From c79b74764e72a29ce82d3ec489c2433e8ad6ba20 Mon Sep 17 00:00:00 2001
From: Leandro Lucarella <luca@llucax.com.ar>
Date: Sat, 14 Jul 2012 20:09:46 +0200
Subject: [PATCH] Get all available pages

SubDivX pages the results, so we keep downloading the next page to get
all the available results until we can't find any subtitles in a page.
---
 subdivxget | 30 +++++++++++++++++++++---------
 1 file changed, 21 insertions(+), 9 deletions(-)

diff --git a/subdivxget b/subdivxget
index aaa3d44..5f67edb 100755
--- a/subdivxget
+++ b/subdivxget
@@ -7,12 +7,13 @@ import subprocess
 import HTMLParser
 
 class SubDivXQuery:
-	def __init__(self, to_search):
+	def __init__(self, to_search, page_number):
 		self.host = "www.subdivx.com"
 		self.page = "/index.php"
 		self.down_page = "/bajar.php"
 		self.query = dict(
 			buscar = to_search,
+			pg = page_number,
 			accion = 5,
 			masdesc = '',
 			subtitulos = 1,
@@ -85,22 +86,33 @@ class SubDivXHTMLParser(HTMLParser.HTMLParser):
 				self.attr = 'fecha'
 
 
-def get_subs(query_str):
-	query = SubDivXQuery(query_str)
+def subdivx_get_subs(query_str):
+	page_number = 1
+	subs = []
+	while True:
+		query = SubDivXQuery(query_str, page_number)
+		url = urllib.urlopen(query.url)
+		parser = SubDivXHTMLParser(query.down_uri)
+
+		for line in url:
+			parser.feed(line)
 
-	url = urllib.urlopen(query.url)
+		url.close()
 
-	parser = SubDivXHTMLParser(query.down_uri)
+		if not parser.subs:
+			break
 
-	for line in url:
-		parser.feed(line)
+		subs.extend(parser.subs)
+		page_number += 1
 
-	url.close()
+	return sorted(subs, key=lambda s: int(s['downloads']), reverse=True)
 
+
+def get_subs(query_str):
 	zip_exts = ('application/zip',)
 	rar_exts = ('application/rar', 'application/x-rar-compressed')
 
-	for sub in sorted(parser.subs, key=lambda s: int(s['downloads']), reverse=True):
+	for sub in subdivx_get_subs(query_str):
 		print '''\
 	- %(title)s (%(autor)s - %(fecha)s - %(downloads)s - %(comentarios)s)
 	  %(desc)s
-- 
2.43.0