forked from john-hix/scrape-canvas
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathdl_instructure_vids.py
56 lines (35 loc) · 1.23 KB
/
dl_instructure_vids.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
from selenium import webdriver
import time
import urllib.request
USERNAME=""
PASSWORD=""
COURSE_URL=""
MODULE_ID_STRING=""
driver = webdriver.Firefox()
driver.get(COURSE_URL)
driver.find_element_by_id("username").send_keys(USERNAME)
driver.find_element_by_id("password").send_keys(PASSWORD)
driver.find_element_by_name("_eventId_proceed").click()
time.sleep(3)
element_list = []
for e in driver.find_elements_by_xpath("//a[contains(text(), '" + MODULE_ID_STRING + "')]"):
lecture_link = e.get_attribute("href")
name = e.get_attribute("title")
print(name)
if name != "":
element_list.append((name, lecture_link))
for e in element_list:
print(e)
driver.get(e[1])
part_elements = driver.find_elements_by_xpath("//*[contains(@href,'lu.instructuremedia.com/embed/')]")
part_links = []
for f in part_elements:
part_links.append(f.get_attribute("href"))
for i in range(len(part_links)):
driver.get(part_links[i])
time.sleep(4)
source_element = driver.find_element_by_tag_name("source")
src = source_element.get_attribute("src")
urllib.request.urlretrieve(src, e[0].replace(r"/", "&") + " Part " + str(i + 1) + ".mp4")
time.sleep(3)
driver.quit()