mirrors/pferd
1
0
Fork 0
mirror of https://github.com/Garmelon/PFERD.git synced 2023-12-21 10:23:01 +01:00
Code Issues Packages Projects Releases Wiki Activity

Add support for ILIAS learning modules

Browse Source
This commit is contained in:
I-Al-Istannen 2023-07-29 23:23:10 +02:00
parent 123a57beec
commit 68c398f1fe
5 changed files with 272 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
CHANGELOG.md
View File

@ -30,6 +30,7 @@ ambiguous situations.
### Added
- `no-delete-prompt-override` conflict resolution strategy
- support for ILIAS learning modules
## 3.4.3 - 2022-11-29

69
PFERD/crawl/ilias/file_templates.py
View File

@ -1,6 +1,10 @@
from enum import Enum
from typing import Optional
import bs4
from PFERD.utils import soupify
_link_template_plain = "{{link}}"
_link_template_fancy = """
<!DOCTYPE html>
@ -94,6 +98,71 @@ _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"

2
PFERD/crawl/ilias/ilias_html_cleaner.py
View File

@ -82,7 +82,7 @@ def clean(soup: BeautifulSoup) -> BeautifulSoup:
dummy.decompose()
if len(children) > 1:
continue
if type(children[0]) == Comment:
if isinstance(type(children[0]), Comment):
dummy.decompose()
for hrule_imposter in soup.find_all(class_="ilc_section_Separator"):

46
PFERD/crawl/ilias/kit_ilias_html.py
View File

@ -22,6 +22,7 @@ class IliasElementType(Enum):
FOLDER = "folder"
FORUM = "forum"
LINK = "link"
LEARNING_MODULE = "learning_module"
BOOKING = "booking"
MEETING = "meeting"
SURVEY = "survey"
@ -71,6 +72,14 @@ 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]):
@ -136,6 +145,34 @@ 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:
@ -222,6 +259,12 @@ 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
@ -812,6 +855,9 @@ 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.

160
PFERD/crawl/ilias/kit_ilias_web_crawler.py
View File

@ -1,8 +1,11 @@
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, Optional, Set, Union, cast
from typing import Any, Callable, Dict, List, Literal, Optional, Set, Union, cast
from urllib.parse import urljoin
import aiohttp
import yarl
@ -16,10 +19,10 @@ 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
from .file_templates import Links, learning_module_template
from .ilias_html_cleaner import clean, insert_base_markup
from .kit_ilias_html import (IliasElementType, IliasForumThread, IliasPage, IliasPageElement,
_sanitize_path_name, parse_ilias_forum_export)
from .kit_ilias_html import (IliasElementType, IliasForumThread, IliasLearningModulePage, IliasPage,
IliasPageElement, _sanitize_path_name, parse_ilias_forum_export)
TargetType = Union[str, int]
@ -394,6 +397,8 @@ 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)
elif element.type == IliasElementType.BOOKING:
@ -739,6 +744,135 @@ instance's greatest bottleneck.
sink.file.write(content.encode("utf-8"))
sink.done()
async def _handle_learning_module(
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:
@ -772,7 +906,7 @@ instance's greatest bottleneck.
self,
url: str,
data: dict[str, Union[str, List[str]]]
) -> BeautifulSoup:
) -> bytes:
auth_id = await self._current_auth_id()
form_data = aiohttp.FormData()
@ -792,6 +926,22 @@ 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)