Created
January 19, 2012 00:37
-
-
Save melpomene/1636776 to your computer and use it in GitHub Desktop.
Script to download all Amigara episodes. [ugly hack]
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import urllib | |
import requests | |
from BeautifulSoup import BeautifulSoup | |
""" CHANGE PATH TO DIRECTORY IN WHICH TO SAVE FILES AND ALL IS WELL""" | |
PATH = "path/to/file" | |
url = "http://brasscockroach.com/h4ll0w33n2007/manga/Amigara-Full/Amigara-0.html" | |
img_url = "http://brasscockroach.com/h4ll0w33n2007/manga/Amigara-Full/" | |
r = requests.get(url) | |
count = 0 | |
old = "t" | |
last_url = "" | |
new_url = url | |
while r.status_code == 200: | |
content = r.content | |
soup = BeautifulSoup(content) | |
img = soup.find('img') | |
img_path = img_url + str(urllib.quote(str(img['src']))) | |
f = open(PATH+ str(count) + ".png", "w") | |
i = requests.get(img_path) | |
f.write(i.content) | |
n = soup.findAll('a') | |
new_url = img_url + str(n[1]['href']) | |
if new_url == old: | |
print "All img downloaded" | |
exit() | |
print new_url | |
r = requests.get(new_url) | |
old = last_url | |
last_url = new_url | |
count+=1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment