StudyDriveDownloader: Python implementation of the StudyDrive API

StudyDriveDownloader.py

import requests
import json
import os
from datetime import datetime

baseurl = "https://api.studydrive.net/"

def login(user, passwd):
	param = {"client_id": 4,
			 "client_secret": "nmGaT4rJ3VVGQXu75ymi5Cu5bdqb3tFnkWw9f1IX",
			 "grant_type":"password",
			 "username": user,
			 "password": passwd}
	req = requests.post('{}oauth/token'.format(baseurl), data=param)
	req.raise_for_status()
	return json.loads(req.text)['access_token']

def getTime():
	return str(datetime.now().strftime('%Y-%m-%d %H:%M:%S'))

def getUniversityData(universityid, token): #returns all courses of the university
	headers={"authorization": "Bearer "+token}
	req = requests.get('{}api/app/v1/universities/{}/courses'.format(baseurl,universityid), headers=headers)
	req.raise_for_status()
	return json.loads(req.text)

def getCourseData(courseid, token, page=0, reference_time=None):
	#reference_time="2019-09-24 14:52:08"
	param = {"sort": "time",
			"page": page,
			"semester_from":0,
			"semester_until":0,
			"type_ids":0}
	if page>0:
		if reference_time is None:
			reference_time = getTime()
		param["reference_time"] = reference_time
	headers={"authorization": "Bearer "+token}
	req = requests.get('{}api/app/v1/feed/courses/{}/documents'.format(baseurl,courseid), params=param, headers=headers)
	req.raise_for_status()
	return json.loads(req.text)

def getFullCourseData(courseid, token, until=None): # until is of type date, e.g. datetime.now()
	reference_time = getTime()
	init_data = getCourseData(courseid, token, page=0, reference_time=reference_time)
	last_page = int(init_data["last_page"])
	files = init_data["files"]
	for i in range(1,last_page+1):
		if (until != None) and (len([f for f in files if datetime.strptime(f["uploaded"], '%Y-%m-%d %H:%M:%S')>until])==0):
			break
		files.extend(getCourseData(courseid, token, page=i, reference_time=reference_time)["files"])
	init_data["files"] = files
	return init_data

def getDocument(docid, token):
	headers={"authorization": "Bearer "+token}
	#uploadDate = datetime.strptime(data["files"][0]["uploaded"], '%Y-%m-%d %H:%M:%S')
	req = requests.get('{}api/app/v1/documents/{}/download'.format(baseurl,docid), headers=headers)
	req.raise_for_status()
	return req.content

def downloadAllFilesInCourse(filelist, token, folder="."):
	for f in filelist:
		docid = f['file_id']
		docname = f['file_name'] + docid + f["file_name"].split(".")[-1]
		print("Downloading {}...".format(docname))
		doc = getDocument(docid,login_token)
		if os.path.isfile(docname):
			print("Found duplicate: {} already exists".format(docname))
		file = open(folder + "/" + docname, "wb")
		file.write(doc)
		file.close()

def crawlAllCourses(lastcrawled, university_id, token):
	#lastcrawled = {'50936': "2019-09-27 11:38:57", ...}
	courses = getUniversityData(universityid, token)
	for c in courses:
		if c["course_id"] in lastcrawled.keys():
			until = lastcrawled[c["course_id"]]
		else:
			until = None
		data = getFullCourseData(c["course_id"], token, until=until)
		if not os.path.exists(c["course_name"]):
			os.mkdir(c["course_name"])
		downloadAllFilesInCourse(data["files"], token, folder=c["course_name"])
		lastcrawled[c["course_id"]] = data["files"][0]["uploaded"]
	return lastcrawled #return updated lastcrawled

Thanks for your fast answer - for testing purposes I used curl instead of python and forgot the -X POST 🙈