|
results: List[IliasPageElement] = []
|
|
|
|
|
|
|
|
|
|
# Find all download links in the container (this will contain all the files)
|
|
|
|
|
download_links: List[Tag] = self._soup.findAll(
|
|
|
|
|
name="a",
|
|
|
|
|
# download links contain the given command class
|
|
|
|
|
attrs={"href": lambda x: x and "cmd=download" in x},
|
|
|
|
|
text="Download"
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
for link in download_links:
|
|
|
|
|
parent_row: Tag = link.findParent("tr")
|
|
|
|
|
children: List[Tag] = parent_row.findChildren("td")
|
|
|
|
|
|
|
|
|
|
name = _sanitize_path_name(children[1].getText().strip())
|
|
|
|
|
log.explain(f"Found exercise detail entry {name!r}")
|
2021-05-31 18:00:42 +02:00
|
|
|
|
|
|
|
|
for child in reversed(children):
|
|
|
|
|
date = demangle_date(child.getText().strip(), fail_silently=True)
|
|
|
|
|
if date is not None:
|
|
|
|
|
break
|
|
|
|
|
if date is None:
|
|
|
|
|
log.warn(f"Date parsing failed for exercise entry {name!r}")
|
|
|
|
|
|
2021-05-24 16:22:51 +02:00
|
|
|
results.append(IliasPageElement(
|
|
|
|
|
IliasElementType.FILE,
|
|
|
|
|
self._abs_url_from_link(link),
|
|
|
|
|
name,
|
|
|
|
|
date
|
|
|
|
|
))
|
|
|
|
|
|
|
|
|
|
return results
|
|
|
|
|
|
|
|
|
|
def _find_exercise_entries_root_page(self) -> List[IliasPageElement]:
|
2021-05-19 21:34:36 +02:00
|
|
|
results: List[IliasPageElement] = []
|
|
|
|
|
|
|
|
|
|
# Each assignment is in an accordion container
|
|
|
|
|
assignment_containers: List[Tag] = self._soup.select(".il_VAccordionInnerContainer")
|
|
|
|
|
|
|
|
|
|
for container in assignment_containers:
|
|
|
|
|
# Fetch the container name out of the header to use it in the path
|
|
|
|
|
container_name = container.select_one(".ilAssignmentHeader").getText().strip()
|
2021-05-24 16:22:51 +02:00
|
|
|
log.explain(f"Found exercise container {container_name!r}")
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
# Find all download links in the container (this will contain all the files)
|
|
|
|
|
files: List[Tag] = container.findAll(
|
|
|
|
|
name="a",
|
|
|
|
|
# download links contain the given command class
|
|
|
|
|
attrs={"href": lambda x: x and "cmdClass=ilexsubmissiongui" in x},
|
|
|
|
|
text="Download"
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# Grab each file as you now have the link
|
|
|
|
|
for file_link in files:
|
|
|
|
|
# Two divs, side by side. Left is the name, right is the link ==> get left
|
|
|
|
|
# sibling
|
|
|
|
|
file_name = file_link.parent.findPrevious(name="div").getText().strip()
|
|
|
|
|
file_name = _sanitize_path_name(file_name)
|
|
|
|
|
url = self._abs_url_from_link(file_link)
|
|
|
|
|
|
2021-05-23 18:12:51 +02:00
|
|
|
log.explain(f"Found exercise entry {file_name!r}")
|
2021-05-19 21:34:36 +02:00
|
|
|
results.append(IliasPageElement(
|
|
|
|
|
IliasElementType.FILE,
|
|
|
|
|
url,
|
|
|
|
|
container_name + "/" + file_name,
|
|
|
|
|
None # We do not have any timestamp
|
|
|
|
|
))
|
|
|
|
|
|
2021-05-24 16:22:51 +02:00
|
|
|
# Find all links to file listings (e.g. "Submitted Files" for groups)
|
|
|
|
|
file_listings: List[Tag] = container.findAll(
|
|
|
|
|
name="a",
|
|
|
|
|
# download links contain the given command class
|
|
|
|
|
attrs={"href": lambda x: x and "cmdClass=ilexsubmissionfilegui" in x}
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# Add each listing as a new
|
|
|
|
|
for listing in file_listings:
|
2021-06-04 19:23:33 +02:00
|
|
|
parent_container: Tag = listing.findParent(
|
|
|
|
|
"div", attrs={"class": lambda x: x and "form-group" in x}
|
|
|
|
|
)
|
|
|
|
|
label_container: Tag = parent_container.find(
|
|
|
|
|
attrs={"class": lambda x: x and "control-label" in x}
|
|
|
|
|
)
|
|
|
|
|
file_name = _sanitize_path_name(label_container.getText().strip())
|
2021-05-24 16:22:51 +02:00
|
|
|
url = self._abs_url_from_link(listing)
|
|
|
|
|
log.explain(f"Found exercise detail {file_name!r} at {url}")
|
|
|
|
|
results.append(IliasPageElement(
|
|
|
|
|
IliasElementType.EXERCISE_FILES,
|
|
|
|
|
url,
|
|
|
|
|
container_name + "/" + file_name,
|
|
|
|
|
None # we do not have any timestamp
|
|
|
|
|
))
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
return results
|
|
|
|
|
|
|
|
|
|
def _find_normal_entries(self) -> List[IliasPageElement]:
|
|
|
|
|
result: List[IliasPageElement] = []
|
|
|
|
|
|
|
|
|
|
# Fetch all links and throw them to the general interpreter
|
|
|
|
|
links: List[Tag] = self._soup.select("a.il_ContainerItemTitle")
|
|
|
|
|
|
|
|
|
|
for link in links:
|
|
|
|
|
abs_url = self._abs_url_from_link(link)
|
2021-05-24 18:53:00 +02:00
|
|
|
parents = self._find_upwards_folder_hierarchy(link)
|
|
|
|
|
|
|
|
|
|
if parents:
|
|
|
|
|
element_name = "/".join(parents) + "/" + _sanitize_path_name(link.getText())
|
|
|
|
|
else:
|
|
|
|
|
element_name = _sanitize_path_name(link.getText())
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
element_type = self._find_type_from_link(element_name, link, abs_url)
|
|
|
|
|
description = self._find_link_description(link)
|
|
|
|
|
|
2022-05-05 22:53:37 +02:00
|
|
|
# The last meeting on every page is expanded by default.
|
|
|
|
|
# Its content is then shown inline *and* in the meeting page itself.
|
|
|
|
|
# We should skip the inline content.
|
|
|
|
|
if element_type != IliasElementType.MEETING and self._is_in_expanded_meeting(link):
|
|
|
|
|
continue
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
if not element_type:
|
|
|
|
|
continue
|
|
|
|
|
if element_type == IliasElementType.MEETING:
|
2021-05-23 18:12:51 +02:00
|
|
|
normalized = _sanitize_path_name(self._normalize_meeting_name(element_name))
|
|
|
|
|
log.explain(f"Normalized meeting name from {element_name!r} to {normalized!r}")
|
|
|
|
|
element_name = normalized
|
2021-05-19 21:34:36 +02:00
|
|
|
elif element_type == IliasElementType.FILE:
|
|
|
|
|
result.append(self._file_to_element(element_name, abs_url, link))
|
|
|
|
|
continue
|
|
|
|
|
|
2021-05-23 18:12:51 +02:00
|
|
|
log.explain(f"Found {element_name!r}")
|
2021-05-19 21:34:36 +02:00
|
|
|
result.append(IliasPageElement(element_type, abs_url, element_name, description=description))
|
|
|
|
|
|
2021-10-25 11:07:25 +02:00
|
|
|
result += self._find_cards()
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
return result
|
|
|
|
|
|
2022-05-05 22:53:37 +02:00
|
|
|
def _is_in_expanded_meeting(self, tag: Tag) -> bool:
|
|
|
|
|
"""
|
|
|
|
|
Returns whether a file is part of an expanded meeting.
|
|
|
|
|
Has false positives for meetings themselves as their title is also "in the expanded meeting content".
|
|
|
|
|
It is in the same general div and this whole thing is guesswork.
|
|
|
|
|
Therefore, you should check for meetings before passing them in this function.
|
|
|
|
|
"""
|
|
|
|
|
parents: List[Tag] = list(tag.parents)
|
|
|
|
|
for parent in parents:
|
|
|
|
|
if not parent.get("class"):
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
# We should not crawl files under meetings
|
|
|
|
|
if "ilContainerListItemContentCB" in parent.get("class"):
|
|
|
|
|
link: Tag = parent.parent.find("a")
|
|
|
|
|
type = IliasPage._find_type_from_folder_like(link, self._page_url)
|
|
|
|
|
return type == IliasElementType.MEETING
|
|
|
|
|
|
|
|
|
|
return False
|
|
|
|
|
|
2021-05-24 18:53:00 +02:00
|
|
|
def _find_upwards_folder_hierarchy(self, tag: Tag) -> List[str]:
|
|
|
|
|
"""
|
|
|
|
|
Interprets accordions and expandable blocks as virtual folders and returns them
|
|
|
|
|
in order. This allows us to find a file named "Test" in an accordion "Acc" as "Acc/Test"
|
|
|
|
|
"""
|
|
|
|
|
found_titles = []
|
|
|
|
|
|
|
|
|
|
outer_accordion_content: Optional[Tag] = None
|
|
|
|
|
|
|
|
|
|
parents: List[Tag] = list(tag.parents)
|
|
|
|
|
for parent in parents:
|
|
|
|
|
if not parent.get("class"):
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
# ILIAS has proper accordions and weird blocks that look like normal headings,
|
|
|
|
|
# but some JS later transforms them into an accordion.
|
|
|
|
|
|
|
|
|
|
# This is for these weird JS-y blocks
|
|
|
|
|
if "ilContainerItemsContainer" in parent.get("class"):
|
|
|
|
|
# I am currently under the impression that *only* those JS blocks have an
|
|
|
|
|
# ilNoDisplay class.
|
|
|
|
|
if "ilNoDisplay" not in parent.get("class"):
|
|
|
|
|
continue
|
|
|
|
|
prev: Tag = parent.findPreviousSibling("div")
|
|
|
|
|
if "ilContainerBlockHeader" in prev.get("class"):
|
2022-01-08 16:58:30 +01:00
|
|
|
if prev.find("h3"):
|
|
|
|
|
found_titles.append(prev.find("h3").getText().strip())
|
|
|
|
|
else:
|
|
|
|
|
found_titles.append(prev.find("h2").getText().strip())
|
2021-05-24 18:53:00 +02:00
|
|
|
|
|
|
|
|
# And this for real accordions
|
|
|
|
|
if "il_VAccordionContentDef" in parent.get("class"):
|
|
|
|
|
outer_accordion_content = parent
|
|
|
|
|
break
|
|
|
|
|
|
|
|
|
|
if outer_accordion_content:
|
|
|
|
|
accordion_tag: Tag = outer_accordion_content.parent
|
|
|
|
|
head_tag: Tag = accordion_tag.find(attrs={
|
|
|
|
|
"class": lambda x: x and "ilc_va_ihead_VAccordIHead" in x
|
|
|
|
|
})
|
|
|
|
|
found_titles.append(head_tag.getText().strip())
|
|
|
|
|
|
|
|
|
|
return [_sanitize_path_name(x) for x in reversed(found_titles)]
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
def _find_link_description(self, link: Tag) -> Optional[str]:
|
|
|
|
|
tile: Tag = link.findParent("div", {"class": lambda x: x and "il_ContainerListItem" in x})
|
|
|
|
|
if not tile:
|
|
|
|
|
return None
|
|
|
|
|
description_element: Tag = tile.find("div", {"class": lambda x: x and "il_Description" in x})
|
|
|
|
|
if not description_element:
|
|
|
|
|
return None
|
|
|
|
|
return description_element.getText().strip()
|
|
|
|
|
|
|
|
|
|
def _file_to_element(self, name: str, url: str, link_element: Tag) -> IliasPageElement:
|
|
|
|
|
# Files have a list of properties (type, modification date, size, etc.)
|
|
|
|
|
# In a series of divs.
|
|
|
|
|
# Find the parent containing all those divs, so we can filter our what we need
|
|
|
|
|
properties_parent: Tag = link_element.findParent(
|
|
|
|
|
"div", {"class": lambda x: "il_ContainerListItem" in x}
|
|
|
|
|
).select_one(".il_ItemProperties")
|
|
|
|
|
# The first one is always the filetype
|
|
|
|
|
file_type = properties_parent.select_one("span.il_ItemProperty").getText().strip()
|
|
|
|
|
|
|
|
|
|
# The rest does not have a stable order. Grab the whole text and reg-ex the date
|
|
|
|
|
# out of it
|
|
|
|
|
all_properties_text = properties_parent.getText().strip()
|
|
|
|
|
modification_date_match = re.search(
|
|
|
|
|
r"(((\d+\. \w+ \d+)|(Gestern|Yesterday)|(Heute|Today)|(Morgen|Tomorrow)), \d+:\d+)",
|
|
|
|
|
all_properties_text
|
|
|
|
|
)
|
|
|
|
|
if modification_date_match is None:
|
|
|
|
|
modification_date = None
|
2021-05-25 15:54:01 +02:00
|
|
|
log.explain(f"Element {name} at {url} has no date.")
|
2021-05-19 21:34:36 +02:00
|
|
|
else:
|
|
|
|
|
modification_date_str = modification_date_match.group(1)
|
|
|
|
|
modification_date = demangle_date(modification_date_str)
|
|
|
|
|
|
|
|
|
|
# Grab the name from the link text
|
|
|
|
|
full_path = name + "." + file_type
|
|
|
|
|
|
2021-05-23 18:12:51 +02:00
|
|
|
log.explain(f"Found file {full_path!r}")
|
2021-05-19 21:34:36 +02:00
|
|
|
return IliasPageElement(IliasElementType.FILE, url, full_path, modification_date)
|
|
|
|
|
|
2021-10-25 11:07:25 +02:00
|
|
|
def _find_cards(self) -> List[IliasPageElement]:
|
|
|
|
|
result: List[IliasPageElement] = []
|
|
|
|
|
|
|
|
|
|
card_titles: List[Tag] = self._soup.select(".card-title a")
|
|
|
|
|
|
|
|
|
|
for title in card_titles:
|
|
|
|
|
url = self._abs_url_from_link(title)
|
|
|
|
|
name = _sanitize_path_name(title.getText().strip())
|
|
|
|
|
type = self._find_type_from_card(title)
|
|
|
|
|
|
|
|
|
|
if not type:
|
|
|
|
|
_unexpected_html_warning()
|
|
|
|
|
log.warn_contd(f"Could not extract type for {title}")
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
result.append(IliasPageElement(type, url, name))
|
|
|
|
|
|
|
|
|
|
card_button_tiles: List[Tag] = self._soup.select(".card-title button")
|
|
|
|
|
|
|
|
|
|
for button in card_button_tiles:
|
|
|
|
|
regex = re.compile(button["id"] + r".*window.open\(['\"](.+?)['\"]")
|
|
|
|
|
res = regex.search(str(self._soup))
|
|
|
|
|
if not res:
|
|
|
|
|
_unexpected_html_warning()
|
|
|
|
|
log.warn_contd(f"Could not find click handler target for {button}")
|
|
|
|
|
continue
|
|
|
|
|
url = self._abs_url_from_relative(res.group(1))
|
|
|
|
|
name = _sanitize_path_name(button.getText().strip())
|
|
|
|
|
type = self._find_type_from_card(button)
|
|
|
|
|
caption_parent = button.findParent(
|
|
|
|
|
"div",
|
|
|
|
|
attrs={"class": lambda x: x and "caption" in x},
|
|
|
|
|
)
|
|
|
|
|
description = caption_parent.find_next_sibling("div").getText().strip()
|
|
|
|
|
|
|
|
|
|
if not type:
|
|
|
|
|
_unexpected_html_warning()
|
|
|
|
|
log.warn_contd(f"Could not extract type for {button}")
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
result.append(IliasPageElement(type, url, name, description=description))
|
|
|
|
|
|
|
|
|
|
return result
|
|
|
|
|
|
|
|
|
|
def _find_type_from_card(self, card_title: Tag) -> Optional[IliasElementType]:
|
|
|
|
|
def is_card_root(element: Tag) -> bool:
|
|
|
|
|
return "il-card" in element["class"] and "thumbnail" in element["class"]
|
|
|
|
|
|
|
|
|
|
card_root: Optional[Tag] = None
|
|
|
|
|
|
|
|
|
|
# We look for the card root
|
|
|
|
|
for parent in card_title.parents:
|
|
|
|
|
if is_card_root(parent):
|
|
|
|
|
card_root = parent
|
|
|
|
|
break
|
|
|
|
|
|
|
|
|
|
if card_root is None:
|
|
|
|
|
_unexpected_html_warning()
|
|
|
|
|
log.warn_contd(f"Tried to figure out element type, but did not find an icon for {card_title}")
|
|
|
|
|
return None
|
|
|
|
|
|
|
|
|
|
icon: Tag = card_root.select_one(".il-card-repository-head .icon")
|
|
|
|
|
|
|
|
|
|
if "opencast" in icon["class"]:
|
|
|
|
|
return IliasElementType.VIDEO_FOLDER_MAYBE_PAGINATED
|
|
|
|
|
if "exc" in icon["class"]:
|
|
|
|
|
return IliasElementType.EXERCISE
|
|
|
|
|
if "webr" in icon["class"]:
|
|
|
|
|
return IliasElementType.LINK
|
|
|
|
|
if "book" in icon["class"]:
|
|
|
|
|
return IliasElementType.BOOKING
|
|
|
|
|
if "frm" in icon["class"]:
|
|
|
|
|
return IliasElementType.FORUM
|
|
|
|
|
if "sess" in icon["class"]:
|
|
|
|
|
return IliasElementType.MEETING
|
|
|
|
|
if "tst" in icon["class"]:
|
|
|
|
|
return IliasElementType.TEST
|
|
|
|
|
if "fold" in icon["class"]:
|
|
|
|
|
return IliasElementType.FOLDER
|
2022-10-24 18:36:54 +02:00
|
|
|
if "copa" in icon["class"]:
|
|
|
|
|
return IliasElementType.FOLDER
|
2022-10-24 18:36:34 +02:00
|
|
|
if "svy" in icon["class"]:
|
|
|
|
|
return IliasElementType.SURVEY
|
2021-10-25 11:07:25 +02:00
|
|
|
|
|
|
|
|
_unexpected_html_warning()
|
|
|
|
|
log.warn_contd(f"Could not extract type from {icon} for card title {card_title}")
|
|
|
|
|
return None
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
@staticmethod
|
|
|
|
|
def _find_type_from_link(
|
|
|
|
|
element_name: str,
|
|
|
|
|
link_element: Tag,
|
|
|
|
|
url: str
|
|
|
|
|
) -> Optional[IliasElementType]:
|
|
|
|
|
"""
|
|
|
|
|
Decides which sub crawler to use for a given top level element.
|
|
|
|
|
"""
|
|
|
|
|
parsed_url = urlparse(url)
|
|
|
|
|
|
|
|
|
|
# file URLs contain "target=file"
|
|
|
|
|
if "target=file_" in parsed_url.query:
|
|
|
|
|
return IliasElementType.FILE
|
|
|
|
|
|
2022-01-08 16:58:15 +01:00
|
|
|
if "target=grp_" in parsed_url.query:
|
|
|
|
|
return IliasElementType.FOLDER
|
|
|
|
|
|
|
|
|
|
if "target=crs_" in parsed_url.query:
|
|
|
|
|
return IliasElementType.FOLDER
|
|
|
|
|
|
|
|
|
|
if "baseClass=ilExerciseHandlerGUI" in parsed_url.query:
|
|
|
|
|
return IliasElementType.EXERCISE
|
|
|
|
|
|
|
|
|
|
if "baseClass=ilLinkResourceHandlerGUI" in parsed_url.query and "calldirectlink" in parsed_url.query:
|
|
|
|
|
return IliasElementType.LINK
|
|
|
|
|
|
|
|
|
|
if "cmd=showThreads" in parsed_url.query or "target=frm_" in parsed_url.query:
|
|
|
|
|
return IliasElementType.FORUM
|
|
|
|
|
|
|
|
|
|
if "cmdClass=ilobjtestgui" in parsed_url.query:
|
|
|
|
|
return IliasElementType.TEST
|
|
|
|
|
|
|
|
|
|
# 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.
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
# Everything with a ref_id can *probably* be opened to reveal nested things
|
|
|
|
|
# video groups, directories, exercises, etc
|
2022-01-08 16:58:15 +01:00
|
|
|
if "ref_id=" in parsed_url.query or "goto.php" in parsed_url.path:
|
2021-05-19 21:34:36 +02:00
|
|
|
return IliasPage._find_type_from_folder_like(link_element, url)
|
|
|
|
|
|
2021-05-23 18:12:51 +02:00
|
|
|
_unexpected_html_warning()
|
|
|
|
|
log.warn_contd(
|
2021-05-27 17:59:22 +02:00
|
|
|
f"Tried to figure out element type, but failed for {element_name!r} / {link_element!r})"
|
2021-05-23 18:12:51 +02:00
|
|
|
)
|
2021-05-19 21:34:36 +02:00
|
|
|
return None
|
|
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
|
def _find_type_from_folder_like(link_element: Tag, url: str) -> Optional[IliasElementType]:
|
|
|
|
|
"""
|
|
|
|
|
Try crawling something that looks like a folder.
|
|
|
|
|
"""
|
|
|
|
|
# pylint: disable=too-many-return-statements
|
|
|
|
|
|
|
|
|
|
found_parent: Optional[Tag] = None
|
|
|
|
|
|
|
|
|
|
# We look for the outer div of our inner link, to find information around it
|
|
|
|
|
# (mostly the icon)
|
|
|
|
|
for parent in link_element.parents:
|
2022-01-08 16:58:15 +01:00
|
|
|
if "ilContainerListItemOuter" in parent["class"] or "il-std-item" in parent["class"]:
|
2021-05-19 21:34:36 +02:00
|
|
|
found_parent = parent
|
|
|
|
|
break
|
|
|
|
|
|
|
|
|
|
if found_parent is None:
|
2021-05-23 18:12:51 +02:00
|
|
|
_unexpected_html_warning()
|
2021-05-24 16:22:51 +02:00
|
|
|
log.warn_contd(f"Tried to figure out element type, but did not find an icon for {url}")
|
2021-05-19 21:34:36 +02:00
|
|
|
return None
|
|
|
|
|
|
|
|
|
|
# Find the small descriptive icon to figure out the type
|
|
|
|
|
img_tag: Optional[Tag] = found_parent.select_one("img.ilListItemIcon")
|
|
|
|
|
|
2022-01-08 16:58:15 +01:00
|
|
|
if img_tag is None:
|
|
|
|
|
img_tag = found_parent.select_one("img.icon")
|
|
|
|
|
|
2022-10-24 14:33:58 +02:00
|
|
|
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
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
if img_tag is None:
|
2021-05-23 18:12:51 +02:00
|
|
|
_unexpected_html_warning()
|
2021-05-24 16:22:51 +02:00
|
|
|
log.warn_contd(f"Tried to figure out element type, but did not find an image for {url}")
|
2021-05-19 21:34:36 +02:00
|
|
|
return None
|
|
|
|
|
|
|
|
|
|
if "opencast" in str(img_tag["alt"]).lower():
|
2021-06-13 15:39:22 +02:00
|
|
|
return IliasElementType.VIDEO_FOLDER_MAYBE_PAGINATED
|
2021-05-19 21:34:36 +02:00
|
|
|
|
|
|
|
|
if str(img_tag["src"]).endswith("icon_exc.svg"):
|
|
|
|
|
return IliasElementType.EXERCISE
|
|
|
|
|
|
|
|
|
|
if str(img_tag["src"]).endswith("icon_webr.svg"):
|
|
|
|
|
return IliasElementType.LINK
|
|
|
|
|
|
2021-07-06 16:13:23 +02:00
|
|
|
if str(img_tag["src"]).endswith("icon_book.svg"):
|
|
|
|
|
return IliasElementType.BOOKING
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
if str(img_tag["src"]).endswith("frm.svg"):
|
|
|
|
|
return IliasElementType.FORUM
|
|
|
|
|
|
|
|
|
|
if str(img_tag["src"]).endswith("sess.svg"):
|
|
|
|
|
return IliasElementType.MEETING
|
|
|
|
|
|
2021-05-24 16:32:29 +02:00
|
|
|
if str(img_tag["src"]).endswith("icon_tst.svg"):
|
|
|
|
|
return IliasElementType.TEST
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
return IliasElementType.FOLDER
|
|
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
|
def _normalize_meeting_name(meeting_name: str) -> str:
|
|
|
|
|
"""
|
|
|
|
|
Normalizes meeting names, which have a relative time as their first part,
|
|
|
|
|
to their date in ISO format.
|
|
|
|
|
"""
|
2022-05-08 23:21:18 +02:00
|
|
|
|
|
|
|
|
# This checks whether we can reach a `:` without passing a `-`
|
|
|
|
|
if re.search(r"^[^-]+: ", meeting_name):
|
|
|
|
|
# Meeting name only contains date: "05. Jan 2000:"
|
|
|
|
|
split_delimiter = ":"
|
|
|
|
|
else:
|
|
|
|
|
# Meeting name contains date and start/end times: "05. Jan 2000, 16:00 - 17:30:"
|
|
|
|
|
split_delimiter = ", "
|
|
|
|
|
|
|
|
|
|
# We have a meeting day without time
|
|
|
|
|
date_portion_str = meeting_name.split(split_delimiter)[0]
|
2021-05-19 21:34:36 +02:00
|
|
|
date_portion = demangle_date(date_portion_str)
|
|
|
|
|
|
2022-05-08 23:21:18 +02:00
|
|
|
# We failed to parse the date, bail out
|
2021-05-19 21:34:36 +02:00
|
|
|
if not date_portion:
|
|
|
|
|
return meeting_name
|
|
|
|
|
|
2022-05-08 23:21:18 +02:00
|
|
|
# Replace the first section with the absolute date
|
|
|
|
|
rest_of_name = split_delimiter.join(meeting_name.split(split_delimiter)[1:])
|
|
|
|
|
return datetime.strftime(date_portion, "%Y-%m-%d") + split_delimiter + rest_of_name
|
2021-05-19 21:34:36 +02:00
|
|
|
|
|
|
|
|
def _abs_url_from_link(self, link_tag: Tag) -> str:
|
|
|
|
|
"""
|
|
|
|
|
Create an absolute url from an <a> tag.
|
|
|
|
|
"""
|
2021-10-25 11:07:25 +02:00
|
|
|
return self._abs_url_from_relative(link_tag.get("href"))
|
|
|
|
|
|
|
|
|
|
def _abs_url_from_relative(self, relative_url: str) -> str:
|
|
|
|
|
"""
|
|
|
|
|
Create an absolute url from a relative URL.
|
|
|
|
|
"""
|
|
|
|
|
return urljoin(self._page_url, relative_url)
|
2021-05-19 21:34:36 +02:00
|
|
|
|
|
|
|
|
|
2021-05-23 18:12:51 +02:00
|
|
|
def _unexpected_html_warning() -> None:
|
|
|
|
|
log.warn("Encountered unexpected HTML structure, ignoring element.")
|
|
|
|
|
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
german_months = ['Jan', 'Feb', 'Mär', 'Apr', 'Mai', 'Jun', 'Jul', 'Aug', 'Sep', 'Okt', 'Nov', 'Dez']
|
|
|
|
|
english_months = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']
|
|
|
|
|
|
|
|
|
|
|
2021-05-31 18:00:42 +02:00
|
|
|
def demangle_date(date_str: str, fail_silently: bool = False) -> Optional[datetime]:
|
2021-05-19 21:34:36 +02:00
|
|
|
"""
|
2022-05-08 23:21:18 +02:00
|
|
|
Demangle a given date in one of the following formats (hour/minute part is optional):
|
2021-05-19 21:34:36 +02:00
|
|
|
"Gestern, HH:MM"
|
|
|
|
|
"Heute, HH:MM"
|
|
|
|
|
"Morgen, HH:MM"
|
|
|
|
|
"dd. mon yyyy, HH:MM
|
|
|
|
|
"""
|
|
|
|
|
try:
|
2022-05-08 23:21:18 +02:00
|
|
|
# Normalize whitespace because users
|
2021-05-19 21:34:36 +02:00
|
|
|
date_str = re.sub(r"\s+", " ", date_str)
|
2022-05-05 22:28:30 +02:00
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
date_str = re.sub("Gestern|Yesterday", _format_date_english(_yesterday()), date_str, re.I)
|
|
|
|
|
date_str = re.sub("Heute|Today", _format_date_english(date.today()), date_str, re.I)
|
|
|
|
|
date_str = re.sub("Morgen|Tomorrow", _format_date_english(_tomorrow()), date_str, re.I)
|
2022-05-05 22:28:30 +02:00
|
|
|
date_str = date_str.strip()
|
2021-05-19 21:34:36 +02:00
|
|
|
for german, english in zip(german_months, english_months):
|
|
|
|
|
date_str = date_str.replace(german, english)
|
|
|
|
|
# Remove trailing dots for abbreviations, e.g. "20. Apr. 2020" -> "20. Apr 2020"
|
|
|
|
|
date_str = date_str.replace(english + ".", english)
|
|
|
|
|
|
2022-05-08 23:21:18 +02:00
|
|
|
# We now have a nice english String in the format: "dd. mmm yyyy, hh:mm" or "dd. mmm yyyy"
|
|
|
|
|
|
|
|
|
|
# Check if we have a time as well
|
|
|
|
|
if ", " in date_str:
|
|
|
|
|
day_part, time_part = date_str.split(",")
|
|
|
|
|
else:
|
|
|
|
|
day_part = date_str.split(",")[0]
|
|
|
|
|
time_part = None
|
|
|
|
|
|
2021-05-19 21:34:36 +02:00
|
|
|
day_str, month_str, year_str = day_part.split(" ")
|
|
|
|
|
|
|
|
|
|
day = int(day_str.strip().replace(".", ""))
|
|
|
|
|
month = english_months.index(month_str.strip()) + 1
|
|
|
|
|
year = int(year_str.strip())
|
|
|
|
|
|
2022-05-08 23:21:18 +02:00
|
|
|
if time_part:
|
|
|
|
|
hour_str, minute_str = time_part.split(":")
|
|
|
|
|
hour = int(hour_str)
|
|
|
|
|
minute = int(minute_str)
|
|
|
|
|
return datetime(year, month, day, hour, minute)
|
2021-05-19 21:34:36 +02:00
|
|
|
|
2022-05-08 23:21:18 +02:00
|
|
|
return datetime(year, month, day)
|
2021-05-19 21:34:36 +02:00
|
|
|
except Exception:
|
2021-05-31 18:00:42 +02:00
|
|
|
if not fail_silently:
|
|
|
|
|
log.warn(f"Date parsing failed for {date_str!r}")
|
2021-05-19 21:34:36 +02:00
|
|
|
return None
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _format_date_english(date_to_format: date) -> str:
|
|
|
|
|
month = english_months[date_to_format.month - 1]
|
|
|
|
|
return f"{date_to_format.day:02d}. {month} {date_to_format.year:04d}"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _yesterday() -> date:
|
|
|
|
|
return date.today() - timedelta(days=1)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _tomorrow() -> date:
|
|
|
|
|
return date.today() + timedelta(days=1)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _sanitize_path_name(name: str) -> str:
|
|
|
|
|
return name.replace("/", "-").replace("\\", "-").strip()
|
2022-05-24 23:28:09 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
def parse_ilias_forum_export(forum_export: BeautifulSoup) -> List[IliasForumThread]:
|
|
|
|
|
elements = []
|
|
|
|
|
for p in forum_export.select("body > p"):
|
|
|
|
|
title_tag = p
|
|
|
|
|
content_tag = p.find_next_sibling("ul")
|
2022-10-19 22:59:33 +02:00
|
|
|
|
|
|
|
|
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
|
|
|
|
|
|
2022-05-24 23:28:09 +02:00
|
|
|
title = p.find("b").text
|
|
|
|
|
if ":" in title:
|
|
|
|
|
title = title[title.find(":") + 1:]
|
|
|
|
|
title = title.strip()
|
|
|
|
|
mtime = _guess_timestamp_from_forum_post_content(content_tag)
|
|
|
|
|
elements.append(IliasForumThread(title, title_tag, content_tag, mtime))
|
|
|
|
|
|
|
|
|
|
return elements
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _guess_timestamp_from_forum_post_content(content: Tag) -> Optional[datetime]:
|
|
|
|
|
posts: Optional[Tag] = content.select(".ilFrmPostHeader > span.small")
|
|
|
|
|
if not posts:
|
|
|
|
|
return None
|
|
|
|
|
|
|
|
|
|
newest_date: Optional[datetime] = None
|
|
|
|
|
|
|
|
|
|
for post in posts:
|
|
|
|
|
text = post.text.strip()
|
|
|
|
|
text = text[text.rfind("|") + 1:]
|
|
|
|
|
date = demangle_date(text, fail_silently=True)
|
|
|
|
|
if not date:
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
if not newest_date or newest_date < date:
|
|
|
|
|
newest_date = date
|
|
|
|
|
|
|
|
|
|
return newest_date
|
