blob: 58ce3d9223dc5b56cfbdfaaaaf2ff7b46a0eb682 (
plain)
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
67
68
69
|
#!/bin/python
"""A download a video from arte.tv website."""
from bs4 import BeautifulSoup
from urllib.request import urlopen, unquote, urlretrieve
import re, json, sys
def download(url):
content = urlopen(url)
json_data = json.loads(content.read().decode())
name = json_data['videoJsonPlayer']['VTI']
url = json_data['videoJsonPlayer']['VSR']['HTTPS_SQ_1']['url']
name=name.replace('/', '-')+".mp4"
try:
print("Downloading '"+name+"'...")
urlretrieve(url, name)
print("\nDownload completed")
except Exception as e:
print(e)
def main():
if len(sys.argv) != 2:
print("Usage:")
print(" "+sys.argv[0]+" <arte.tv_link>")
print("Example:")
print(" "+sys.argv[0]+" https://www.arte.tv/fr/videos/051868-000-A/liberte-egalite-indemnites-vers-un-revenu-universel/")
sys.exit(0)
url = sys.argv[1]
programId = re.findall('[0-9A-Z]{6}-[0-9A-Z]{3}-[0-9A-Z]', url)
collection = re.findall('[0-9A-Z]{2}-[0-9A-Z]{6}', url)
if len(programId) > 0:
url = "https://api.arte.tv/api/player/v1/config/en/{}".format(programId[0])
download(url)
elif len(collection) > 0:
content = urlopen(url)
soup = BeautifulSoup(content, "lxml")
links = soup.find_all("a", {"class": "next-teaser__link"}, href=True)
for link in links:
programId = re.findall('[0-9A-Z]{6}-[0-9A-Z]{3}-[0-9A-Z]', link['href'])
url = "https://api.arte.tv/api/player/v1/config/en/{}".format(programId[0])
download(url)
if not links:
url = "https://api.arte.tv/api/player/v1/collectionData/en/{}".format(collection[0])
content = urlopen(url)
json_data = json.loads(content.read().decode())
videos = json_data['videos']
for video in videos:
url = "https://api.arte.tv/api/player/v1/config/en/{}".format(video['programId'])
download(url)
else:
print("This is not a valid url")
if __name__ == "__main__":
main()
|
