PyPI - bhfutils - Versions diffs - 0.2.99__tar.gz → 0.3.0__tar.gz - Mend

@@ -35,19 +35,31 @@ class MetaPassthroughMiddleware(object):
     def from_crawler(cls, crawler):
         return cls(crawler.settings)
-    def process_spider_output(self, response, result, spider):
+    @staticmethod
+    def _passthrough(response, x):
+        # only operate on requests: pass along all known meta fields, but only
+        # if they were not already set in the spider's new request
+        if isinstance(x, Request):
+            for key in list(response.meta.keys()):
+                if key not in x.meta and key != 'playwright_page_methods':
+                    x.meta[key] = response.meta[key]
+        return x
+    def process_spider_output(self, response, result):
         '''
         Ensures the meta data from the response is passed
-        through in any Request's generated from the spider
+        through in any Request's generated from the spider (sync path).
         '''
         self.logger.debug("processing meta passthrough middleware")
         for x in result:
-            # only operate on requests
-            if isinstance(x, Request):
-                self.logger.debug("found request")
-                # pass along all known meta fields, only if
-                # they were not already set in the spider's new request
-                for key in list(response.meta.keys()):
-                    if key not in x.meta and key != 'playwright_page_methods':
-                        x.meta[key] = response.meta[key]
-            yield x
+            yield self._passthrough(response, x)
+    async def process_spider_output_async(self, response, result):
+        '''
+        Async-generator variant required by Scrapy >= 2.13 when the spider
+        output is an async iterable (AsyncCrawlerProcess). Defining both makes
+        this a "universal" spider middleware compatible with old + new Scrapy.
+        '''
+        self.logger.debug("processing meta passthrough middleware (async)")
+        async for x in result:
+            yield self._passthrough(response, x)

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: bhfutils
-Version: 0.2.99
+Version: 0.3.0
 Summary: Utilities that are used by any spider of Behoof project
 Home-page: https://behoof.app/
 Author: Teplygin Vladimir

@@ -7,7 +7,7 @@ class CustomCookiesMiddleware(CookiesMiddleware):
     persist between calls
     '''
-    def process_request(self, request, spider):
+    def process_request(self, request):
         if 'dont_merge_cookies' in request.meta:
             return
@@ -22,4 +22,4 @@ class CustomCookiesMiddleware(CookiesMiddleware):
         request.headers.pop('Cookie', None)
         jar.add_cookie_header(request)
-        self._debug_cookie(request, spider)
+        self._debug_cookie(request)

@@ -44,16 +44,14 @@ class AggregatorPriceResponseItem(RawResponseItem):
     price = Field()
-class ProductDetailsResponseItem(RawResponseItem):
-    playgroundId = Field()
-    productUrl = Field()
-    groupId = Field()
+class ProductDetailsResponseItem(ProductResponseItem):
     imageUrls = Field()
     type = Field()
     name = Field()
     brandName = Field()
     sellerName = Field()
     description = Field()
+    vendorCode = Field()
     details = Field()
     comments = Field()

@@ -85,12 +85,12 @@ class LogRetryMiddleware(object):
         crawler.settings.set('SPIDER_NAME', crawler.spider.name)
         return cls.from_settings(crawler.settings)
-    def process_exception(self, request, exception, spider):
+    def process_exception(self, request, exception):
         if isinstance(exception, self.EXCEPTIONS_TO_RETRY):
-            self._log_retry(request, exception, spider)
+            self._log_retry(request, exception)
             self._increment_504_stat(request)
-    def _log_retry(self, request, exception, spider):
+    def _log_retry(self, request, exception):
         extras = {}
         extras['logger'] = self.logger.name
         extras['error_request'] = request

@@ -58,7 +58,9 @@ class RedisStatsMiddleware(object):
     @classmethod
     def from_crawler(cls, crawler):
-        return cls(crawler.settings)
+        obj = cls(crawler.settings)
+        obj.crawler = crawler
+        return obj
     def _get_hostname(self):
         '''
@@ -108,12 +110,13 @@ class RedisStatsMiddleware(object):
                               .format(h=hostname, n=spider_name, s=status_code))
             self.stats_dict[spider_name]['status_codes'][status_code]['lifetime'] = total
-    def process_spider_input(self, response, spider):
+    def process_spider_input(self, response):
         '''
         Ensures the meta data from the response is passed
         through in any Request's generated from the spider
         '''
         self.logger.debug("processing redis stats middleware")
+        spider = self.crawler.spider
         if self.settings['STATS_STATUS_CODES']:
             if spider.name not in self.stats_dict:
                 self._setup_stats_status_codes(spider.name)

@@ -43,7 +43,7 @@ if 'nosetests' in sys.argv[1:]:
 setup(
     name='bhfutils',
-    version='0.2.99',
+    version='0.3.0',
     description='Utilities that are used by any spider of Behoof project',
     long_description=readme(),
     long_description_content_type='text/x-rst',

bhfutils 0.2.99__tar.gz → 0.3.0__tar.gz

bhfutils 0.2.99tar.gz → 0.3.0tar.gz