From 5c0c76b020a7f6974209574209b1124ed7c771c9 Mon Sep 17 00:00:00 2001
From: JLUVicent <17390955615@163.com>
Date: Thu, 16 Sep 2021 19:05:44 +0800
Subject: [PATCH] =?UTF-8?q?=E7=88=AC=E5=8F=96=E5=BD=93=E5=BD=93=E7=BD=91?=
 =?UTF-8?q?=E5=9B=BE=E7=89=87=EF=BC=8C=E4=B9=A6=E5=90=8D=EF=BC=8C=E4=BB=B7?=
 =?UTF-8?q?=E6=A0=BC?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 scrapy_dangdang_040/scrapy.cfg                |  11 ++
 .../scrapy_dangdang_040/__init__.py           |   0
 .../__pycache__/__init__.cpython-39.pyc       | Bin 0 -> 190 bytes
 .../__pycache__/settings.cpython-39.pyc       | Bin 0 -> 299 bytes
 .../scrapy_dangdang_040/items.py              |  14 +++
 .../scrapy_dangdang_040/middlewares.py        | 103 ++++++++++++++++++
 .../scrapy_dangdang_040/pipelines.py          |  13 +++
 .../scrapy_dangdang_040/settings.py           |  88 +++++++++++++++
 .../scrapy_dangdang_040/spiders/__init__.py   |   4 +
 .../__pycache__/__init__.cpython-39.pyc       | Bin 0 -> 198 bytes
 .../spiders/__pycache__/dang.cpython-39.pyc   | Bin 0 -> 961 bytes
 .../scrapy_dangdang_040/spiders/dang.py       |  39 +++++++
 12 files changed, 272 insertions(+)
 create mode 100644 scrapy_dangdang_040/scrapy.cfg
 create mode 100644 scrapy_dangdang_040/scrapy_dangdang_040/__init__.py
 create mode 100644 scrapy_dangdang_040/scrapy_dangdang_040/__pycache__/__init__.cpython-39.pyc
 create mode 100644 scrapy_dangdang_040/scrapy_dangdang_040/__pycache__/settings.cpython-39.pyc
 create mode 100644 scrapy_dangdang_040/scrapy_dangdang_040/items.py
 create mode 100644 scrapy_dangdang_040/scrapy_dangdang_040/middlewares.py
 create mode 100644 scrapy_dangdang_040/scrapy_dangdang_040/pipelines.py
 create mode 100644 scrapy_dangdang_040/scrapy_dangdang_040/settings.py
 create mode 100644 scrapy_dangdang_040/scrapy_dangdang_040/spiders/__init__.py
 create mode 100644 scrapy_dangdang_040/scrapy_dangdang_040/spiders/__pycache__/__init__.cpython-39.pyc
 create mode 100644 scrapy_dangdang_040/scrapy_dangdang_040/spiders/__pycache__/dang.cpython-39.pyc
 create mode 100644 scrapy_dangdang_040/scrapy_dangdang_040/spiders/dang.py

diff --git a/scrapy_dangdang_040/scrapy.cfg b/scrapy_dangdang_040/scrapy.cfg
new file mode 100644
index 0000000..2b5d2d2
--- /dev/null
+++ b/scrapy_dangdang_040/scrapy.cfg
@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
+
+[settings]
+default = scrapy_dangdang_040.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = scrapy_dangdang_040
diff --git a/scrapy_dangdang_040/scrapy_dangdang_040/__init__.py b/scrapy_dangdang_040/scrapy_dangdang_040/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/scrapy_dangdang_040/scrapy_dangdang_040/__pycache__/__init__.cpython-39.pyc b/scrapy_dangdang_040/scrapy_dangdang_040/__pycache__/__init__.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..63d1f74c2372b1c89171c4505a2bd3893290c0f1
GIT binary patch
literal 190
zcmYe~<>g`kg2T_95<&E15P=LBfgA@QE@lA|DGb33nv8xc8Hzx{2;yr3kn3s{Q&3rw
zk)NlKpQezLnpl*VnU@~(bi=IY3tL}o*#5j@&5N0<W1jDBezJ2xOmT8iVnJnmN@89*
n2*(?k7+@8PkI&4@EQycTE2zB1VUwGmQks)$2eSM#5HkP(e1SP5

literal 0
HcmV?d00001

diff --git a/scrapy_dangdang_040/scrapy_dangdang_040/__pycache__/settings.cpython-39.pyc b/scrapy_dangdang_040/scrapy_dangdang_040/__pycache__/settings.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..3ac7951f67146028f04e12802149d8cde02a439f
GIT binary patch
literal 299
zcmYe~<>g`kf*sP%iETU#439w^WWWgIH~?|65Rgb=h+;@#OlOQ@Oks>-N?{6S&}5Dh
zE>12=EU1i6Nz6+J;dlcRgDPn(f_lXTnJKA7#eSO1w>X^qL*o4$eO+(y1qXP#xCX`h
z`n!bsxCY-6@N*4E5n9Pm!~(P%OnglMvRtiV3Mxx7^79n((-d-26N~aP^U`CUZkY9a
zVe5+x+n;x=c`<W!%=6vNPj)Vd!Qu|=VyPu1Kx2ya3My}L*yQG?l;)(`fr6$OWH}2H
G8zTUTSX;UP

literal 0
HcmV?d00001

diff --git a/scrapy_dangdang_040/scrapy_dangdang_040/items.py b/scrapy_dangdang_040/scrapy_dangdang_040/items.py
new file mode 100644
index 0000000..ae4f13b
--- /dev/null
+++ b/scrapy_dangdang_040/scrapy_dangdang_040/items.py
@@ -0,0 +1,14 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class ScrapyDangdang040Item(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    # 通俗的说就是要下载的数据都要什么
+
+    pass
diff --git a/scrapy_dangdang_040/scrapy_dangdang_040/middlewares.py b/scrapy_dangdang_040/scrapy_dangdang_040/middlewares.py
new file mode 100644
index 0000000..3c41796
--- /dev/null
+++ b/scrapy_dangdang_040/scrapy_dangdang_040/middlewares.py
@@ -0,0 +1,103 @@
+# 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
+
+# useful for handling different item types with a single interface
+from itemadapter import is_item, ItemAdapter
+
+
+class ScrapyDangdang040SpiderMiddleware:
+    # 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 ScrapyDangdang040DownloaderMiddleware:
+    # 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)
diff --git a/scrapy_dangdang_040/scrapy_dangdang_040/pipelines.py b/scrapy_dangdang_040/scrapy_dangdang_040/pipelines.py
new file mode 100644
index 0000000..58327f2
--- /dev/null
+++ b/scrapy_dangdang_040/scrapy_dangdang_040/pipelines.py
@@ -0,0 +1,13 @@
+# 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
+
+
+class ScrapyDangdang040Pipeline:
+    def process_item(self, item, spider):
+        return item
diff --git a/scrapy_dangdang_040/scrapy_dangdang_040/settings.py b/scrapy_dangdang_040/scrapy_dangdang_040/settings.py
new file mode 100644
index 0000000..34dff05
--- /dev/null
+++ b/scrapy_dangdang_040/scrapy_dangdang_040/settings.py
@@ -0,0 +1,88 @@
+# Scrapy settings for scrapy_dangdang_040 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 = 'scrapy_dangdang_040'
+
+SPIDER_MODULES = ['scrapy_dangdang_040.spiders']
+NEWSPIDER_MODULE = 'scrapy_dangdang_040.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'scrapy_dangdang_040 (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+# ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# 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 = {
+#    'scrapy_dangdang_040.middlewares.ScrapyDangdang040SpiderMiddleware': 543,
+# }
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+# DOWNLOADER_MIDDLEWARES = {
+#    'scrapy_dangdang_040.middlewares.ScrapyDangdang040DownloaderMiddleware': 543,
+# }
+
+# 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 = {
+#    'scrapy_dangdang_040.pipelines.ScrapyDangdang040Pipeline': 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'
diff --git a/scrapy_dangdang_040/scrapy_dangdang_040/spiders/__init__.py b/scrapy_dangdang_040/scrapy_dangdang_040/spiders/__init__.py
new file mode 100644
index 0000000..ebd689a
--- /dev/null
+++ b/scrapy_dangdang_040/scrapy_dangdang_040/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/scrapy_dangdang_040/scrapy_dangdang_040/spiders/__pycache__/__init__.cpython-39.pyc b/scrapy_dangdang_040/scrapy_dangdang_040/spiders/__pycache__/__init__.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..4d5c9576fceccc102a595913573beb87bf8f93ec
GIT binary patch
literal 198
zcmYe~<>g`kg2T_95*GsL#~=<eU<7g;fVh|iNTe_XGiWmUtz;+y2_uNF89=V9RZKx;
zNk)F2LVlV;PHJLNUS?i;%+n3Co-b^Dv0?l3jx{f4u8w)WyZOn^1u@0RMTrHK@hORU
v=^z|$U}At>tROQbwWv5IK0Y%qvm`!Vub}c4hfQvNN@-529mo-%ftUdR=@UI7

literal 0
HcmV?d00001

diff --git a/scrapy_dangdang_040/scrapy_dangdang_040/spiders/__pycache__/dang.cpython-39.pyc b/scrapy_dangdang_040/scrapy_dangdang_040/spiders/__pycache__/dang.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..5b004ca94c9b663939366478a22ce113603cee9a
GIT binary patch
literal 961
zcmaJ=zi$&U6t?eIu4z+PU;u%tsskCC3l$xxD2mh~whnZ=rn0QFn;dfPuC}8#(Pc`J
z_!nSmMg&OR5aK_%6;KO1Gdy3~k^%AL_nqJ8=XdYf&$L#nB9M<OTlA-k&{t#3iUURq
zRNV()h+%<3^c*pZ*(ZqE9KFP2JG2<yMRn%~_@JH0;H+3+v_RDg07oHa$m|GhW_57r
zl;|>>IVULem<y4-qPk6!&TbYnF2Mul!}YG#*+vjVRP#<M2Mxm-ZA57=h_dFxh8b&(
zX7h4%bx%a*=T}mJ2^5L8Kve>up`bCwD95LmSra_6a%&syzZluM4U9d(r`80GoZOLX
zxifN-#gccfdE@0?T5h@KU0R+-xs$uOH?}c4yv-1lRoNNdTm7F5?*>6%?6qRHxeQfh
zX~Gjt)*mnL2O=KcY6L;t>jW)EHC;_*+=&w^hVxgnlF?s-3O%gDipprR*NOyHYI9j}
zDx)q*(j$_|IN}gj^JD#>UbhPum_!%uaYl8wr~xf$q{%@nm9AF`M{#jb_>wEgO7XBF
zVj^Ot3roa>4Zkj&g!Xu7!bJQXlJjuBzZk%?jdnKB-85NB50(UEki<!+{r&9i`Q+8b
z*{Ac@A1>a!Z=Zh|fBSseR*|IHfLz@zX+CQHn=4yGwaW&`29Q0KiqDygy#s)-KUc-R
zvxpt+S&NqWTEBgJ(H-90zV56>xoHQg^9eE86H-(O>7}eM%zS~6!#)+$6=@zyaf1qx
z9&tuk+M{uzimK97YSNcN$r^Z+b<e<p;Y<^nm!y0E-{b^Yl`I^*H?6twrtMzRGXcyw
TN)x5<pG-4*icKgJ)3^Ts;=BR@

literal 0
HcmV?d00001

diff --git a/scrapy_dangdang_040/scrapy_dangdang_040/spiders/dang.py b/scrapy_dangdang_040/scrapy_dangdang_040/spiders/dang.py
new file mode 100644
index 0000000..0dbbdbc
--- /dev/null
+++ b/scrapy_dangdang_040/scrapy_dangdang_040/spiders/dang.py
@@ -0,0 +1,39 @@
+import scrapy
+
+
+class DangSpider(scrapy.Spider):
+    name = 'dang'
+    allowed_domains = ['http://category.dangdang.com/cp01.01.02.00.00.00.html']
+    start_urls = ['http://category.dangdang.com/cp01.01.02.00.00.00.html']
+
+    def parse(self, response):
+        print("-----------------------------")
+
+        # pipelines  下载数据
+        # items      定义数据结构
+
+        # src='//ul[@id="component_59"]/li//img/@src'
+        # alt='//ul[@id="component_59"]/li//img/@alt'
+        # price='//ul[@id="component_59"]/li//span[@class="search_now_price"]/text()'
+        # 所有的seletor的对象都可以再次调用xpath方法
+        li_list = response.xpath('//ul[@id="component_59"]/li')
+        for li in li_list:
+            # 图片有懒加载，需要注意更换路径
+            # 第一张图片和其他标签的属性是不一样的
+            # 第一张图片的src可以使用，其他的图片的地址是data-original
+            src = li.xpath('.//img/@data-original').extract_first()
+            if src:
+                src = src
+            else:
+                src = li.xpath('.//img/@src').extract_first()
+
+            name = li.xpath('.//img/@alt').extract_first()
+            price = li.xpath(
+                './/span[@class="search_now_price"]/text()').extract_first()
+
+            print(src, name, price)
+
+        # price = response.xpath(
+        #     '//ul[@id="component_59"]/li//span[@class="search_now_price"]/text()')
+        # print(price.extract())
+        pass