diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/\347\254\254\345\215\201\344\270\200\345\221\250\344\275\234\344\270\232/.keep" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/\347\254\254\345\215\201\344\270\200\345\221\250\344\275\234\344\270\232/.keep"
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/\347\254\254\345\215\201\344\270\200\345\221\250\344\275\234\344\270\232/\347\254\254\345\215\201\344\270\200\345\221\250_\347\254\254\344\270\200\350\212\202/.keep" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/\347\254\254\345\215\201\344\270\200\345\221\250\344\275\234\344\270\232/\347\254\254\345\215\201\344\270\200\345\221\250_\347\254\254\344\270\200\350\212\202/.keep"
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/\347\254\254\345\215\201\344\270\200\345\221\250\344\275\234\344\270\232/\347\254\254\345\215\201\344\270\200\345\221\250_\347\254\254\344\270\200\350\212\202/middlewares.py" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/\347\254\254\345\215\201\344\270\200\345\221\250\344\275\234\344\270\232/\347\254\254\345\215\201\344\270\200\345\221\250_\347\254\254\344\270\200\350\212\202/middlewares.py"
new file mode 100644
index 0000000000000000000000000000000000000000..7483baca1aa68da7f2407f41a8247c190935b870
--- /dev/null
+++ "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/\347\254\254\345\215\201\344\270\200\345\221\250\344\275\234\344\270\232/\347\254\254\345\215\201\344\270\200\345\221\250_\347\254\254\344\270\200\350\212\202/middlewares.py"
@@ -0,0 +1,158 @@
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy.utils.response import response_status_message
+from scrapy.dupefilters import RFPDupeFilter
+from scrapy import signals
+from scrapy.downloadermiddlewares.retry import RetryMiddleware
+from itemadapter import is_item, ItemAdapter
+from w3lib.url import canonicalize_url
+from scrapy.utils.python import to_bytes
+
+import hashlib
+import weakref
+_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 UAMiddleware:
+    def process_request(self, request, spider):
+        """
+        在正式请求前为当前请求添加headers
+        :param request:
+        :param spider:
+        :return:
+        """
+        request.headers["user-agent"] = "Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.190 Mobile 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
+    通过换IP可以解决验证码，那么应该可以重试
+
+    """
+    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之前九生成了过滤指纹，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_gragments=False):
+        cache = _fingerprint_cache.setdefault(request, {})
+        cache_key = (include_headers, keep_gragments)
+        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_gragments)))
+            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]
+
+
+
+
+
diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/\347\254\254\345\215\201\344\270\200\345\221\250\344\275\234\344\270\232/\347\254\254\345\215\201\344\270\200\345\221\250_\347\254\254\344\270\200\350\212\202/settings.py" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/\347\254\254\345\215\201\344\270\200\345\221\250\344\275\234\344\270\232/\347\254\254\345\215\201\344\270\200\345\221\250_\347\254\254\344\270\200\350\212\202/settings.py"
new file mode 100644
index 0000000000000000000000000000000000000000..2a8e819637ca0ddc74f1ed3d6b02778dd89630ee
--- /dev/null
+++ "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/\347\254\254\345\215\201\344\270\200\345\221\250\344\275\234\344\270\232/\347\254\254\345\215\201\344\270\200\345\221\250_\347\254\254\344\270\200\350\212\202/settings.py"
@@ -0,0 +1,111 @@
+# 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, 408, 429]
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16) 请求限制
+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,
+}
+
+# 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": "lmc.123",
+    "db": "tunan_class3"
+}
+
+
+#log
+LOG_FILE = "F:\log\jd_search.log"
+LOG_LEVEL= "DEBUG"
\ No newline at end of file