Compare commits

..

11 Commits

Author SHA1 Message Date
9a9018751e Bump version 2021-02-06 22:54:05 +01:00
83b75e8254 syncurl: Sanitize element name on windows if it is used as folder name
Otherwise the name of the course might not be a invalid file name.
2021-02-06 22:53:26 +01:00
35c3fa205d Fixed description of activating venv (#22)
Add 'source' to the venv activate command in the readme

`source` was picked over `.` to conform to the python recommendation
(https://docs.python.org/3/library/venv.html#module-venv).

This patch also adds the `egg-info` you get when building to the
gitignore.
2021-01-28 21:24:09 +01:00
0b606f02fa Bump version 2021-01-17 10:33:10 +01:00
fb78a6e98e Retry ILIAS downloads a few times and only fail that file 2021-01-06 13:08:10 +01:00
5de68a0400 Bump version 2020-12-30 17:20:30 +01:00
f0562049b6 Remove Python 3.9 method in crawler 2020-12-30 17:18:04 +01:00
0e1077bb50 Bump version 2020-12-30 14:50:49 +01:00
c978e9edf4 Resolve a few pylint warnings 2020-12-30 14:45:46 +01:00
2714ac6be6 Send CSRF token to Shibboleth 2020-12-30 14:34:11 +01:00
9b048a9cfc Canonize meeting names to a properly formatted date 2020-12-30 14:32:59 +01:00
10 changed files with 57 additions and 16 deletions

1
.gitignore vendored
View File

@ -8,6 +8,7 @@ build/
.env .env
.vscode .vscode
ilias_cookies.txt ilias_cookies.txt
PFERD.egg-info/
# PyInstaller # PyInstaller
sync_url.spec sync_url.spec

View File

@ -14,7 +14,7 @@ PRETTY = PrettyLogger(LOGGER)
try: try:
import keyring import keyring
except ImportError: except ImportError:
PRETTY.warning("Keyring module not found, KeyringAuthenticator won't work!") pass
class TfaAuthenticator: class TfaAuthenticator:

View File

@ -74,6 +74,8 @@ class KitShibbolethAuthenticator(IliasAuthenticator):
form = soup.find("form", {"class": "full content", "method": "post"}) form = soup.find("form", {"class": "full content", "method": "post"})
action = form["action"] action = form["action"]
csrf_token = form.find("input", {"name": "csrf_token"})["value"]
# Equivalent: Enter credentials in # Equivalent: Enter credentials in
# https://idp.scc.kit.edu/idp/profile/SAML2/Redirect/SSO # https://idp.scc.kit.edu/idp/profile/SAML2/Redirect/SSO
LOGGER.debug("Attempt to log in to Shibboleth using credentials") LOGGER.debug("Attempt to log in to Shibboleth using credentials")
@ -82,6 +84,7 @@ class KitShibbolethAuthenticator(IliasAuthenticator):
"_eventId_proceed": "", "_eventId_proceed": "",
"j_username": self._auth.username, "j_username": self._auth.username,
"j_password": self._auth.password, "j_password": self._auth.password,
"csrf_token": csrf_token
} }
soup = soupify(sess.post(url, data=data)) soup = soupify(sess.post(url, data=data))

View File

@ -40,6 +40,7 @@ class IliasElementType(Enum):
REGULAR_FILE = "REGULAR_FILE" REGULAR_FILE = "REGULAR_FILE"
VIDEO_FILE = "VIDEO_FILE" VIDEO_FILE = "VIDEO_FILE"
FORUM = "FORUM" FORUM = "FORUM"
MEETING = "MEETING"
EXTERNAL_LINK = "EXTERNAL_LINK" EXTERNAL_LINK = "EXTERNAL_LINK"
def is_folder(self) -> bool: def is_folder(self) -> bool:
@ -241,6 +242,8 @@ class IliasCrawler:
entries_to_process += self._crawl_video_directory(entry.path, url) entries_to_process += self._crawl_video_directory(entry.path, url)
continue continue
PRETTY.warning(f"Unknown type: {entry.entry_type}!")
return result return result
def _crawl_folder(self, folder_path: Path, url: str) -> List[IliasCrawlerEntry]: def _crawl_folder(self, folder_path: Path, url: str) -> List[IliasCrawlerEntry]:
@ -269,6 +272,25 @@ class IliasCrawler:
if element_type == IliasElementType.REGULAR_FILE: if element_type == IliasElementType.REGULAR_FILE:
result += self._crawl_file(folder_path, link, abs_url) result += self._crawl_file(folder_path, link, abs_url)
elif element_type == IliasElementType.MEETING:
meeting_name = str(element_path.name)
date_portion_str = meeting_name.split(" - ")[0]
date_portion = demangle_date(date_portion_str)
if not date_portion:
result += [IliasCrawlerEntry(element_path, abs_url, element_type, None)]
continue
rest_of_name = meeting_name
if rest_of_name.startswith(date_portion_str):
rest_of_name = rest_of_name[len(date_portion_str):]
new_name = datetime.datetime.strftime(date_portion, "%Y-%m-%d, %H:%M") \
+ rest_of_name
new_path = Path(folder_path, _sanitize_path_name(new_name))
result += [
IliasCrawlerEntry(new_path, abs_url, IliasElementType.REGULAR_FOLDER, None)
]
elif element_type is not None: elif element_type is not None:
result += [IliasCrawlerEntry(element_path, abs_url, element_type, None)] result += [IliasCrawlerEntry(element_path, abs_url, element_type, None)]
else: else:
@ -320,6 +342,8 @@ class IliasCrawler:
""" """
# pylint: disable=too-many-return-statements # pylint: disable=too-many-return-statements
found_parent: Optional[bs4.Tag] = None
# We look for the outer div of our inner link, to find information around it # We look for the outer div of our inner link, to find information around it
# (mostly the icon) # (mostly the icon)
for parent in link_element.parents: for parent in link_element.parents:
@ -350,6 +374,9 @@ class IliasCrawler:
if str(img_tag["src"]).endswith("frm.svg"): if str(img_tag["src"]).endswith("frm.svg"):
return IliasElementType.FORUM return IliasElementType.FORUM
if str(img_tag["src"]).endswith("sess.svg"):
return IliasElementType.MEETING
return IliasElementType.REGULAR_FOLDER return IliasElementType.REGULAR_FOLDER
@staticmethod @staticmethod

View File

@ -122,9 +122,22 @@ class IliasDownloader:
tmp_file = self._tmp_dir.new_path() tmp_file = self._tmp_dir.new_path()
while not self._try_download(info, tmp_file): download_successful = False
LOGGER.info("Retrying download: %r", info) for _ in range(0, 3):
self._authenticator.authenticate(self._session) try:
if not self._try_download(info, tmp_file):
LOGGER.info("Re-Authenticating due to download failure: %r", info)
self._authenticator.authenticate(self._session)
else:
download_successful = True
break
except IOError as e:
PRETTY.warning(f"I/O Error when downloading ({e}). Retrying...",)
LOGGER.info("Retrying download for %s", info.path)
if not download_successful:
PRETTY.error(f"Download of file {info.path} failed too often! Skipping it...")
return
dst_path = self._organizer.accept_file(tmp_file, info.path) dst_path = self._organizer.accept_file(tmp_file, info.path)
if dst_path and info.modification_date: if dst_path and info.modification_date:

View File

@ -3,13 +3,10 @@ Contains a few logger utility functions and implementations.
""" """
import logging import logging
from pathlib import Path from typing import Optional
from typing import List, Optional
from rich import print as rich_print
from rich._log_render import LogRender from rich._log_render import LogRender
from rich.console import Console from rich.console import Console
from rich.panel import Panel
from rich.style import Style from rich.style import Style
from rich.text import Text from rich.text import Text
from rich.theme import Theme from rich.theme import Theme

View File

@ -116,7 +116,7 @@ class Organizer(Location):
if self._is_marked(dst): if self._is_marked(dst):
PRETTY.warning(f"File {str(dst_absolute)!r} was already written!") PRETTY.warning(f"File {str(dst_absolute)!r} was already written!")
conflict = ConflictType.MARKED_FILE_OVERWRITTEN conflict = ConflictType.MARKED_FILE_OVERWRITTEN
if self._resolve_conflict(f"Overwrite file?", dst_absolute, conflict, default=False): if self._resolve_conflict("Overwrite file?", dst_absolute, conflict, default=False):
PRETTY.ignored_file(dst_absolute, "file was written previously") PRETTY.ignored_file(dst_absolute, "file was written previously")
return None return None

View File

@ -37,7 +37,7 @@ Ensure that you have at least Python 3.8 installed.
To install PFERD or update your installation to the latest version, run this To install PFERD or update your installation to the latest version, run this
wherever you want to install or have already installed PFERD: wherever you want to install or have already installed PFERD:
``` ```
$ pip install git+https://github.com/Garmelon/PFERD@v2.5.0 $ pip install git+https://github.com/Garmelon/PFERD@v2.5.4
``` ```
The use of [venv] is recommended. The use of [venv] is recommended.
@ -59,9 +59,9 @@ A full example setup and initial use could look like:
$ mkdir Vorlesungen $ mkdir Vorlesungen
$ cd Vorlesungen $ cd Vorlesungen
$ python3 -m venv .venv $ python3 -m venv .venv
$ .venv/bin/activate $ source .venv/bin/activate
$ pip install git+https://github.com/Garmelon/PFERD@v2.5.0 $ pip install git+https://github.com/Garmelon/PFERD@v2.5.4
$ curl -O https://raw.githubusercontent.com/Garmelon/PFERD/v2.5.0/example_config.py $ curl -O https://raw.githubusercontent.com/Garmelon/PFERD/v2.5.4/example_config.py
$ python3 example_config.py $ python3 example_config.py
$ deactivate $ deactivate
``` ```
@ -69,7 +69,7 @@ $ deactivate
Subsequent runs of the program might look like: Subsequent runs of the program might look like:
``` ```
$ cd Vorlesungen $ cd Vorlesungen
$ .venv/bin/activate $ source .venv/bin/activate
$ python3 example_config.py $ python3 example_config.py
$ deactivate $ deactivate
``` ```

View File

@ -2,7 +2,7 @@ from setuptools import find_packages, setup
setup( setup(
name="PFERD", name="PFERD",
version="2.5.0", version="2.5.4",
packages=find_packages(), packages=find_packages(),
install_requires=[ install_requires=[
"requests>=2.21.0", "requests>=2.21.0",

View File

@ -113,7 +113,7 @@ def main() -> None:
if not element_name: if not element_name:
print("Error, could not get element name. Please specify a folder yourself.") print("Error, could not get element name. Please specify a folder yourself.")
return return
folder = Path(element_name) folder = sanitize_windows_path(Path(element_name.replace("/", "-").replace("\\", "-")))
cookie_jar.save_cookies() cookie_jar.save_cookies()
else: else:
folder = Path(args.folder) folder = Path(args.folder)