blob: f1ebbab64d3a20bd5c16f76c67202bf5107ca873 (
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
|
#!/usr/bin/python
# -*-coding:utf-8 -*
import re
import os
import sys
import tempfile
sujet = []
sujetT = []
new_file, filename = tempfile.mkstemp()
if not new_file:
filename = "index.html"
os.system("wget " + sys.argv[1] + " -O " + filename + " -N -q")
os.system("sed -i 's/<\\/a>/<\\/a>\\n/g' " + filename)
regex = '<span class="filesize">(File : |File)<a href="(.*?)" \
target="_blank">(.*?)</a>'
regex = '<a class="fileThumb" href="(.*?)" target="_blank">'
dumpDir = "dump"
if len(sys.argv) >= 3:
dumpDir = sys.argv[2]
os.system("mkdir -p " + dumpDir)
with open(filename, 'r') as f:
for line in f:
yes = re.search(regex, line)
if yes:
print(yes.group(1))
sujetT.append([yes.group(1)])
print("Téléchargement de : " + yes.group(1))
os.system("wget " + 'http:' + yes.group(1) + " -N -q")
os.system("mv " + yes.group(1)[yes.group(1).rfind('/')+1:] + " " +
dumpDir)
os.remove(filename)
|