X-Git-Url: https://git.llucax.com/software/subdivxget.git/blobdiff_plain/aa52c87e353921174d3b3874c2a261f175970a8c..44c70b16fa26aad38244f816c2b0ad3c3a170ecc:/subdivxget

diff --git a/subdivxget b/subdivxget
index 5c5cc7a..1aecc66 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,
@@ -29,8 +30,6 @@ class SubDivXQuery:
 	def down_uri(self):
 		return 'http://' + self.host + self.down_page
 
-class Subtitle:
-	pass
 
 class SubDivXHTMLParser(HTMLParser.HTMLParser):
 
@@ -48,7 +47,6 @@ class SubDivXHTMLParser(HTMLParser.HTMLParser):
 	def handle_starttag(self, tag, attrs):
 		attrs = dict(attrs)
 		if tag == 'div' and attrs.get('id') == 'menu_detalle_buscador':
-			#self.cur = Subtitle()
 			self.cur = dict()
 			self.subs.append(self.cur)
 			self.parsing = True
@@ -74,38 +72,48 @@ class SubDivXHTMLParser(HTMLParser.HTMLParser):
 			self.parsing = False
 
 	def handle_data(self, data):
-		if self.parsing:
-			data = data.strip()
-			if self.attr is not None and data:
-				self.cur[self.attr] = data
-				self.attr = None
-				#self.cur[self.attr] = self.cur.get(self.attr, '') + data.strip()
-				#setattr(self.cur, self.attr, data.strip())
-			elif data in ('Downloads:', 'Cds:', 'Comentarios:',
-					'Formato:'):
-				self.attr = data[:-1].lower()
-			elif data == 'Subido por:':
-				self.attr = 'autor'
-			elif data == 'el':
-				self.attr = 'fecha'
+		if not self.parsing:
+			return
+		data = data.strip()
+		if self.attr is not None and data:
+			self.cur[self.attr] = data
+			self.attr = None
+		elif data in ('Downloads:', 'Cds:', 'Comentarios:',
+				'Formato:'):
+			self.attr = data[:-1].lower()
+		elif data == 'Subido por:':
+			self.attr = 'autor'
+		elif data == 'el':
+			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)
 
-	url = urllib.urlopen(query.url)
+		for line in url:
+			parser.feed(line)
 
-	parser = SubDivXHTMLParser(query.down_uri)
+		url.close()
 
-	for line in url:
-		parser.feed(line)
+		if not parser.subs:
+			break
 
-	url.close()
+		subs.extend(parser.subs)
+		page_number += 1
 
+	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