Bump version to 1.1.8

(hopefully)

.gitignore

@@ -10,3 +10,4 @@ pyvenv.cfg
 
 .tmp/
 pip-selfcheck.json
+.mypy_cache/

PFERD/__init__.py

@@ -3,6 +3,7 @@ import logging
 from .ffm import *
 from .ilias import *
 from .norbert import *
+from .ti import *
 from .utils import *
 
 __all__ = ["STYLE", "FORMAT", "DATE_FORMAT", "FORMATTER", "enable_logging"]
@@ -10,6 +11,7 @@ __all__ = ["STYLE", "FORMAT", "DATE_FORMAT", "FORMATTER", "enable_logging"]
 __all__ += ffm.__all__
 __all__ += ilias.__all__
 __all__ += norbert.__all__
+__all__ += ti.__all__
 __all__ += utils.__all__
 
 STYLE = "{"

PFERD/ffm.py

@@ -8,10 +8,11 @@ import bs4
 import requests
 
 from .organizer import Organizer
-from .utils import stream_to_path
+from .utils import stream_to_path, PrettyLogger
 
 __all__ = ["FfM"]
 logger = logging.getLogger(__name__)
+pretty = PrettyLogger(logger)
 
 class FfM:
     BASE_URL = "http://www.math.kit.edu/"
@@ -23,7 +24,7 @@ class FfM:
         self._session = requests.Session()
 
     def synchronize(self, urlpart, to_dir, transform=lambda x: x):
-        logger.info(f"    Synchronizing {urlpart} to {to_dir} using the FfM synchronizer.")
+        pretty.starting_synchronizer(to_dir, "FfM", urlpart)
 
         sync_path = pathlib.Path(self.base_path, to_dir)
 

PFERD/ilias.py

@@ -4,13 +4,13 @@ import logging
 import pathlib
 import re
 
-import bs4
-
 from .ilias_authenticators import ShibbolethAuthenticator
 from .organizer import Organizer
+from .utils import PrettyLogger
 
 __all__ = ["Ilias"]
 logger = logging.getLogger(__name__)
+pretty = PrettyLogger(logger)
 
 class Ilias:
     FILE_RE = re.compile(r"goto\.php\?target=(file_\d+_download)")
@@ -22,7 +22,7 @@ class Ilias:
         self._auth = ShibbolethAuthenticator(base_path / cookie_file)
 
     def synchronize(self, ref_id, to_dir, transform=lambda x: x, filter=lambda x: True):
-        logger.info(f"    Synchronizing ref_id {ref_id} to {to_dir} using the Ilias synchronizer.")
+        pretty.starting_synchronizer(to_dir, "ILIAS", f"ref_id {ref_id}")
 
         sync_path = pathlib.Path(self.base_path, to_dir)
         orga = Organizer(self.base_path, sync_path)

PFERD/ilias_authenticators.py

@@ -23,16 +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",
-        "text/xml",
-        "text/plain",
-        "image/jpeg",
-        "image/png",
-    ]
-
     def __init__(self, cookie_file) -> None:
         # Because LWPCookieJar insists on the path being str-like instead of
         # Path-like.
@@ -147,11 +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:
+            if content_type.startswith("text/html"):
-                # Yay, we got the file :)
-                stream_to_path(r, to_path)
-                return True
-            elif content_type == "text/html":
                 # Dangit, we're probably not logged in.
                 soup = bs4.BeautifulSoup(r.text, "html.parser")
                 if self._is_logged_in(soup):
@@ -159,9 +145,9 @@ class ShibbolethAuthenticator:
                             "Attempting to download a web page, not a file")
                 return False
             else:
-                # What *did* we get?
+                # Yay, we got the file :)
-                raise ContentTypeException(
+                stream_to_path(r, to_path)
-                        f"Unknown file of type {content_type}")
+                return True
 
     def download_file(self, file_id, to_path):
         params = {"target": file_id}

PFERD/norbert.py

@@ -9,10 +9,11 @@ import bs4
 import requests
 
 from .organizer import Organizer
-from .utils import rename, stream_to_path
+from .utils import rename, stream_to_path, PrettyLogger
 
 __all__ = ["Norbert"]
 logger = logging.getLogger(__name__)
+pretty = PrettyLogger(logger)
 
 class Norbert:
     BASE_URL = "https://studwww.informatik.kit.edu/~s_blueml/"
@@ -24,7 +25,7 @@ class Norbert:
         self._session = requests.Session()
 
     def synchronize(self, to_dir, transform=lambda x: x, unzip=lambda _: True):
-        logger.info(f"    Synchronizing to {to_dir} using the Norbert synchronizer.")
+        pretty.starting_synchronizer(to_dir, "Norbert")
 
         sync_path = pathlib.Path(self.base_path, to_dir)
         orga = Organizer(self.base_path, sync_path)

PFERD/organizer.py

@@ -7,6 +7,7 @@ from . import utils
 
 __all__ = ["Organizer"]
 logger = logging.getLogger(__name__)
+pretty = utils.PrettyLogger(logger)
 
 class Organizer:
     def __init__(self, base_dir, sync_dir):
@@ -64,7 +65,7 @@ class Organizer:
 
         if to_path.exists():
             if filecmp.cmp(from_path, to_path, shallow=False):
-                logger.info(f"Ignored {to_path}")
+                pretty.ignored_file(to_path)
 
                 # remember path for later reference
                 self._added_files.add(to_path.resolve())
@@ -73,9 +74,9 @@ class Organizer:
                 # No further action needed, especially not overwriting symlinks...
                 return
             else:
-                logger.info(f"Different file at {to_path}")
+                pretty.modified_file(to_path)
         else:
-            logger.info(f"New file at {to_path}")
+            pretty.new_file(to_path)
 
         # copy the file from from_path to sync_dir/to_path
         # If the file being replaced was a symlink, the link itself is overwritten,

PFERD/ti.py

@@ -0,0 +1,112 @@
+# Fakultät für Mathematik (FfM)
+
+import getpass
+import logging
+import pathlib
+import re
+from urllib.parse import urljoin
+
+import bs4
+import requests
+
+from .organizer import Organizer
+from .utils import stream_to_path, PrettyLogger
+
+__all__ = ["Ti"]
+logger = logging.getLogger(__name__)
+pretty = PrettyLogger(logger)
+
+class Ti:
+    BASE_URL = "http://ti.ira.uka.de/"
+    FILE_RE = re.compile(r"^.+\.pdf$")
+
+    def __init__(self, base_path):
+        self.base_path = base_path
+
+        self._session = requests.Session()
+        self._credentials = None
+
+    def synchronize(self, urlpart, to_dir, transform=lambda x: x,
+            filter=lambda x: True):
+        pretty.starting_synchronizer(to_dir, "Ti", urlpart)
+
+        sync_path = pathlib.Path(self.base_path, to_dir)
+
+        orga = Organizer(self.base_path, sync_path)
+        orga.clean_temp_dir()
+
+        self._reset_credentials()
+
+        available = self._find_available(urlpart)
+
+        for name, address in sorted(available.items()):
+            path = pathlib.PurePath(name)
+            if filter(path):
+                self._crawl(urlpart + address, path, orga, transform)
+            else:
+                logger.info(f"Skipping {name}/")
+
+        orga.clean_sync_dir()
+        orga.clean_temp_dir()
+
+        self._reset_credentials()
+
+    def _find_available(self, urlpart):
+        url = self.BASE_URL + urlpart
+        r = self._session.get(url)
+        soup = bs4.BeautifulSoup(r.text, "html.parser")
+
+        available = {}
+
+        if soup.find(href="./Vorlesung/Vorlesung.php"):
+            logger.info("Found Folien/")
+            available["Folien"] = "/Vorlesung/"
+        if soup.find(href="./Uebungen/Uebungen.php"):
+            logger.info("Found Blätter/")
+            available["Blätter"] = "/Uebungen/"
+        if soup.find(href="./Tutorien/Tutorien.php"):
+            logger.info("Found Tutorien/")
+            available["Tutorien"] = "/Tutorien/"
+
+        return available
+
+    def _crawl(self, urlpart, path, orga, transform):
+        url = self.BASE_URL + urlpart
+        r = self._session.get(url)
+        soup = bs4.BeautifulSoup(r.text, "html.parser")
+
+        for filelink in soup.find_all("a", href=self.FILE_RE):
+            filepath = path / filelink["href"]
+            fileurl = urljoin(url, filelink["href"])
+
+            new_path = transform(filepath)
+            if new_path is None:
+                continue
+            logger.debug(f"Transformed from {filepath} to {new_path}")
+
+            temp_path = orga.temp_file()
+            self._download(fileurl, temp_path)
+            orga.add_file(temp_path, new_path)
+
+
+    def _get_credentials(self):
+        if self._credentials is None:
+            print("Please enter Ti credentials.")
+            username = getpass.getpass(prompt="Username: ")
+            password = getpass.getpass(prompt="Password: ")
+            self._credentials = (username, password)
+        return self._credentials
+
+    def _reset_credentials(self):
+        self._credentials = None
+
+    def _download(self, url, to_path):
+        while True:
+            username, password = self._get_credentials()
+            with self._session.get(url, stream=True, auth=(username, password)) as r:
+                if r.ok:
+                    stream_to_path(r, to_path)
+                    return
+                else:
+                    print("Incorrect credentials.")
+                    self._reset_credentials()

PFERD/utils.py

@@ -1,5 +1,8 @@
 import os
+import sys
 import pathlib
+from colorama import Style
+from colorama import Fore
 
 __all__ = [
     "get_base_dir",
@@ -8,6 +11,7 @@ __all__ = [
     "stream_to_path",
     "ContentTypeException",
     "FileNotFoundException",
+    "PrettyLogger",
 ]
 
 def get_base_dir(script_file):
@@ -26,8 +30,35 @@ def stream_to_path(response, to_path, chunk_size=1024**2):
         for chunk in response.iter_content(chunk_size=chunk_size):
             fd.write(chunk)
 
+def isOutputPipe():
+    """Returns whether this program's output is attached to a pipe.
+    """
+    return sys.stdout.isatty
+
 class ContentTypeException(Exception):
     pass
 
 class FileNotFoundException(Exception):
     pass
+
+class PrettyLogger:
+
+    def __init__(self, logger):
+        self.logger = logger
+
+    def modified_file(self, file_name):
+        self.logger.info(f"{Fore.MAGENTA}{Style.BRIGHT}Modified {file_name}.{Style.RESET_ALL}")
+
+    def new_file(self, file_name):
+        self.logger.info(f"{Fore.GREEN}{Style.BRIGHT}Created {file_name}.{Style.RESET_ALL}")
+
+    def ignored_file(self, file_name):
+        self.logger.info(f"{Style.DIM}Ignored {file_name}.{Style.RESET_ALL}")
+
+    def starting_synchronizer(self, target_directory, synchronizer_name, subject=None):
+        subject_str = f"{subject} " if subject else ""
+        self.logger.info("")
+        self.logger.info((
+            f"{Fore.CYAN}{Style.BRIGHT}Synchronizing {subject_str}to {target_directory}"
+            f" using the {synchronizer_name} synchronizer.{Style.RESET_ALL}"
+        ))

README.md

@@ -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@v1.1.0
+$ 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@v1.1.0
+$ 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

setup.py

@@ -2,11 +2,12 @@ from setuptools import setup
 
 setup(
         name="PFERD",
-        version="1.1.0",
+        version="1.1.8",
         packages=["PFERD"],
         install_requires=[
             "requests>=2.21.0",
             "beautifulsoup4>=4.7.1",
+            "colorama>=0.4.1"
         ],
 )