|
|
@ -1,11 +1,34 @@ |
|
|
|
#!/usr/bin/python |
|
|
|
|
|
|
|
import re, urllib, urllib2 |
|
|
|
import re, urllib, urllib2, argparse, os |
|
|
|
|
|
|
|
parser = argparse.ArgumentParser(description='Downloads all full-size images in an arbitrary 4chan thread.') |
|
|
|
|
|
|
|
parser.add_argument('urllist', metavar='url', type=str, nargs=1, |
|
|
|
help='the URL of the thread') |
|
|
|
parser.add_argument('-n', '--newdir', dest='newdir', action='store_true', |
|
|
|
help='create a new directory for this thread in the current directory') |
|
|
|
|
|
|
|
args = parser.parse_args() |
|
|
|
options = vars(args) |
|
|
|
|
|
|
|
regex = 'href="(\/\/images\.4chan\.org\/b\/src\/[0-9]+\.[a-z]+)"' |
|
|
|
url = 'http://boards.4chan.org/b/res/400860795' |
|
|
|
url = options['urllist'][0] |
|
|
|
|
|
|
|
try: |
|
|
|
page = urllib2.urlopen(url).read() |
|
|
|
except ValueError: |
|
|
|
print "That does not look like a valid URL." |
|
|
|
exit(1) |
|
|
|
|
|
|
|
if options['newdir'] == True: |
|
|
|
thread_id = url.split('/')[-1] |
|
|
|
target_dir = "%s/" % thread_id |
|
|
|
|
|
|
|
page = urllib2.urlopen(url).read() |
|
|
|
if not os.path.exists(thread_id): |
|
|
|
os.makedirs(thread_id) |
|
|
|
else: |
|
|
|
target_dir = "" |
|
|
|
|
|
|
|
search = re.compile(regex) |
|
|
|
matches = search.finditer(page) |
|
|
@ -24,6 +47,7 @@ print "Parsed thread. Total images: %d" % total |
|
|
|
for downloadurl in urls: |
|
|
|
downloadurl = "http:%s" % downloadurl |
|
|
|
filename = downloadurl.split('/')[-1] |
|
|
|
urllib.urlretrieve(downloadurl, filename) |
|
|
|
path = target_dir + filename |
|
|
|
urllib.urlretrieve(downloadurl, path) |
|
|
|
print "Downloaded %s (%d/%d)." % (filename, current, total) |
|
|
|
current += 1 |
|
|
|