X-Git-Url: https://git.llucax.com/software/subdivxget.git/blobdiff_plain/8c1a098a0ed392dfb253e7fecd46353eea7e371a..24b7c11c0eaeb895bf4c4c1b16572160aa529d9d:/subdivxget

diff --git a/subdivxget b/subdivxget
index 4ebcca5..954b80a 100755
--- a/subdivxget
+++ b/subdivxget
@@ -1,10 +1,20 @@
 #!/usr/bin/env python
 
 import sys
-import urllib
+if sys.version_info[0] < 3:
+	from HTMLParser import HTMLParser
+	from urllib import urlopen, urlretrieve, urlencode
+	def get_encoding(info):
+		return info.getparam('charset')
+
+else:
+	from html.parser import HTMLParser
+	from urllib.request import urlopen, urlretrieve
+	from urllib.parse import urlencode
+	def get_encoding(info):
+		return info.get_content_charset('ascii')
 import zipfile
 import subprocess
-import HTMLParser
 
 class SubDivXQuery:
 	def __init__(self, to_search, page_number):
@@ -22,22 +32,22 @@ class SubDivXQuery:
 	@property
 	def url(self):
 		return 'http://%s%s?%s' % (self.host, self.page,
-				urllib.urlencode(self.query))
+				urlencode(self.query))
 	@property
 	def page_uri(self):
-		return self.page + '?' + urllib.urlencode(self.query)
+		return self.page + '?' + urlencode(self.query)
 	@property
 	def down_uri(self):
 		return 'http://' + self.host + self.down_page
 
 
-class SubDivXHTMLParser(HTMLParser.HTMLParser):
+class SubDivXHTMLParser(HTMLParser):
 
 	IDLE = 1
 	HEADER = 2
 
 	def __init__(self, down_uri):
-		HTMLParser.HTMLParser.__init__(self)
+		HTMLParser.__init__(self)
 		self.down_uri = down_uri
 		self.depth = 0
 		self.parsing = False
@@ -118,16 +128,71 @@ class SubDivXHTMLParser(HTMLParser.HTMLParser):
 			self.cur[self.attr] = ''
 
 
+def filter_subtitles(subs, filters):
+	def is_good(sub, filter):
+		def is_any_good(sub, filter):
+			for value in sub.values():
+				if value.lower().find(filter) >= 0:
+					return True
+
+		field = None
+		if len(filter) > 2 and filter[1] == ':':
+			field = filter[0]
+			filter = filter[2:]
+		filter = filter.lower()
+
+		if field is None:
+			return is_any_good(sub, filter)
+		elif field == 't':
+			key = 'titulo'
+		elif field == 'd':
+			key = 'desc'
+		elif field == 'a':
+			key = 'autor'
+		elif field == 'f':
+			key = 'formato'
+		elif field == 'c':
+			key = 'comentarios'
+		elif field == 'C':
+			key = 'cds'
+		elif field == 'F':
+			key = 'fecha'
+		elif field == 'D':
+			key = 'downloads'
+		else:
+			# Not a recognizer field identifier, use the raw filter
+			return is_any_good(sub, field + ':' + filter)
+
+		return sub[key].lower().find(filter) >= 0
+
+	if not filters:
+		return subs
+
+	result = []
+	for sub in subs:
+		for filter in filters:
+			if not is_good(sub, filter):
+				break
+		else:
+			result.append(sub)
+	return result
+
+
 def subdivx_get_subs(query_str):
 	page_number = 1
 	subs = []
 	while True:
 		query = SubDivXQuery(query_str, page_number)
-		url = urllib.urlopen(query.url)
+		url = urlopen(query.url)
 		parser = SubDivXHTMLParser(query.down_uri)
 
+		try:
+			encoding = get_encoding(url.info())
+		except:
+			encoding = 'ascii'
+
 		for line in url:
-			parser.feed(line)
+			parser.feed(line.decode(encoding))
 
 		url.close()
 
@@ -140,37 +205,41 @@ def subdivx_get_subs(query_str):
 	return sorted(subs, key=lambda s: int(s['downloads']), reverse=True)
 
 
-def get_subs(query_str):
+def get_subs(query_str, filters):
+	sub_exts = ('.srt', '.sub')
 	zip_exts = ('application/zip',)
 	rar_exts = ('application/rar', 'application/x-rar-compressed')
 
-	for sub in subdivx_get_subs(query_str):
-		print '''\
-	- %(titulo)s (%(autor)s - %(fecha)s - %(downloads)s - %(comentarios)s)
-	  %(desc)s
-		DOWNLOADING ...
-	''' % sub
-		fname, headers = urllib.urlretrieve(sub['url'])
+	subs = subdivx_get_subs(query_str)
+	subs = filter_subtitles(subs, filters)
+
+	for sub in subs:
+		print('''\
+- %(titulo)s (%(autor)s - %(fecha)s - %(downloads)s - %(comentarios)s)
+  %(desc)s
+	DOWNLOADING ...
+''' % sub)
+		continue
+		fname, headers = urlretrieve(sub['url'])
 		if 'Content-Type' in headers:
 			if headers['Content-Type'] in zip_exts:
 				z = zipfile.ZipFile(fname, 'r')
 				z.printdir()
 				for fn in z.namelist():
-					if fn.endswith('.srt') or fn.endswith('.sub'):
+					if fn.endswith(sub_exts):
 						if '..' in fn or fn.startswith('/'):
-							print 'Dangerous file name:', fn
+							print('Dangerous file name:', fn)
 							continue
-						print 'Extracting', fn, '...'
+						print('Extracting', fn, '...')
 						z.extract(fn)
 			elif headers['Content-Type'] in rar_exts:
 				if subprocess.call(['rar', 'x', fname]) != 0:
-					print 'Error unraring file %s' % fname
+					print('Error unraring file %s' % fname)
 			else:
-				print 'Unrecognized file type:', headers['Content-Type']
+				print('Unrecognized file type:', headers['Content-Type'])
 		else:
-			print 'No Content-Type!'
+			print('No Content-Type!')
 
 
-for q in sys.argv[1:]:
-	get_subs(q)
+get_subs(sys.argv[1], sys.argv[2:])