From 5d0058492c07d3f89f46ccfd2b8e33849f8bd30e Mon Sep 17 00:00:00 2001
From: Bernardas <bernardas.alisauskas@gmail.com>
Date: Tue, 23 Aug 2016 16:54:10 +0000
Subject: [PATCH] add media pipeline settings to enable redirection and
 handling of certain http statuses

---
 scrapy/pipelines/files.py |  2 +-
 scrapy/pipelines/media.py | 34 +++++++++++++++++++++++++++++++---
 2 files changed, 32 insertions(+), 4 deletions(-)

diff --git a/scrapy/pipelines/files.py b/scrapy/pipelines/files.py
index 843b4d3ec..4ae7e1d89 100644
--- a/scrapy/pipelines/files.py
+++ b/scrapy/pipelines/files.py
@@ -249,7 +249,7 @@ class FilesPipeline(MediaPipeline):
             resolve('FILES_RESULT_FIELD'), self.FILES_RESULT_FIELD
         )
 
-        super(FilesPipeline, self).__init__(download_func=download_func)
+        super(FilesPipeline, self).__init__(download_func=download_func, settings=settings)
 
     @classmethod
     def from_settings(cls, settings):
diff --git a/scrapy/pipelines/media.py b/scrapy/pipelines/media.py
index 57f70499e..4177d294f 100644
--- a/scrapy/pipelines/media.py
+++ b/scrapy/pipelines/media.py
@@ -1,5 +1,6 @@
 from __future__ import print_function
 
+import functools
 import logging
 from collections import defaultdict
 from twisted.internet.defer import Deferred, DeferredList
@@ -16,6 +17,7 @@ logger = logging.getLogger(__name__)
 class MediaPipeline(object):
 
     LOG_FAILED_RESULTS = True
+    ALLOW_REDIRECTS = False
 
     class SpiderInfo(object):
         def __init__(self, spider):
@@ -24,9 +26,16 @@ class MediaPipeline(object):
             self.downloaded = {}
             self.waiting = defaultdict(list)
 
-    def __init__(self, download_func=None):
+    def __init__(self, download_func=None, settings=None):
         self.download_func = download_func
-
+        resolve = functools.partial(self._key_for_pipe,
+                                    base_class_name="MediaPipeline")
+        self.allow_redirects = settings.getbool(
+            resolve('MEDIA_ALLOW_REDIRECTS'), self.ALLOW_REDIRECTS
+        )
+        self.allow_httpstatus_list = settings.getlist(
+            resolve('MEDIA_HTTPSTATUS_LIST'), []
+        )
 
     def _key_for_pipe(self, key, base_class_name=None,
                       settings=None):
@@ -93,6 +102,25 @@ class MediaPipeline(object):
         )
         return dfd.addBoth(lambda _: wad)  # it must return wad at last
 
+    def _modify_media_request(self, request):
+        httpstatus_list = []
+        if self.allow_httpstatus_list:
+            httpstatus_list = self.allow_httpstatus_list
+        elif self.allow_redirects:
+            if not httpstatus_list:
+                httpstatus_list = list(range(0, 300)) + list(range(400, 1000))
+            else:
+                for i in range(300, 400):
+                    try:
+                        httpstatus_list.remove(i)
+                    except ValueError:
+                        pass
+        if httpstatus_list:
+            request.meta['handle_httpstatus_list'] = httpstatus_list
+        else:
+            request.meta['handle_httpstatus_all'] = True
+        return request
+
     def _check_media_to_download(self, result, request, info):
         if result is not None:
             return result
@@ -103,7 +131,7 @@ class MediaPipeline(object):
                 callback=self.media_downloaded, callbackArgs=(request, info),
                 errback=self.media_failed, errbackArgs=(request, info))
         else:
-            request.meta['handle_httpstatus_all'] = True
+            request = self._modify_media_request(request)
             dfd = self.crawler.engine.download(request, info.spider)
             dfd.addCallbacks(
                 callback=self.media_downloaded, callbackArgs=(request, info),