pyAutomation/tedTalkDownloader.py at main · mydevground/pyAutomation · GitHub

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
import requests #getting content of the TED Talk page

from bs4 import BeautifulSoup #web scraping

import re #Regular Expression pattern matching

from urllib.request import urlretrieve #downloading mp4


url = "https://www.ted.com/talks/talithia_williams_own_your_body_s_data"


r = requests.get(url)

print("Download about to start")

soup = BeautifulSoup(r.content, features="lxml")

for val in soup.findAll("script"):
    if(re.search("talkPage.init",str(val))) is not None:
        result = str(val)

result_mp4 = re.search("(?P<url>https?://[^\s]+)(mp4)", result).group("url")

mp4_url = result_mp4.split('"')[0]

print("Downloading video from ..... " + mp4_url)

file_name = mp4_url.split("/")[len(mp4_url.split("/"))-1].split('?')[0]

print("Storing video in ..... " + file_name)


r = requests.get(mp4_url)

with open(file_name,'wb') as f:
  f.write(r.content)

print("Download Process finished")