爬取当当网图片，书名，价格

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

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

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)

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

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'

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.

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