Created
July 27, 2012 02:08
-
-
Save rgegriff/3185805 to your computer and use it in GitHub Desktop.
A script to download all of the epubs from a calibre library
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
#!/bin/env python | |
#python scrape.py "http://some.url.nyud.net/" | |
import urllib, re, sys, time, shutil | |
url = sys.argv[1] | |
search_str = "mobile?search=;order=descending;sort=author;num=10000000;start=1" | |
epub_list = [l for l in re.findall('href=[\"\'](.[^\"\']+)[\"\']', urllib.urlopen(url+search_str).read(), re.I) if l[-4:] == "epub"] | |
if len(sys.argv) == 3: | |
print "RESUMING AT #"+str(sys.argv[2]) | |
count = int(sys.argv[2]) | |
else: | |
count = 0 | |
total = len(epub_list)-1 | |
while count < total: | |
for book_url in epub_list[count:]: | |
book_fname = urllib.unquote(book_url.split('/')[-1]) | |
print "Downloading ",count,"/",total, book_fname | |
try: | |
start = time.time() | |
with open(book_fname ,"wb") as f: | |
shutil.copyfileobj(urllib.urlopen(url + book_url),f ) | |
f.close() | |
end = time.time() | |
print "Done!........ ", end - start | |
count += 1 | |
except IOError: | |
print "Network Error... Retrying." | |
break |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment