joepie91/4chandownloader
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Actual file downloading and regex fix

Browse source
This commit is contained in:
Sven Slootweg 2012-05-21 00:03:18 +02:00
parent c738ec4a6c
commit 8d406c2582
1 changed files with 13 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
4c Normal file → Executable file
View file

@ -1,8 +1,8 @@
#!/usr/bin/python
import re, urllib2
import re, urllib, urllib2
regex = 'href="(\/\/images\.4chan\.org\/b\/src\/[0-9]+\.jpg)"'
regex = 'href="(\/\/images\.4chan\.org\/b\/src\/[0-9]+\.[a-z]+)"'
url = 'http://boards.4chan.org/b/res/400860795'
page = urllib2.urlopen(url).read()
@ -16,4 +16,14 @@ for match in matches:
if match.group(1) not in urls:
urls.append(match.group(1))
print urls
current = 1
total = len(urls)
print "Parsed thread. Total images: %d" % total
for downloadurl in urls:
downloadurl = "http:%s" % downloadurl
filename = downloadurl.split('/')[-1]
urllib.urlretrieve(downloadurl, filename)
print "Downloaded %s (%d/%d)." % (filename, current, total)
current += 1