mirror of
https://github.com/Garmelon/PFERD.git
synced 2023-12-21 10:23:01 +01:00
Compare commits
4 Commits
Author | SHA1 | Date | |
---|---|---|---|
52852d11a6 | |||
f94629a7fa | |||
c8ee456d33 | |||
2752e98621 |
@ -23,21 +23,6 @@ logger = logging.getLogger(__name__)
|
||||
class ShibbolethAuthenticator:
|
||||
ILIAS_GOTO = "https://ilias.studium.kit.edu/goto.php"
|
||||
|
||||
ALLOWED_CONTENT_TYPES = [
|
||||
"application/pdf",
|
||||
"application/zip",
|
||||
"application/msword",
|
||||
"application/vnd.wolfram.nb",
|
||||
"application/octet-stream",
|
||||
"application/excel",
|
||||
"text/xml",
|
||||
"text/xml;charset=UTF-8",
|
||||
"text/plain",
|
||||
"text/plain;charset=UTF-8",
|
||||
"image/jpeg",
|
||||
"image/png",
|
||||
]
|
||||
|
||||
def __init__(self, cookie_file) -> None:
|
||||
# Because LWPCookieJar insists on the path being str-like instead of
|
||||
# Path-like.
|
||||
@ -152,11 +137,7 @@ class ShibbolethAuthenticator:
|
||||
with self._session.get(url, params=params, stream=True) as r:
|
||||
content_type = r.headers["content-type"]
|
||||
|
||||
if content_type in self.ALLOWED_CONTENT_TYPES:
|
||||
# Yay, we got the file :)
|
||||
stream_to_path(r, to_path)
|
||||
return True
|
||||
elif content_type == "text/html":
|
||||
if content_type.startswith("text/html"):
|
||||
# Dangit, we're probably not logged in.
|
||||
soup = bs4.BeautifulSoup(r.text, "html.parser")
|
||||
if self._is_logged_in(soup):
|
||||
@ -164,9 +145,9 @@ class ShibbolethAuthenticator:
|
||||
"Attempting to download a web page, not a file")
|
||||
return False
|
||||
else:
|
||||
# What *did* we get?
|
||||
raise ContentTypeException(
|
||||
f"Unknown file of type {content_type}")
|
||||
# Yay, we got the file :)
|
||||
stream_to_path(r, to_path)
|
||||
return True
|
||||
|
||||
def download_file(self, file_id, to_path):
|
||||
params = {"target": file_id}
|
||||
|
@ -4,6 +4,7 @@ import getpass
|
||||
import logging
|
||||
import pathlib
|
||||
import re
|
||||
from urllib.parse import urljoin
|
||||
|
||||
import bs4
|
||||
import requests
|
||||
@ -43,7 +44,7 @@ class Ti:
|
||||
if filter(path):
|
||||
self._crawl(urlpart + address, path, orga, transform)
|
||||
else:
|
||||
loggwe.info(f"Skipping {name}/")
|
||||
logger.info(f"Skipping {name}/")
|
||||
|
||||
orga.clean_sync_dir()
|
||||
orga.clean_temp_dir()
|
||||
@ -76,7 +77,7 @@ class Ti:
|
||||
|
||||
for filelink in soup.find_all("a", href=self.FILE_RE):
|
||||
filepath = path / filelink["href"]
|
||||
fileurl = url + "/" + filelink["href"]
|
||||
fileurl = urljoin(url, filelink["href"])
|
||||
|
||||
new_path = transform(filepath)
|
||||
if new_path is None:
|
||||
|
@ -10,7 +10,7 @@ test it though).
|
||||
To install PFERD or update your installation to the latest version, run this
|
||||
wherever you want to install/have installed PFERD:
|
||||
```
|
||||
$ pip install git+https://github.com/Garmelon/PFERD@v1.1.6
|
||||
$ pip install git+https://github.com/Garmelon/PFERD@v1.1.8
|
||||
```
|
||||
|
||||
The use of [venv](https://docs.python.org/3/library/venv.html) is recommended.
|
||||
@ -25,7 +25,7 @@ $ mkdir Vorlesungen
|
||||
$ cd Vorlesungen
|
||||
$ python3 -m venv .
|
||||
$ . bin/activate
|
||||
$ pip install git+https://github.com/Garmelon/PFERD@v1.1.6
|
||||
$ pip install git+https://github.com/Garmelon/PFERD@v1.1.8
|
||||
$ curl -O https://raw.githubusercontent.com/Garmelon/PFERD/master/example_config.py
|
||||
$ python3 example_config.py
|
||||
$ deactivate
|
||||
|
Reference in New Issue
Block a user