Created
June 30, 2012 18:38
-
-
Save minitech/3025010 to your computer and use it in GitHub Desktop.
Manga Downloader
This file contains hidden or 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
# My first Python program. | |
# Feedback please; anything non-Pythonic here? | |
manga = raw_input("Enter the slug name of the manga: ") | |
while True: | |
try: | |
start = int(raw_input("Start chapter: ")) | |
break | |
except ValueError: | |
pass | |
while True: | |
try: | |
end = int(raw_input("End chapter: ")) | |
break | |
except ValueError: | |
pass | |
print("Getting chapters from %d to %d of %s." % (start, end, manga)) | |
import urllib2 | |
import re | |
for chapter in xrange(start, end + 1): | |
page = 0 | |
try: | |
while True: | |
page += 1 | |
print("Fetching page %d of chapter %d..." % (page, chapter)) | |
handle = urllib2.urlopen("http://manga.animea.net/%s-chapter-%d-page-%d.html" % (manga, chapter, page)) | |
content = handle.read() | |
handle.close() | |
m = re.search(r'src="(.+?)"[^>]+class="mangaimg"', content) | |
if m is not None: | |
url = m.group(1) | |
m = re.search(r'\.([a-zA-Z]+)$', url) | |
if m is None: | |
break | |
local = open("%s-%d-%d.%s" % (manga, chapter, page, m.group(1)), 'w') | |
handle = urllib2.urlopen(url) | |
local.write(handle.read()) | |
handle.close() | |
local.close() | |
else: | |
print("Failed to find data for page %d." % (page,)) | |
break | |
except urllib2.URLError: | |
print("Got a URLError trying to fetch page %d of chapter %d" % (page, chapter)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment