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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/.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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/.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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson1/.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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson1/.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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson1/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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson1/middlewares.py"
new file mode 100644
index 0000000000000000000000000000000000000000..a4243bf4b737ef2d0d8bec82859c388ec05feb3d
--- /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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson1/middlewares.py"
@@ -0,0 +1,143 @@
+# 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
+from itemadapter import is_item, ItemAdapter
+from w3lib.url import canonicalize_url
+from scrapy.utils.python import to_bytes, to_unicode
+
+import hashlib
+import weakref
+
+
+
+# useful for handling different item types with a single interface
+
+
+_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):
+        request.headers["user-agent"] = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.182 Safari/537.36 Edg/88.0.705.81"
+
+class MyRetryMiddleware(RetryMiddleware):
+    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):
+    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]
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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson1/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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson1/settings.py"
new file mode 100644
index 0000000000000000000000000000000000000000..cad027e2603c1462ca1adb7ff9cdf8bf2276842f
--- /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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson1/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
+
+REDIRECT_ENABLE = False
+
+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,
+}
+
+# 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 = {
+    "host": "127.0.0.1",
+    "user": "root",
+    "password": "xmt66237029",
+    "db": "week9"
+}
+
+# LOG
+LOG_FILE = "D:/log/jd_search.log"
+LOG_LEVEL = "DEBUG"
+
+# DUP
+DUPEFILTER_CLASS = "jd_crawler_scrapy.middlewares.MyRFPDupeFilter"
\ 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\245/3\347\217\255/3\347\217\255_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/.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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/.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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/__init__.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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/__init__.py"
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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/items.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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/items.py"
new file mode 100644
index 0000000000000000000000000000000000000000..1c96e07c60317eb9eab5a44b1563c75f732e47fe
--- /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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/items.py"
@@ -0,0 +1,19 @@
+# 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\245/3\347\217\255/3\347\217\255_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/middlewares.py"
new file mode 100644
index 0000000000000000000000000000000000000000..50871150543fc0c315075457fee7737beec9466d
--- /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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/middlewares.py"
@@ -0,0 +1,163 @@
+# 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
+from itemadapter import is_item, ItemAdapter
+from w3lib.url import canonicalize_url
+from scrapy.utils.python import to_bytes, to_unicode
+
+import hashlib
+import weakref
+
+
+
+# useful for handling different item types with a single interface
+
+
+_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):
+        # request.headers['cookie'] = "__jdu=16145053508501715621824; shshshfpa=04eb19ca-e4a4-e402-4ba1-661209b44b45-1614505356; shshshfpb=pfquKaGf2BF9BEAn5FVoKTQ%3D%3D; qrsc=3; unpl=V2_ZzNtbUcCRkUlCE8Ech9eAmIGGg1LUUURJwBDUCsRC1BiVBUKclRCFnUUR1ZnGVkUZwoZWEpcQBRFCEdkeBBVAWMDE1VGZxBFLV0CFSNGF1wjU00zQwBBQHcJFF0uSgwDYgcaDhFTQEJ2XBVQL0oMDDdRFAhyZ0AVRQhHZHseXABjAhZfRlZKEXQIQFR%2fHl8FbgAXbXJQcyVFCEZSfRtdNWYzE20AAx8cdAhEVXlUXAJnBhZcRlVHFHwMR1R9GVgCZAMbXkdnQiV2; __jdv=76161171|baidu-pinzhuan|t_288551095_baidupinzhuan|cpc|0f3d30c8dba7459bb52f2eb5eba8ac7d_0_4d4aa18a8736449a8775c945a9fd4f6f|1615718959550; areaId=12; ipLoc-djd=12-988-40034-0; PCSYCityID=CN_0_0_0; __jda=122270672.16145053508501715621824.1614505351.1614530307.1615718960.4; __jdb=122270672.2.16145053508501715621824|4.1615718960; __jdc=122270672; shshshfp=c907bac07f57d2d9bd6b95e4bbd98546; shshshsID=dd3ddb3830270a6da29617dd323e8665_2_1615718964705; rkv=1.0; 3AB9D23F7A4B3C9B=UZVSMFBYANBA7S4P2CFROVSTUANCYW6XIJDGKUWUAK76VESYQC6EAFH3EXFMOYCWPYX3DK3TKKQ3XROBBURIVBFCMM"
+        # 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):
+        if isinstance(exception, IndexError):
+            retry_times = request.meta.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/88.0.4324.182 Safari/537.36 Edg/88.0.705.81"
+
+class MyRetryMiddleware(RetryMiddleware):
+    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):
+    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]
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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/pipelines.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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/pipelines.py"
new file mode 100644
index 0000000000000000000000000000000000000000..3a8e610be4d21e810ddff6c8e9eb4c31ca76b994
--- /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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/pipelines.py"
@@ -0,0 +1,29 @@
+# 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\245/3\347\217\255/3\347\217\255_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/settings.py"
new file mode 100644
index 0000000000000000000000000000000000000000..f7ee7fda1a46df047d28c5d60885d3092a6018b2
--- /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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/settings.py"
@@ -0,0 +1,113 @@
+# 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
+
+REDIRECT_ENABLE = False
+
+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 = {
+    "host": "127.0.0.1",
+    "user": "root",
+    "password": "xmt66237029",
+    "db": "week9"
+}
+
+# LOG
+# LOG_FILE = "D:/log/jd_search.log"
+LOG_LEVEL = "DEBUG"
+
+# DUP
+DUPEFILTER_CLASS = "jd_crawler_scrapy.middlewares.MyRFPDupeFilter"
\ 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\245/3\347\217\255/3\347\217\255_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/spiders/__init__.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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/spiders/__init__.py"
new file mode 100644
index 0000000000000000000000000000000000000000..ebd689ac51d69c5e1dbbe80083c2b20a39f8bb79
--- /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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/spiders/__init__.py"
@@ -0,0 +1,4 @@
+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.
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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/spiders/__pycache__/__init__.cpython-38.pyc" "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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/spiders/__pycache__/__init__.cpython-38.pyc"
new file mode 100644
index 0000000000000000000000000000000000000000..a5aa3f6872be2c5db2d5616e3974bf013526f9b0
Binary files /dev/null and "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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/spiders/__pycache__/__init__.cpython-38.pyc" differ
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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/spiders/__pycache__/jd_search.cpython-38.pyc" "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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/spiders/__pycache__/jd_search.cpython-38.pyc"
new file mode 100644
index 0000000000000000000000000000000000000000..fbd52bfcd463ff425af14f12d6467d10fe2d5197
Binary files /dev/null and "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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/spiders/__pycache__/jd_search.cpython-38.pyc" differ
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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/spiders/__pycache__/run.cpython-38.pyc" "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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/spiders/__pycache__/run.cpython-38.pyc"
new file mode 100644
index 0000000000000000000000000000000000000000..936fe43bf52dd38455fa565106a45b9a68fbd82a
Binary files /dev/null and "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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/spiders/__pycache__/run.cpython-38.pyc" differ
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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/spiders/jd_search.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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/spiders/jd_search.py"
new file mode 100644
index 0000000000000000000000000000000000000000..33bcf6544415a348f6ff6eec84cc94eb1d585033
--- /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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/spiders/jd_search.py"
@@ -0,0 +1,64 @@
+import scrapy
+import json
+import time
+from bs4 import BeautifulSoup
+from jd_crawler_scrapy.items import JdCrawlerScrapyItem
+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}"
+                yield scrapy.FormRequest(
+                    meta={"keyword": keyword, "sta_date": time.strftime("%Y-%m-%d")},
+                    dont_filter=False,
+                    url=url,
+                    method='GET',
+                    callback=self.parse_search,
+                    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["price"] = price
+                item["shop"] = shop
+                item["img"] = img
+                item["title"] = title
+                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
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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/spiders/run.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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/spiders/run.py"
new file mode 100644
index 0000000000000000000000000000000000000000..81ab43352b367946dd538b65e432f3ea1c7a2b7a
--- /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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/lesson2/spiders/run.py"
@@ -0,0 +1,4 @@
+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\245/3\347\217\255/3\347\217\255_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/\347\254\254\345\215\201\344\270\200\345\221\250-\347\254\254\344\270\211\350\212\202.md" "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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/\347\254\254\345\215\201\344\270\200\345\221\250-\347\254\254\344\270\211\350\212\202.md"
new file mode 100644
index 0000000000000000000000000000000000000000..419e9a0398114ad88e5e2a4f671ae953f21d8698
--- /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_\350\214\227\350\214\227\346\230\257\345\217\252\345\201\207\351\270\275\345\255\220/week11/\347\254\254\345\215\201\344\270\200\345\221\250-\347\254\254\344\270\211\350\212\202.md"
@@ -0,0 +1,99 @@
+# 第十一周-第三节
+
+```
+C:\Users\47116>redis-server
+[29224] 14 Mar 21:44:54.017 # Warning: no config file specified, using the default config. In order to specify a config file use redis-server /path/to/redis.conf
+[29224] 14 Mar 21:44:54.021 # Creating Server TCP listening socket *:6379: bind: No such file or directory
+
+C:\Users\47116>redis-cli
+127.0.0.1:6379> select 2
+OK
+127.0.0.1:6379[2]> keys *
+(empty list or set)
+127.0.0.1:6379[2]> set 'a' 1
+OK
+127.0.0.1:6379[2]> get 'a'
+"1"
+127.0.0.1:6379[2]> set 'a' 2
+OK
+127.0.0.1:6379[2]> del 'a'
+(integer) 1
+127.0.0.1:6379[2]> keys *
+(empty list or set)
+127.0.0.1:6379[2]> set 'a' 1
+OK
+127.0.0.1:6379[2]> hset 'hash_test' 'a' 1
+(integer) 1
+127.0.0.1:6379[2]> hset 'hash_test' 'b' 2
+(integer) 1
+127.0.0.1:6379[2]> hget 'hash_test' 'a'
+"1"
+127.0.0.1:6379[2]> hdel 'hash_test' 'a'
+(integer) 1
+127.0.0.1:6379[2]> lpush 'list_test' 1
+(integer) 1
+127.0.0.1:6379[2]> lpush 'list_test' 2
+(integer) 2
+127.0.0.1:6379[2]> lpush 'list_test' 3
+(integer) 3
+127.0.0.1:6379[2]> lindex 'list_test' 1
+"2"
+127.0.0.1:6379[2]> lrange 'list_test' 0 2
+1) "3"
+2) "2"
+3) "1"
+127.0.0.1:6379[2]> linsert 'list_test' before a 'a'
+(integer) -1
+127.0.0.1:6379[2]> linsert 'list_test' before 1 'a'
+(integer) 4
+127.0.0.1:6379[2]> linsert 'list_test' before 'a' 'b'
+(integer) 5
+127.0.0.1:6379[2]> rpop 'list_test'
+"1"
+127.0.0.1:6379[2]> lrem 'list_test' 1 1
+(integer) 0
+127.0.0.1:6379[2]> lrem 'list_test' 2 'a'
+(integer) 1
+127.0.0.1:6379[2]> lrem 'list_test' 2 'b'
+(integer) 1
+127.0.0.1:6379[2]> lpush 'list_test' 3 3 3 3
+(integer) 6
+127.0.0.1:6379[2]> lrem 'list_test' 3 2
+(integer) 1
+127.0.0.1:6379[2]> lrem 'list_test' 2 3
+(integer) 2
+127.0.0.1:6379[2]> sadd 'set_test' 1
+(integer) 1
+127.0.0.1:6379[2]> sadd 'set_test' 2
+(integer) 1
+127.0.0.1:6379[2]> smembers 'set_test'
+1) "1"
+2) "2"
+127.0.0.1:6379[2]> sismember 'set_test' 2
+(integer) 1
+127.0.0.1:6379[2]> srandmember 'set_test' 2
+1) "1"
+2) "2"
+127.0.0.1:6379[2]> spop 'set_test'
+"1"
+127.0.0.1:6379[2]> zadd 'zse_test' 10 'a'
+(integer) 1
+127.0.0.1:6379[2]> zadd 'zse_test' 1 'b'
+(integer) 1
+127.0.0.1:6379[2]> zadd 'zse_test' 12 'c'
+(integer) 1
+127.0.0.1:6379[2]> zcard 'zse_test'
+(integer) 3
+127.0.0.1:6379[2]> zcount 'zse_test' 2 11
+(integer) 1
+127.0.0.1:6379[2]> zrangebyscore 'zse_test' 2 11
+1) "a"
+127.0.0.1:6379[2]> zincrby 'zse_test' 1 'b'
+"2"
+127.0.0.1:6379[2]> zremrangebyrank 'zse_test' 1 2
+(integer) 2
+127.0.0.1:6379[2]> zremrangebyscore 'zse_test' 2 2
+(integer) 1
+127.0.0.1:6379[2]>
+```
+