From 1705510150e582824e5be828810ea3e1ba37b58f Mon Sep 17 00:00:00 2001
From: pnhekgfuf <1913997697@qq.com>
Date: Sat, 29 Apr 2023 12:18:14 +0800
Subject: [PATCH] ADD file via upload

---
 Scrapy-Redis-Zhihu/scrapy_redis/pipelines.py | 76 ++++++++++++++++++++
 1 file changed, 76 insertions(+)
 create mode 100644 Scrapy-Redis-Zhihu/scrapy_redis/pipelines.py

diff --git a/Scrapy-Redis-Zhihu/scrapy_redis/pipelines.py b/Scrapy-Redis-Zhihu/scrapy_redis/pipelines.py
new file mode 100644
index 0000000..8ae4ef0
--- /dev/null
+++ b/Scrapy-Redis-Zhihu/scrapy_redis/pipelines.py
@@ -0,0 +1,76 @@
+from scrapy.utils.misc import load_object
+from scrapy.utils.serialize import ScrapyJSONEncoder
+from twisted.internet.threads import deferToThread
+
+from . import connection, defaults
+
+
+default_serialize = ScrapyJSONEncoder().encode
+
+
+class RedisPipeline(object):
+    """Pushes serialized item into a redis list/queue
+
+    Settings
+    --------
+    REDIS_ITEMS_KEY : str
+        Redis key where to store items.
+    REDIS_ITEMS_SERIALIZER : str
+        Object path to serializer function.
+
+    """
+
+    def __init__(self, server,
+                 key=defaults.PIPELINE_KEY,
+                 serialize_func=default_serialize):
+        """Initialize pipeline.
+
+        Parameters
+        ----------
+        server : StrictRedis
+            Redis client instance.
+        key : str
+            Redis key where to store items.
+        serialize_func : callable
+            Items serializer function.
+
+        """
+        self.server = server
+        self.key = key
+        self.serialize = serialize_func
+
+    @classmethod
+    def from_settings(cls, settings):
+        params = {
+            'server': connection.from_settings(settings),
+        }
+        if settings.get('REDIS_ITEMS_KEY'):
+            params['key'] = settings['REDIS_ITEMS_KEY']
+        if settings.get('REDIS_ITEMS_SERIALIZER'):
+            params['serialize_func'] = load_object(
+                settings['REDIS_ITEMS_SERIALIZER']
+            )
+
+        return cls(**params)
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        return cls.from_settings(crawler.settings)
+
+    def process_item(self, item, spider):
+        return deferToThread(self._process_item, item, spider)
+
+    def _process_item(self, item, spider):
+        key = self.item_key(item, spider)
+        data = self.serialize(item)
+        self.server.rpush(key, data)
+        return item
+
+    def item_key(self, item, spider):
+        """Returns redis key based on given spider.
+
+        Override this function to use a different key depending on the item
+        and/or spider.
+
+        """
+        return self.key % {'spider': spider.name}