opensubtitles

scrapeit/__init__.py

@@ -9,6 +9,6 @@ import mininova
 import thepiratebay
 import torrent
 import rottentomatoes
-
+import opensubtitles
 
 __version__ = '1.0.0'

scrapeit/btjunkie.py

@@ -1,5 +1,5 @@
-# -*- Mode: Python; -*-
 # -*- coding: utf-8 -*-
+# -*- Mode: Python; -*-
 # vi:si:et:sw=2:sts=2:ts=2
 
 from urllib import quote

scrapeit/opensubtitles.py

@@ -0,0 +1,44 @@
+# -*- coding: utf-8 -*-
+# -*- Mode: Python; -*-
+# vi:si:et:sw=2:sts=2:ts=2
+
+from utils import read_url
+import feedparser
+import StringIP
+import zipfile
+
+def searchSubtitlesByIMDb(imdb, parts = 1, language = "eng"):
+  url = "http://www.opensubtitles.org/en/search/sublanguageid-%s/subsumcd-%s/subformat-srt/imdbid-%s/rss_2_00" % (language, parts, imdb)
+  data = read_url(url)
+  fd = feedparser.parse(data)
+  os_id = None
+  if fd.entries:
+    link = fd.entries[0]['links'][0]['href']
+    os_id = re.compile('subtitles/(.*?)/').findall(link)
+    if os_id:
+      os_id = os_id[0]
+  return os_id
+
+def getZipFileLink(opensubtitle_id):
+  return "http://www.opensubtitles.org/en/download/sub/%s" % opensubtitle_id
+
+def downloadSubtitle(zip_link):
+  srts ={}
+  zip = StringIO.StringIO()
+  zip.write(read_url(zip_link))
+  zfile = zipfile.ZipFile(zip)
+  files = zfile.namelist()
+  def is_not_nfo(file): return not file.endswith('nfo')
+  files = filter(is_not_nfo, files)
+  if len(files) == 1:
+    srts[files[0]] = zfile.read(files[0])
+  else:
+    for f in zfile.namelist():
+      if f.endswith('.srt'):
+        srts[f] = zfile.read(f)
+  return srts
+
+
+def downloadSubtitleByID(opensubtitle_id):
+  zip_file = getZipFileLink(opensubtitle_id)
+  return downloadSubtitle(zip_file)