cyberes
/
canvas-student-data-export
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Added checks to prevent redownloading of a page.

This commit is contained in:
dj346 2021-12-24 05:23:10 -08:00
parent 97b02f3f5b
commit 3dfe0b191e
1 changed files with 56 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

56
export.py
View File

@ -677,7 +677,10 @@ def downloadCourseHTML(api_url, cookies_path):
if not os.path.exists(course_dir): if not os.path.exists(course_dir):
os.makedirs(course_dir) os.makedirs(course_dir)
course_list_path = os.path.join(course_dir, "course_list.html")
# Downloads the course list. # Downloads the course list.
if not os.path.exists(course_list_path):
download_page(api_url + "/courses/", cookies_path, course_dir, "course_list.html") download_page(api_url + "/courses/", cookies_path, course_dir, "course_list.html")
def downloadCourseHomePageHTML(api_url, course_view, cookies_path): def downloadCourseHomePageHTML(api_url, course_view, cookies_path):
@ -692,7 +695,10 @@ def downloadCourseHomePageHTML(api_url, course_view, cookies_path):
if not os.path.exists(dl_dir): if not os.path.exists(dl_dir):
os.makedirs(dl_dir) os.makedirs(dl_dir)
homepage_path = os.path.join(dl_dir, "homepage.html")
# Downloads the course home page. # Downloads the course home page.
if not os.path.exists(homepage_path):
download_page(api_url + "/courses/" + str(course_view.course_id), cookies_path, dl_dir, "homepage.html") download_page(api_url + "/courses/" + str(course_view.course_id), cookies_path, dl_dir, "homepage.html")
def downloadAssignmentPages(api_url, course_view, cookies_path): def downloadAssignmentPages(api_url, course_view, cookies_path):
@ -706,7 +712,10 @@ def downloadAssignmentPages(api_url, course_view, cookies_path):
if not os.path.exists(base_assign_dir): if not os.path.exists(base_assign_dir):
os.makedirs(base_assign_dir) os.makedirs(base_assign_dir)
assignment_list_path = os.path.join(base_assign_dir, "assignment_list.html")
# Download assignment list (theres a chance this might be the course homepage if the course has the assignments page disabled) # Download assignment list (theres a chance this might be the course homepage if the course has the assignments page disabled)
if not os.path.exists(assignment_list_path):
download_page(api_url + "/courses/" + str(course_view.course_id) + "/assignments/", cookies_path, base_assign_dir, "assignment_list.html") download_page(api_url + "/courses/" + str(course_view.course_id) + "/assignments/", cookies_path, base_assign_dir, "assignment_list.html")
for assignment in course_view.assignments: for assignment in course_view.assignments:
@ -720,7 +729,10 @@ def downloadAssignmentPages(api_url, course_view, cookies_path):
if not os.path.exists(assign_dir): if not os.path.exists(assign_dir):
os.makedirs(assign_dir) os.makedirs(assign_dir)
assignment_page_path = os.path.join(assign_dir, "assignment.html")
# Download assignment page, this usually has instructions and etc. # Download assignment page, this usually has instructions and etc.
if not os.path.exists(assignment_page_path):
download_page(assignment.html_url, cookies_path, assign_dir, "assignment.html") download_page(assignment.html_url, cookies_path, assign_dir, "assignment.html")
for submission in assignment.submissions: for submission in assignment.submissions:
@ -734,7 +746,10 @@ def downloadAssignmentPages(api_url, course_view, cookies_path):
if not os.path.exists(submission_dir): if not os.path.exists(submission_dir):
os.makedirs(submission_dir) os.makedirs(submission_dir)
submission_page_dir = os.path.join(submission_dir, "submission.html")
# Download submission url, this is typically a more focused page # Download submission url, this is typically a more focused page
if not os.path.exists(submission_page_dir):
download_page(submission.preview_url, cookies_path, submission_dir, "submission.html") download_page(submission.preview_url, cookies_path, submission_dir, "submission.html")
# If theres more then 1 attempt, save each attempt in attempts folder # If theres more then 1 attempt, save each attempt in attempts folder
@ -749,7 +764,11 @@ def downloadAssignmentPages(api_url, course_view, cookies_path):
# different ID's however, as I wasnt able to find out what the url # different ID's however, as I wasnt able to find out what the url
# for the specific id's attempts would be. # for the specific id's attempts would be.
for i in range(submission.attempt): for i in range(submission.attempt):
download_page(assignment.updated_url + "/history?version=" + str(i+1), cookies_path, submission_dir, "attempt_" + str(i+1) + ".html") filename = "attempt_" + str(i+1) + ".html"
submission_page_attempt_dir = os.path.join(submission_dir, filename)
if not os.path.exists(submission_page_attempt_dir):
download_page(assignment.updated_url + "/history?version=" + str(i+1), cookies_path, filename)
def downloadCourseModulePages(api_url, course_view, cookies_path): def downloadCourseModulePages(api_url, course_view, cookies_path):
if(cookies_path == "" or len(course_view.modules) == 0): if(cookies_path == "" or len(course_view.modules) == 0):
@ -762,7 +781,10 @@ def downloadCourseModulePages(api_url, course_view, cookies_path):
if not os.path.exists(modules_dir): if not os.path.exists(modules_dir):
os.makedirs(modules_dir) os.makedirs(modules_dir)
module_list_dir = os.path.join(modules_dir, "modules_list.html")
# Downloads the modules page (possible this is disabled by the teacher) # Downloads the modules page (possible this is disabled by the teacher)
if not os.path.exists(module_list_dir):
download_page(api_url + "/courses/" + str(course_view.course_id) + "/modules/", COOKIES_PATH, modules_dir, "modules_list.html") download_page(api_url + "/courses/" + str(course_view.course_id) + "/modules/", COOKIES_PATH, modules_dir, "modules_list.html")
for module in course_view.modules: for module in course_view.modules:
@ -776,8 +798,12 @@ def downloadCourseModulePages(api_url, course_view, cookies_path):
if not os.path.exists(items_dir): if not os.path.exists(items_dir):
os.makedirs(items_dir) os.makedirs(items_dir)
filename = makeValidFilename(str(item.title)) + ".html"
module_item_dir = os.path.join(items_dir, filename)
# Download the module page. # Download the module page.
download_page(item.url, cookies_path, items_dir, makeValidFilename(str(item.title)) + ".html") if not os.path.exists(module_item_dir):
download_page(item.url, cookies_path, items_dir, filename)
def downloadCourseAnnouncementPages(api_url, course_view, cookies_path): def downloadCourseAnnouncementPages(api_url, course_view, cookies_path):
if(cookies_path == "" or len(course_view.announcements) == 0): if(cookies_path == "" or len(course_view.announcements) == 0):
@ -790,7 +816,10 @@ def downloadCourseAnnouncementPages(api_url, course_view, cookies_path):
if not os.path.exists(base_announce_dir): if not os.path.exists(base_announce_dir):
os.makedirs(base_announce_dir) os.makedirs(base_announce_dir)
announcement_list_dir = os.path.join(base_announce_dir, "announcement_list.html")
# Download assignment list (theres a chance this might be the course homepage if the course has the assignments page disabled) # Download assignment list (theres a chance this might be the course homepage if the course has the assignments page disabled)
if not os.path.exists(announcement_list_dir):
download_page(api_url + "/courses/" + str(course_view.course_id) + "/announcements/", cookies_path, base_announce_dir, "announcement_list.html") download_page(api_url + "/courses/" + str(course_view.course_id) + "/announcements/", cookies_path, base_announce_dir, "announcement_list.html")
for announcements in course_view.announcements: for announcements in course_view.announcements:
@ -803,8 +832,12 @@ def downloadCourseAnnouncementPages(api_url, course_view, cookies_path):
os.makedirs(announce_dir) os.makedirs(announce_dir)
for i in range(announcements.amount_pages): for i in range(announcements.amount_pages):
filename = "announcement_" + str(i+1) + ".html"
announcement_page_dir = os.path.join(announce_dir, filename)
# Download assignment page, this usually has instructions and etc. # Download assignment page, this usually has instructions and etc.
download_page(announcements.url + "/page-" + str(i+1), cookies_path, announce_dir, "announcement_" + str(i+1) + ".html") if not os.path.exists(announcement_page_dir):
download_page(announcements.url + "/page-" + str(i+1), cookies_path, announce_dir, filename)
def downloadCourseDicussionPages(api_url, course_view, cookies_path): def downloadCourseDicussionPages(api_url, course_view, cookies_path):
if(cookies_path == "" or len(course_view.discussions) == 0): if(cookies_path == "" or len(course_view.discussions) == 0):
@ -817,7 +850,10 @@ def downloadCourseDicussionPages(api_url, course_view, cookies_path):
if not os.path.exists(base_discussion_dir): if not os.path.exists(base_discussion_dir):
os.makedirs(base_discussion_dir) os.makedirs(base_discussion_dir)
dicussion_list_dir = os.path.join(base_discussion_dir, "discussion_list.html")
# Download assignment list (theres a chance this might be the course homepage if the course has the assignments page disabled) # Download assignment list (theres a chance this might be the course homepage if the course has the assignments page disabled)
if not os.path.exists(dicussion_list_dir):
download_page(api_url + "/courses/" + str(course_view.course_id) + "/discussion_topics/", cookies_path, base_discussion_dir, "discussion_list.html") download_page(api_url + "/courses/" + str(course_view.course_id) + "/discussion_topics/", cookies_path, base_discussion_dir, "discussion_list.html")
for discussion in course_view.discussions: for discussion in course_view.discussions:
@ -830,8 +866,12 @@ def downloadCourseDicussionPages(api_url, course_view, cookies_path):
os.makedirs(dicussion_dir) os.makedirs(dicussion_dir)
for i in range(discussion.amount_pages): for i in range(discussion.amount_pages):
filename = "dicussion_" + str(i+1) + ".html"
dicussion_page_dir = os.path.join(dicussion_dir, filename)
# Download assignment page, this usually has instructions and etc. # Download assignment page, this usually has instructions and etc.
download_page(discussion.url + "/page-" + str(i+1), cookies_path, dicussion_dir, "dicussion_" + str(i+1) + ".html") if not os.path.exists(dicussion_page_dir):
download_page(discussion.url + "/page-" + str(i+1), cookies_path, dicussion_dir, filename)
if __name__ == "__main__": if __name__ == "__main__":
@ -881,6 +921,10 @@ if __name__ == "__main__":
skip = set(COURSES_TO_SKIP) skip = set(COURSES_TO_SKIP)
if (COOKIES_PATH):
print(" Downloading course list page")
downloadCourseHTML(API_URL, COOKIES_PATH)
for course in courses: for course in courses:
if course.id in skip or not hasattr(course, "name") or not hasattr(course, "term"): if course.id in skip or not hasattr(course, "name") or not hasattr(course, "term"):
continue continue
@ -899,9 +943,6 @@ if __name__ == "__main__":
course_view.modules = findCourseModules(course, course_view) course_view.modules = findCourseModules(course, course_view)
if(COOKIES_PATH): if(COOKIES_PATH):
print(" Downloading course list page")
downloadCourseHTML(API_URL, COOKIES_PATH)
print(" Downloading course home page") print(" Downloading course home page")
downloadCourseHomePageHTML(API_URL, course_view, COOKIES_PATH) downloadCourseHomePageHTML(API_URL, course_view, COOKIES_PATH)
@ -917,7 +958,6 @@ if __name__ == "__main__":
print(" Downloading course dicussion pages") print(" Downloading course dicussion pages")
downloadCourseDicussionPages(API_URL, course_view, COOKIES_PATH) downloadCourseDicussionPages(API_URL, course_view, COOKIES_PATH)
print(" Exporting all course data") print(" Exporting all course data")
exportAllCourseData(course_view) exportAllCourseData(course_view)