Accept multiple threads as input arguments

master
Sven Slootweg 13 years ago
parent 7d578cdea3
commit df175d7715

32
4c

@ -7,7 +7,7 @@ import re, urllib, urllib2, argparse, os
parser = argparse.ArgumentParser(description='Downloads all full-size images in an arbitrary 4chan thread.') parser = argparse.ArgumentParser(description='Downloads all full-size images in an arbitrary 4chan thread.')
parser.add_argument('urllist', metavar='url', type=str, nargs=1, parser.add_argument('urllist', metavar='url', type=str, nargs='+',
help='the URL of the thread') help='the URL of the thread')
parser.add_argument('-n', '--newdir', dest='newdir', action='store_true', parser.add_argument('-n', '--newdir', dest='newdir', action='store_true',
help='create a new directory for this thread in the current directory') help='create a new directory for this thread in the current directory')
@ -18,41 +18,43 @@ args = parser.parse_args()
options = vars(args) options = vars(args)
regex = 'href="(\/\/images\.4chan\.org\/b\/src\/[0-9]+\.[a-z]+)"' regex = 'href="(\/\/images\.4chan\.org\/b\/src\/[0-9]+\.[a-z]+)"'
url = options['urllist'][0]
try: for url in options['urllist']:
print "Thread URL: %s" % url
try:
page = urllib2.urlopen(url).read() page = urllib2.urlopen(url).read()
except ValueError: except ValueError:
print "That does not look like a valid URL." print "That does not look like a valid URL."
exit(1) exit(1)
except urllib2.HTTPError: except urllib2.HTTPError:
print "The given URL returns a HTTP 404 status code - the thread may have died." print "The given URL returns a HTTP 404 status code - the thread may have died."
exit(1) exit(1)
if options['newdir'] == True: if options['newdir'] == True:
thread_id = url.split('/')[-1] thread_id = url.split('/')[-1]
target_dir = "%s/" % thread_id target_dir = "%s/" % thread_id
if not os.path.exists(thread_id): if not os.path.exists(thread_id):
os.makedirs(thread_id) os.makedirs(thread_id)
else: else:
target_dir = "" target_dir = ""
search = re.compile(regex) search = re.compile(regex)
matches = search.finditer(page) matches = search.finditer(page)
urls = [] urls = []
for match in matches: for match in matches:
if match.group(1) not in urls: if match.group(1) not in urls:
urls.append(match.group(1)) urls.append(match.group(1))
current = 1 current = 1
total = len(urls) total = len(urls)
print "Parsed thread. Total images: %d" % total print "Parsed thread. Total images: %d" % total
for downloadurl in urls: for downloadurl in urls:
downloadurl = "http:%s" % downloadurl downloadurl = "http:%s" % downloadurl
filename = downloadurl.split('/')[-1] filename = downloadurl.split('/')[-1]
path = target_dir + filename path = target_dir + filename

Loading…
Cancel
Save