From 6aacabaf5aeb635cf5155624c267560e71ba5a6b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=BC=A0=E8=99=9A=E5=B9=B3?=
 <8437069+zhang-xuping@user.noreply.gitee.com>
Date: Fri, 12 Mar 2021 00:51:34 +0800
Subject: [PATCH] good

---
 .../items.py"                                 |  20 +++
 .../jd_search.py"                             |  72 ++++++++
 .../middlewares.py"                           | 167 ++++++++++++++++++
 .../pipelines.py"                             |  28 +++
 .../run.py"                                   |   7 +
 .../settings.py"                              | 114 ++++++++++++
 6 files changed, 408 insertions(+)
 create mode 100644 "\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/items.py"
 create mode 100644 "\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/jd_search.py"
 create mode 100644 "\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/middlewares.py"
 create mode 100644 "\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/pipelines.py"
 create mode 100644 "\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/run.py"
 create mode 100644 "\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/settings.py"

diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/items.py" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/items.py"
new file mode 100644
index 00000000..04d29cab
--- /dev/null
+++ "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/items.py"
@@ -0,0 +1,20 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class JdCrawlerScrapyItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    sku_id = scrapy.Field()
+    img = scrapy.Field()
+    price = scrapy.Field()
+    title = scrapy.Field()
+    shop = scrapy.Field()
+    icons = scrapy.Field()
+    sta_date = scrapy.Field()
+    keyword = scrapy.Field()
+
diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/jd_search.py" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/jd_search.py"
new file mode 100644
index 00000000..70e58ba3
--- /dev/null
+++ "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/jd_search.py"
@@ -0,0 +1,72 @@
+import scrapy
+import json
+from bs4 import BeautifulSoup
+from jd_crawler_scrapy.items import JdCrawlerScrapyItem
+import time
+from scrapy.exceptions import CloseSpider
+
+class JdSearch(scrapy.Spider):
+    name = "jd_search"
+
+    def start_requests(self):
+        for keyword in ["鼠标", "键盘", "显卡", "耳机"]:
+            for page_num in range(1, 11):
+                url = f"https://search.jd.com/Search?keyword={keyword}&page={page_num}"
+
+               #选用FormRequest是因为它即可以发送GET请求，又可以发送POST请求
+                yield scrapy.FormRequest(
+                    meta={"keyword": keyword, "sta_date": time.strftime("%Y-%m-%d")},
+                    dont_filter=False,
+                    url=url,
+                    method='GET',
+                    # formdata = data,         #如果是Post请求，携带数据使用formdata参数
+
+                    callback=self.parse_search, #指定回调函数处理response对象
+                    errback=self.process_error
+                )
+            break
+
+    def parse_search(self, response):
+        print(response)
+        soup = BeautifulSoup(response.text, "lxml")
+        item_array = soup.select("ul[class='gl-warp clearfix'] li[class=gl-item]")
+        for item in item_array:
+            try:
+                sku_id = item.attrs["data-sku"]
+                img = item.select("img[data-img='1']")
+                price = item.select("div[class='p-price']")
+                title = item.select("div[class='p-name p-name-type-2']")
+                shop = item.select("div[class='p-shop']")
+                icons = item.select("div[class='p-icons']")
+
+                img = img[0].attrs['data-lazy-img'] if img else ""
+                price = price[0].strong.i.text if price else ""
+                title = title[0].text.strip() if title else ""
+                shop = shop[0].span.a.attrs['title'] if shop[0].text.strip() else ""
+                icons = json.dumps([tag_ele.text for tag_ele in icons[0].select("i")]) if icons else '[]'
+
+                item = JdCrawlerScrapyItem()
+                item["sku_id"] = sku_id
+                item["img"] = img
+                item["price"] = price
+                item["title"] = title
+                item["shop"] = shop
+                item["icons"] = icons
+                item["sta_date"] = response.meta["sta_date"]
+                item["keyword"] = response.meta["keyword"]
+                yield item
+
+            except Exception as e:
+                print(e.args)
+
+    def process_error(self, failure):
+        print(failure)
+        if "身份已过期" in str(failure.value):
+            raise CloseSpider
+        #记录异常
+        #发送通知
+        #重做任务
+
+
+
+
diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/middlewares.py" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/middlewares.py"
new file mode 100644
index 00000000..e9f4e970
--- /dev/null
+++ "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/middlewares.py"
@@ -0,0 +1,167 @@
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+from scrapy.downloadermiddlewares.retry import RetryMiddleware
+from scrapy.utils.response import response_status_message
+from scrapy.dupefilters import RFPDupeFilter
+import hashlib
+import weakref
+from w3lib.url import canonicalize_url
+from scrapy.utils.python import to_bytes
+import random
+
+# useful for handling different item types with a single interface
+from itemadapter import is_item, ItemAdapter
+
+_fingerprint_cache = weakref.WeakKeyDictionary()
+
+
+class JdCrawlerScrapySpiderMiddleware:
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(self, response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(self, response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, or item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(self, response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Request or item objects.
+        pass
+
+    def process_start_requests(self, start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)
+
+
+class JdCrawlerScrapyDownloaderMiddleware:
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the downloader middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_request(self, request, spider):
+        # Called for each request that goes through the downloader
+        # middleware.
+
+        # Must either:
+        # - return None: continue processing this request
+        # - or return a Response object
+        # - or return a Request object
+        # - or raise IgnoreRequest: process_exception() methods of
+        #   installed downloader middleware will be called
+        return None
+
+    def process_response(self, request, response, spider):
+        # Called with the response returned from the downloader.
+
+        # Must either;
+        # - return a Response object
+        # - return a Request object
+        # - or raise IgnoreRequest
+        return response
+
+    def process_exception(self, request, exception, spider):
+        # Called when a download handler or a process_request()
+        # (from other downloader middleware) raises an exception.
+
+        # Must either:
+        # - return None: continue processing this exception
+        # - return a Response object: stops process_exception() chain
+        # - return a Request object: stops process_exception() chain
+        pass
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)
+
+class CookieMiddleware:
+    def process_request(self, request, spider):
+        # cookie_pool = []
+        # request.headers['cookie'] = cookie_pool.pop()
+        pass
+
+    def process_response(self, request, response, spider):
+
+        # if "身份过期" in response.text:
+        raise Exception("当前cookie身份已过期")
+
+    def process_exception(self, request, exception, spider):
+        #如果异常是cookie池空了，可以在这里完成cookie池的补充
+        #补充cookie池
+        if isinstance(exception, IndexError):
+            retry_times = request.met.get('retry_times', 1)
+            request.meta['retry_times'] = retry_times - 1
+            return request
+
+
+class UAMiddleware:
+    def process_request(self, request, spider):
+
+        request.headers["user-agent"] = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.72 Safari/537.36"
+
+class MyRetryMiddleware(RetryMiddleware):
+    """
+    解决对方服务器返回正常状态码200，但是根据IP需要进行验证码验证的情况
+    我们可以通过换IP可以解决验证码，那么就应该重试.
+    """
+    def process_response(self, request, response, spider):
+        if request.meta.get('dont_retry', False):
+            return response
+        if "验证码" in response.text:
+            reason = response_status_message(response.status)
+            return self.retry(request, reason, spider) or response
+        return response
+class MyRFPDupeFilter(RFPDupeFilter):
+    """
+    过滤器是在到达下载器之前就生成了过滤指纹，如果我们的下载器中间件报错，那么过滤指纹仍然生效，但是没有实际请求。
+    所以我们可以通过一些特殊参数来进行自定义过滤规则
+    """
+    def request_fingerprint(self, request, include_headers=None, keep_fragments=False):
+        cache = _fingerprint_cache.setdefault(request, {})
+        cache_key = (include_headers, keep_fragments)
+        if cache_key not in cache:
+            fp = hashlib.sha1()
+            fp.update(to_bytes(request.method))
+            fp.update(to_bytes(canonicalize_url(request.url, keep_fragments=keep_fragments)))
+            fp.update(request.body or b'')
+            fp.update(request.meta.get("batch_no", "").encode("utf-8"))
+            cache[cache_key] = fp.hexdigest()
+        return cache[cache_key]
\ No newline at end of file
diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/pipelines.py" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/pipelines.py"
new file mode 100644
index 00000000..e16c4882
--- /dev/null
+++ "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/pipelines.py"
@@ -0,0 +1,28 @@
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+# useful for handling different item types with a single interface
+from itemadapter import ItemAdapter
+from jd_crawler_scrapy.items import JdCrawlerScrapyItem
+import pymysql
+
+class JdCrawlerScrapyPipeline:
+    def __init__(self):
+        self.mysql_con = None
+
+    def process_item(self, item, spider):
+        if not self.mysql_con:
+            self.mysql_con = pymysql.connect(**spider.settings["MYSQL_CONF"])
+        if isinstance(item, JdCrawlerScrapyItem):
+            cursor = self.mysql_con.cursor()
+            SQL = """INSERT INTO jd_search(sku_id, img, price, title, shop, icons, sta_date, keyword)
+                         VALUES ('{}', '{}', '{}', '{}', '{}', '{}', '{}', '{}')""".format(
+                item['sku_id'], item['img'], item['price'], item['title'], item['shop'], item['icons'], item['sta_date'], item['keyword']
+            )
+            cursor.execute(SQL)
+            self.mysql_con.commit()
+            cursor.close()
+        return item
diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/run.py" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/run.py"
new file mode 100644
index 00000000..676d216e
--- /dev/null
+++ "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/run.py"
@@ -0,0 +1,7 @@
+from scrapy import cmdline
+
+command = "scrapy crawl jd_search".split()
+cmdline.execute(command)
+
+
+
diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/settings.py" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/settings.py"
new file mode 100644
index 00000000..25d994bd
--- /dev/null
+++ "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/1\347\217\255/1\347\217\255_\345\230\230\345\230\230/1\347\217\255_\345\230\230\345\230\230_\347\254\254\345\215\201\344\270\200\345\221\250_\344\275\234\344\270\232/1\347\217\255_\345\230\230\345\230\230_\347\254\254\344\272\214\350\212\202\350\257\276_\344\275\234\344\270\232/settings.py"
@@ -0,0 +1,114 @@
+# Scrapy settings for jd_crawler_scrapy project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     https://docs.scrapy.org/en/latest/topics/settings.html
+#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'jd_crawler_scrapy'
+
+SPIDER_MODULES = ['jd_crawler_scrapy.spiders']
+NEWSPIDER_MODULE = 'jd_crawler_scrapy.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'jd_crawler_scrapy (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = False
+
+#Enable redirect
+REDIRECT_ENABLE = False
+
+#Retry
+RETRY_ENABLE = False
+RETRY_HTTP_CODES = [500, 502, 503, 504, 408, 429]
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+CONCURRENT_REQUESTS = 1
+
+# Configure a delay for requests for the same website (default: 0)
+# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+#DOWNLOAD_DELAY = 3
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+#COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'jd_crawler_scrapy.middlewares.JdCrawlerScrapySpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+DOWNLOADER_MIDDLEWARES = {
+   # 'jd_crawler_scrapy.middlewares.JdCrawlerScrapyDownloaderMiddleware': 543,
+   'jd_crawler_scrapy.middlewares.UAMiddleware': 100,
+   'jd_crawler_scrapy.middlewares.MyRetryMiddleware': 200,
+   'jd_crawler_scrapy.middlewares.CookieMiddleware': 150,
+}
+
+# Enable or disable extensions
+# See https://docs.scrapy.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'jd_crawler_scrapy.pipelines.JdCrawlerScrapyPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
+
+#MYSQL CONF
+MYSQL_CONF = {
+   "host": "127.0.0.1",
+   "user": "root",
+   "password": "zhang1128",
+   "db": "tunan_class"
+}
+
+#LOG
+# LOG_FILE = "C:/Users/张虚平/PycharmProjects/认识python/jd_crawler_scrapy/log/jd_search.log"
+LOG_LEVEL = "DEBUG"
+
+#DUP
+DUPEFILTER_CLASS = "jd_crawler_scrapy.middlewares.MyRFPDupeFilter"
+
-- 
Gitee