mirrors/pferd
1
0
Fork 0
mirror of https://github.com/Garmelon/PFERD.git synced 2025-07-12 14:12:30 +02:00
Code Issues Packages Projects Releases Wiki Activity

Prettify forum thread exports

Browse Source 
Co-authored-by: Tim <me@scriptim.dev>
This commit is contained in:
I-Al-Istannen
2025-02-19 14:29:37 +01:00
parent be175f9347
commit 72cd0f77e2
3 changed files with 99 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
CHANGELOG.md
View File

@ -22,6 +22,9 @@ ambiguous situations.
## Unreleased
### Changed
- Added prettier CSS to forum threads
## Fixed
- File links in report on Windows
- TOTP authentication in KIT Shibboleth

89
PFERD/crawl/ilias/file_templates.py
View File

@ -126,6 +126,88 @@ _learning_module_template = """
</html>
"""
_forum_thread_template = """
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>ILIAS - Forum: {{name}}</title>
<style>
* {
box-sizing: border-box;
}
body {
font-family: 'Open Sans', Verdana, Arial, Helvetica, sans-serif;
padding: 8px;
}
ul, ol, p {
margin: 1.2em 0;
}
p {
margin-top: 8px;
margin-bottom: 8px;
}
a {
color: #00876c;
text-decoration: none;
cursor: pointer;
}
a:hover {
text-decoration: underline;
}
body > p:first-child > span:first-child {
font-size: 1.6em;
}
body > p:first-child > span:first-child ~ span.default {
display: inline-block;
font-size: 1.2em;
padding-bottom: 8px;
}
.ilFrmPostContent {
margin-top: 8px;
max-width: 64em;
}
.ilFrmPostContent > *:first-child {
margin-top: 0px;
}
.ilFrmPostTitle {
margin-top: 24px;
color: #00876c;
font-weight: bold;
}
#ilFrmPostList {
list-style: none;
padding-left: 0;
}
li.ilFrmPostRow {
padding: 3px 0 3px 3px;
margin-bottom: 24px;
border-left: 6px solid #dddddd;
}
.ilFrmPostRow > div {
display: flex;
}
.ilFrmPostImage img {
margin: 0 !important;
padding: 6px 9px 9px 6px;
}
.ilUserIcon {
width: 115px;
}
.small {
text-decoration: none;
font-size: 0.75rem;
color: #6f6f6f;
}
</style>
</head>
<body>
{{heading}}
{{content}}
</body>
</html>
""".strip() # noqa: E501 line too long
def learning_module_template(body: bs4.Tag, name: str, prev: Optional[str], next: Optional[str]) -> str:
# Seems to be comments, ignore those.
@ -164,6 +246,13 @@ def learning_module_template(body: bs4.Tag, name: str, prev: Optional[str], next
return _learning_module_template.replace("{{body}}", body_str).replace("{{name}}", name)
def forum_thread_template(name: str, heading: bs4.Tag, content: bs4.Tag) -> str:
return _forum_thread_template \
.replace("{{name}}", name) \
.replace("{{heading}}", cast(str, heading.prettify())) \
.replace("{{content}}", cast(str, content.prettify()))
class Links(Enum):
IGNORE = "ignore"
PLAINTEXT = "plaintext"

12
PFERD/crawl/ilias/ilias_web_crawler.py
View File

@ -19,7 +19,7 @@ from ...utils import fmt_path, soupify, url_set_query_param
from ..crawler import CrawlError, CrawlToken, CrawlWarning, DownloadToken, anoncritical
from ..http_crawler import HttpCrawler, HttpCrawlerSection
from .async_helper import _iorepeat
from .file_templates import Links, learning_module_template
from .file_templates import Links, forum_thread_template, learning_module_template
from .ilias_html_cleaner import clean, insert_base_markup
from .kit_ilias_html import (IliasElementType, IliasForumThread, IliasLearningModulePage, IliasPage,
IliasPageElement, _sanitize_path_name, parse_ilias_forum_export)
@ -786,10 +786,12 @@ instance's greatest bottleneck.
return
async with maybe_dl as (bar, sink):
content = "<!DOCTYPE html>\n"
content += cast(str, element.name_tag.prettify())
content += cast(str, await self.internalize_images(element.content_tag.prettify()))
sink.file.write(content.encode("utf-8"))
rendered = forum_thread_template(
element.name,
element.name_tag,
element.content_tag
)
sink.file.write(rendered.encode("utf-8"))
sink.done()
async def _handle_learning_module(