KevinMidboe/ITLscraper
1
0
Fork 0
mirror of https://github.com/KevinMidboe/ITLscraper.git synced 2025-10-29 01:30:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

add single scrape

Browse Source
This commit is contained in:
sigvartmh
2017-05-11 22:51:43 +02:00
parent 41e4ab00fc
commit 2b761d9c8f
1 changed files with 19 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
itl_scrape.py
View File

@@ -203,16 +203,28 @@ def find_files(folders):
#print(args.session_cookie) #print(args.session_cookie)
#key = args.session_cookie #key = args.session_cookie
folder_url = "https://ntnu.itslearning.com/Folder/processfolder.aspx?FolderID=" folder_url = "https://ntnu.itslearning.com/Folder/processfolder.aspx?FolderID="
for course in courses: course_url = input("Emne link or leave blank to download all:")
r = rq.get(base_url+course, cookies=itl_cookies) if course_url:
folder_title=input("folder title:")
r = rq.get(course_url, cookies=itl_cookies)
course_path = os.path.join(os.path.abspath(os.path.curdir)) course_path = os.path.join(os.path.abspath(os.path.curdir))
make_folder(course_path, course_title[course]) make_folder(course_path, folder_title)
folder_id = re.search("FolderID=(.+?)'",r.text).group(1) folder_id = re.search("FolderID=(.+?)'",r.text).group(1)
print("folder id",folder_id)
print("folder_url"+folder_id)
r = rq.get(folder_url+folder_id, cookies=itl_cookies) r = rq.get(folder_url+folder_id, cookies=itl_cookies)
print(r.url) r = rq.get(folder_url+folder_id, cookies=itl_cookies)
table = find_folder_table(r.text) table = find_folder_table(r.text)
find_files(table) find_files(table)
os.chdir('..') else:
for course in courses:
r = rq.get(base_url+course, cookies=itl_cookies)
course_path = os.path.join(os.path.abspath(os.path.curdir))
make_folder(course_path, course_title[course])
folder_id = re.search("FolderID=(.+?)'",r.text).group(1)
print("folder id",folder_id)
print("folder_url"+folder_id)
r = rq.get(folder_url+folder_id, cookies=itl_cookies)
print(r.url)
table = find_folder_table(r.text)
find_files(table)
os.chdir('..')