From 3803f6764516e00bbea24055a418c5902a17c350 Mon Sep 17 00:00:00 2001
From: Daniel Grana <dangra@gmail.com>
Date: Fri, 12 Sep 2008 21:55:14 +0000
Subject: [PATCH] mediamiddleware: bugfixes and remove prints

--HG--
extra : convert_revision : svn%3Ab85faa78-f9eb-468e-a121-7cced6da292c%40229
---
 scrapy/trunk/scrapy/contrib/pipeline/media.py | 29 +++++--------------
 1 file changed, 8 insertions(+), 21 deletions(-)

diff --git a/scrapy/trunk/scrapy/contrib/pipeline/media.py b/scrapy/trunk/scrapy/contrib/pipeline/media.py
index df12233e2..6346ffae3 100644
--- a/scrapy/trunk/scrapy/contrib/pipeline/media.py
+++ b/scrapy/trunk/scrapy/contrib/pipeline/media.py
@@ -1,8 +1,5 @@
-from __future__ import with_statement
-
 from twisted.internet import defer
 from twisted.python import failure
-from pprint import pprint
 
 from scrapy.core import log
 from scrapy.http import Request
@@ -14,6 +11,7 @@ from scrapy.stats import stats
 from scrapy.utils.misc import chain_deferred, mustbe_deferred
 from scrapy.conf import settings
 
+
 class DomainInfo(object):
     def __init__(self, domain):
         self.domain = domain
@@ -32,7 +30,7 @@ class MediaPipeline(object):
         info = self.cache[domain]
 
         ulist = []
-        for url in urls:
+        for url in urls or ():
             dfd = self._enqueue(url, info)
             dfd.addCallbacks(
                     callback=self.new_item_media,
@@ -48,30 +46,27 @@ class MediaPipeline(object):
 
     def _enqueue(self, url, info):
         wad = defer.Deferred()
-        wad.addBoth(lambda _: pprint(_))
 
         request = Request(url=url)
         fp = request.fingerprint()
         waiting = info.waiting.setdefault(fp, []).append(wad)
 
-        if fp in info.downloading:
-            return
-
-        dwld = scrapyengine.schedule(request, info.spider, priority=0)
-        dwld.addCallbacks(self.media_downloaded, self.media_failure)
-        dwld.addBoth(self._download_finished, info, fp)
-        info.downloading[fp] = (request, dwld)
+        if fp not in info.downloading:
+            dwld = scrapyengine.schedule(request, info.spider, priority=0)
+            dwld.addCallbacks(self.media_downloaded, self.media_failure)
+            dwld.addBoth(self._download_finished, info, fp)
+            info.downloading[fp] = (request, dwld)
         return wad
 
     def _download_finished(self, result, info, fp):
         del info.downloading[fp]
         info.downloaded[fp] = result # cache result
         waiting = info.waiting[fp]
+        del info.waiting[fp]
 
         isfail = isinstance(result, failure.Failure)
         for wad in waiting:
             tocall = wad.errback if isfail else wad.callback
-            pprint(tocall)
             tocall(result)
         return result
 
@@ -82,37 +77,29 @@ class MediaPipeline(object):
         self.cache[domain] = DomainInfo(domain)
 
     def close_domain(self, domain):
-        print '##### closing'
         del self.cache[domain]
 
     ### Overradiable Interface
 
     def get_urls_from_item(self, item):
-        print '##### get_urls_from_item'
         return item.image_urls
 
     def media_to_download(self, url):
-        print '##### media_to_download'
         pass
 
     def media_downloaded(self, response):
-        print '##### media_downloaded'
         pass
 
     def media_failure(self, _failure):
-        print '##### media_failure'
         return _failure
 
     def new_item_media(self, result, item):
-        print '##### new_item_media'
         pass
 
     def failed_item_media(self, _failure, item):
-        print '##### failed_item_media'
         pass
 
     def item_completed(self, item):
-        print '##### item_completed'
         return item