Merge pull request #4486 from ilias-ant/add-file-status-on-media-pipelines-file-info

Add status (downloaded, uptodate) to files information

docs/topics/media-pipeline.rst

@@ -50,7 +50,7 @@ this:
 4. When the files are downloaded, another field (``files``) will be populated
    with the results. This field will contain a list of dicts with information
    about the downloaded files, such as the downloaded path, the original
-   scraped url (taken from the ``file_urls`` field) , and the file checksum.
+   scraped url (taken from the ``file_urls`` field), the file checksum and the file status.
    The files in the list of the ``files`` field will retain the same order of
    the original ``file_urls`` field. If some file failed downloading, an
    error will be logged and the file won't be present in the ``files`` field.
@@ -470,6 +470,14 @@ See here the methods that you can override in your custom Files Pipeline:
 
         * ``checksum`` - a `MD5 hash`_ of the image contents
 
+        * ``status`` - the file status indication. It can be one of the following:
+
+          * ``downloaded`` - file was downloaded.
+          * ``uptodate`` - file was not downloaded, as it was downloaded recently,
+            according to the file expiration policy.
+          * ``cached`` - file was already scheduled for download, by another item
+            sharing the same file.
+
       The list of tuples received by :meth:`~item_completed` is
       guaranteed to retain the same order of the requests returned from the
       :meth:`~get_media_requests` method.
@@ -479,7 +487,8 @@ See here the methods that you can override in your custom Files Pipeline:
           [(True,
             {'checksum': '2b00042f7481c7b056c4b410d28f33cf',
              'path': 'full/0a79c461a4062ac383dc4fade7bc09f1384a3910.jpg',
-             'url': 'http://www.example.com/files/product1.pdf'}),
+             'url': 'http://www.example.com/files/product1.pdf',
+             'status': 'downloaded'}),
            (False,
             Failure(...))]
 

scrapy/pipelines/files.py

@@ -432,7 +432,7 @@ class FilesPipeline(MediaPipeline):
             self.inc_stats(info.spider, 'uptodate')
 
             checksum = result.get('checksum', None)
-            return {'url': request.url, 'path': path, 'checksum': checksum}
+            return {'url': request.url, 'path': path, 'checksum': checksum, 'status': 'uptodate'}
 
         path = self.file_path(request, info=info)
         dfd = defer.maybeDeferred(self.store.stat_file, path, info)
@@ -509,7 +509,7 @@ class FilesPipeline(MediaPipeline):
             )
             raise FileException(str(exc))
 
-        return {'url': request.url, 'path': path, 'checksum': checksum}
+        return {'url': request.url, 'path': path, 'checksum': checksum, 'status': status}
 
     def inc_stats(self, spider, status):
         spider.crawler.stats.inc_value('file_count', spider=spider)

tests/test_pipeline_crawl.py

@@ -91,6 +91,11 @@ class FileDownloadCrawlTestCase(TestCase):
         file_dl_success = 'File (downloaded): Downloaded file from'
         self.assertEqual(logs.count(file_dl_success), 3)
 
+        # check that the images/files status is `downloaded`
+        for item in items:
+            for i in item[self.media_key]:
+                self.assertEqual(i['status'], 'downloaded')
+
         # check that the images/files checksums are what we know they should be
         if self.expected_checksums is not None:
             checksums = set(

tests/test_pipeline_files.py

@@ -93,6 +93,7 @@ class FilesPipelineTestCase(unittest.TestCase):
 
         result = yield self.pipeline.process_item(item, None)
         self.assertEqual(result['files'][0]['checksum'], 'abc')
+        self.assertEqual(result['files'][0]['status'], 'uptodate')
 
         for p in patchers:
             p.stop()
@@ -114,6 +115,29 @@ class FilesPipelineTestCase(unittest.TestCase):
 
         result = yield self.pipeline.process_item(item, None)
         self.assertNotEqual(result['files'][0]['checksum'], 'abc')
+        self.assertEqual(result['files'][0]['status'], 'downloaded')
+
+        for p in patchers:
+            p.stop()
+
+    @defer.inlineCallbacks
+    def test_file_cached(self):
+        item_url = "http://example.com/file3.pdf"
+        item = _create_item_with_files(item_url)
+        patchers = [
+            mock.patch.object(FilesPipeline, 'inc_stats', return_value=True),
+            mock.patch.object(FSFilesStore, 'stat_file', return_value={
+                'checksum': 'abc',
+                'last_modified': time.time() - (self.pipeline.expires * 60 * 60 * 24 * 2)}),
+            mock.patch.object(FilesPipeline, 'get_media_requests',
+                              return_value=[_prepare_request_object(item_url, flags=['cached'])])
+        ]
+        for p in patchers:
+            p.start()
+
+        result = yield self.pipeline.process_item(item, None)
+        self.assertNotEqual(result['files'][0]['checksum'], 'abc')
+        self.assertEqual(result['files'][0]['status'], 'cached')
 
         for p in patchers:
             p.stop()
@@ -412,10 +436,10 @@ def _create_item_with_files(*files):
     return item
 
 
-def _prepare_request_object(item_url):
+def _prepare_request_object(item_url, flags=None):
     return Request(
         item_url,
-        meta={'response': Response(item_url, status=200, body=b'data')})
+        meta={'response': Response(item_url, status=200, body=b'data', flags=flags)})
 
 
 if __name__ == "__main__":