|
|
@ -1,4 +1,4 @@ |
|
|
|
#VERSION: 1.00 |
|
|
|
#VERSION: 1.10 |
|
|
|
#AUTHORS: Fabien Devaux (fab@gnux.info) |
|
|
|
#AUTHORS: Fabien Devaux (fab@gnux.info) |
|
|
|
from novaprinter import prettyPrinter |
|
|
|
from novaprinter import prettyPrinter |
|
|
|
import urllib |
|
|
|
import urllib |
|
|
@ -26,9 +26,13 @@ class mininova(object): |
|
|
|
return txt.toxml() |
|
|
|
return txt.toxml() |
|
|
|
else: |
|
|
|
else: |
|
|
|
return ''.join([ get_text(n) for n in txt.childNodes]) |
|
|
|
return ''.join([ get_text(n) for n in txt.childNodes]) |
|
|
|
dat = urllib.urlopen(self.url+'/search/%s/seeds'%(what,)).read().decode('utf-8', 'replace') |
|
|
|
page = 1 |
|
|
|
|
|
|
|
while True: |
|
|
|
|
|
|
|
res = 0 |
|
|
|
|
|
|
|
dat = urllib.urlopen(self.url+'/search/%s/seeds/%d'%(what, page)).read().decode('utf-8', 'replace') |
|
|
|
dat = re.sub("<a href=\"http://www.boardreader.com/index.php.*\"", "<a href=\"plop\"", dat) |
|
|
|
dat = re.sub("<a href=\"http://www.boardreader.com/index.php.*\"", "<a href=\"plop\"", dat) |
|
|
|
dat = re.sub("<=", "<=", dat) |
|
|
|
dat = re.sub("<=", "<=", dat) |
|
|
|
|
|
|
|
dat = re.sub("&\s", "& ", dat) |
|
|
|
x = minidom.parseString(dat.encode('utf-8', 'replace')) |
|
|
|
x = minidom.parseString(dat.encode('utf-8', 'replace')) |
|
|
|
table = x.getElementsByTagName('table').item(0) |
|
|
|
table = x.getElementsByTagName('table').item(0) |
|
|
|
if not table: return |
|
|
|
if not table: return |
|
|
@ -48,3 +52,7 @@ class mininova(object): |
|
|
|
if not vals['leech'].isdigit(): |
|
|
|
if not vals['leech'].isdigit(): |
|
|
|
vals['leech'] = 0 |
|
|
|
vals['leech'] = 0 |
|
|
|
prettyPrinter(vals) |
|
|
|
prettyPrinter(vals) |
|
|
|
|
|
|
|
res = res + 1 |
|
|
|
|
|
|
|
if res == 0: |
|
|
|
|
|
|
|
break |
|
|
|
|
|
|
|
page = page +1 |
|
|
|