FilesExpand file tree

 master

/

pythonVideoDownloader.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

66 lines (44 loc) · 1.68 KB

 master

/

pythonVideoDownloader.py

Copy path

Top

File metadata and controls

• Code
• Blame

66 lines (44 loc) · 1.68 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

57

58

59

60

61

62

63

64

65

66

import requests

from bs4 import BeautifulSoup

'''

URL of the archive web-page which provides link to

all video lectures. It would have been tiring to

download each video manually.

In this example, we first crawl the webpage to extract

all the links and then download videos.

'''

# specify the URL of the archive here

archive_url = "http://www-personal.umich.edu/~csev/books/py4inf/media/"

def get_video_links():

# create response object

r = requests.get(archive_url)

# create beautiful-soup object

soup = BeautifulSoup(r.content,'html5lib')

# find all links on web-page

links = soup.findAll('a')

# filter the link sending with .mp4

video_links = [archive_url + link['href'] for link in links if link['href'].endswith('mp4')]

return video_links

def download_video_series(video_links):

for link in video_links:

'''iterate through all links in video_links

and download them one by one'''

# obtain filename by splitting url and getting

# last string

file_name = link.split('/')[-1]

print "Downloading the file:%s"%file_name

# create response object

r = requests.get(link, stream = True)

# download started

with open(file_name, 'wb') as f:

for chunk in r.iter_content(chunk_size = 1024*1024):

if chunk:

f.write(chunk)

print "%s downloaded!\n"%file_name

print "All videos are downloaded!"

return

if __name__ == "__main__":

# getting all video links

video_links = get_video_links()

# download all videos

download_video_series(video_links)