Merge pull request #3 from jnthn-b/master

Multi-Threading!

.gitignore

@@ -1,3 +1,4 @@
 .vscode/settings.json
 config.ini
 .DS_Store
+.idea

README.md

@@ -4,6 +4,8 @@ to run for the studip platform of the university of bremen:
 https://elearning.uni-bremen.de
 But it should be possible to move this to any studip installation by changing
 the urls.
+This version is using Multi-Threading to download, extract & clean all 
+files from your courses at the same time.
 
 ## Setup
 It's just a script no GUI or service files yet. To run it you need to have
@@ -32,3 +34,4 @@ Run the script by double click or from the command line
 
 ## Credits
 [StudIP_Filename_Cleaner](https://github.com/Schlaurens/StudIP_Filename_Cleaner) courtesy of [Schlaurens](https://github.com/Schlaurens/)
+Multi-Threading made by [Jonathan Bröring](https://github.com/jnthn-b) 

studip-sync.py

@@ -1,22 +1,28 @@
-import requests, io, zipfile, os, configparser, re
-from lxml import html
+import configparser
+import io
+import os
+import re
+import requests
+import zipfile
 from bs4 import BeautifulSoup
+import threading
 
 login_url = 'https://elearning.uni-bremen.de/index.php?again=yes'
 course_url = 'https://elearning.uni-bremen.de/dispatch.php/course/files?cid='
 newest_url = 'https://elearning.uni-bremen.de/dispatch.php/course/files/newest_files?cid='
 
 cfg = configparser.ConfigParser()
 script_path = os.path.dirname(os.path.abspath(__file__))
-cfg.read(os.path.join(script_path,'config.ini'))
+cfg.read(os.path.join(script_path, 'config.ini'))
 try:
     user = cfg.get('settings', 'user')
     password = cfg.get('settings', 'password')
-    path = cfg.get('settings', 'data_folder')  
+    path = cfg.get('settings', 'data_folder')
     new_only = cfg.get('settings', 'new_only')
 except Exception as e:
     print('error parsing config file')
     print(e)
+print("Config Loaded!")
 
 print('starting session')
 session = requests.Session()
@@ -38,49 +44,56 @@
 else:
     print('login failed')
 
-for course in cfg.items('courses'):
+def getfiles(course):
     file_target = os.path.join(path, course[0])
     download_url = course_url + course[1]
-    print('finding course',course[0],'(',course[1],')')
+    print('finding course', course[0], '(', course[1], ')')
 
     download_page = session.get(download_url)
-    
+
     parsed_content = BeautifulSoup(download_page.content, 'html.parser')
     pretty_content = BeautifulSoup(parsed_content.prettify(), 'html.parser')
 
-    print('extracting post parameters')
-    security_token = pretty_content.find('input', attrs={'type':'hidden', 'name':'security_token'}).attrs['value']
-    parent_folder_id = pretty_content.find('input', attrs={'type':'hidden', 'name':'parent_folder_id'}).attrs['value']
-    post_url = pretty_content.find('form', attrs={'method': 'post', 'action':re.compile('^https://elearning.uni-bremen.de/dispatch.php/file/bulk/')}).attrs['action']
-    checkboxes =  pretty_content.find_all('input', attrs={'class':'studip-checkbox', 'type':'checkbox', 'name':'ids[]', 'id':re.compile('^file_checkbox_')})
-    ids = list(map(lambda c : c.attrs['value'], checkboxes))
+    print(course[0], ': extracting post parameters')
+    security_token = pretty_content.find('input', attrs={'type': 'hidden', 'name': 'security_token'}).attrs['value']
+    parent_folder_id = pretty_content.find('input', attrs={'type': 'hidden', 'name': 'parent_folder_id'}).attrs['value']
+    post_url = pretty_content.find('form', attrs={'method': 'post', 'action': re.compile(
+        '^https://elearning.uni-bremen.de/dispatch.php/file/bulk/')}).attrs['action']
+    checkboxes = pretty_content.find_all('input',
+                                         attrs={'class': 'studip-checkbox', 'type': 'checkbox', 'name': 'ids[]',
+                                                'id': re.compile('^file_checkbox_')})
+    ids = list(map(lambda c: c.attrs['value'], checkboxes))
 
     token = {}
     token['security_token'] = security_token
     token['parent_folder_id'] = parent_folder_id
     token['ids[]'] = ids
     token['download'] = ''
 
-    if(new_only == 'yes'):
+    if (new_only == 'yes'):
         post_url = newest_url + course[1]
         token = {}
 
-    print('requesting download')
+    print(course[0], ': requesting download')
     r = session.post(post_url, data=token)
-    if(r.status_code != 200):
-        print('request failed')
+    if (r.status_code != 200):
+        print(course[0], ': request failed')
 
     z = zipfile.ZipFile(io.BytesIO(r.content))
-    print('extracting zip')
+    print(course[0], ': extracting zip')
     z.extractall(file_target)
 
     for root, dirs, files in os.walk(file_target):
-        for file in files: 
+        for file in files:
             if file == "archive_filelist.csv":
                 os.remove(os.path.join(root, file))
                 continue
 
-            filename = os.path.join(root,file)
+            filename = os.path.join(root, file)
             os.replace(filename, os.path.join(root, re.sub('^[+[0-9]+]_', '', file)))
-
-    print("cleaned files")
+
+    print(course[0], ': cleaned files')
+
+for course in cfg.items('courses'):
+    threading.Thread(target=getfiles, args=(course,)).start()
+