上传文件至 'zjjtPro'

浙江交通职业技术学院各个学院的新闻爬取

zjjtPro/items.py

@@ -0,0 +1,16 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class ZjjtproItem(scrapy.Item):
+    index = scrapy.Field()
+    img_src = scrapy.Field()
+    title = scrapy.Field()
+    news_id = scrapy.Field()
+    content = scrapy.Field()
+    date = scrapy.Field()
+    author = scrapy.Field()

zjjtPro/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 ZjjtproSpiderMiddleware:
+    # 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 ZjjtproDownloaderMiddleware:
+    # 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)

zjjtPro/pipelines.py

@@ -0,0 +1,70 @@
+# 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
+import pymysql
+
+
+class ZjjtproPipeline:
+    def process_item(self, item, spider):
+        return item
+
+# 数据库存储管道
+class mysqlPileLine(object):
+    conn = None  # 链接对象
+    cursor = None  # 游标对象
+
+    def open_spider(self, spider):
+        # 实例化链接对象
+        self.conn = pymysql.Connect(host='127.0.0.1', port=3306, user='root', password='root', db='zjjt', charset='utf8')
+
+    def process_item(self, item, spider):
+        # 实例化游标对象
+        self.cursor = self.conn.cursor()
+        index = item['index']
+        try:
+            if index == 0:
+                self.cursor.execute('insert into lqxy values("%s", "%s", "%s", "%s", "%s")'%(
+                    item['news_id'], item['title'], item['date'], item['content'], item['img_src']))
+                self.conn.commit()
+            elif index == 1:
+                self.cursor.execute('insert into qcxy values("%s", "%s", "%s", "%s", "%s")'%(
+                    item['news_id'], item['title'], item['date'], item['content'], item['img_src']))
+                self.conn.commit()
+            elif index == 2:
+                self.cursor.execute('insert into hyxy values("%s", "%s", "%s", "%s", "%s")'%(
+                    item['news_id'], item['title'], item['date'], item['content'], item['img_src']))
+                self.conn.commit()
+            elif index == 3:
+                self.cursor.execute('insert into hkxy values("%s", "%s", "%s", "%s", "%s")'%(
+                    item['news_id'], item['title'], item['date'], item['content'], item['img_src']))
+                self.conn.commit()
+            elif index == 4:
+                self.cursor.execute('insert into gdxy values("%s", "%s", "%s", "%s", "%s")'%(
+                    item['news_id'], item['title'], item['date'], item['content'], item['img_src']))
+                self.conn.commit()
+            elif index == 5:
+                self.cursor.execute('insert into zhxy values("%s", "%s", "%s", "%s", "%s")'%(
+                    item['news_id'], item['title'], item['date'], item['content'], item['img_src']))
+                self.conn.commit()
+            elif index == 6:
+                self.cursor.execute('insert into ysxy values("%s", "%s", "%s", "%s", "%s")'%(
+                    item['news_id'], item['title'], item['date'], item['content'], item['img_src']))
+                self.conn.commit()
+            elif index == 7:
+                self.cursor.execute('insert into rwxy values("%s", "%s", "%s", "%s", "%s")'%(
+                    item['news_id'], item['title'], item['date'], item['content'], item['img_src']))
+                self.conn.commit()
+        except Exception as e:
+            print(e)
+            self.conn.rollback()
+        return item
+
+    def close_spider(self, spider):
+        # self.cursor.close()
+        # self.conn.close()
+        pass

zjjtPro/settings.py

@@ -0,0 +1,90 @@
+# Scrapy settings for zjjtPro 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 = 'zjjtPro'
+
+SPIDER_MODULES = ['zjjtPro.spiders']
+NEWSPIDER_MODULE = 'zjjtPro.spiders'
+
+
+LOG_LEVEL = 'ERROR'
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36 OPR/26.0.1656.60'
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = False
+
+# 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 = {
+#    'zjjtPro.middlewares.ZjjtproSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'zjjtPro.middlewares.ZjjtproDownloaderMiddleware': 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 = {
+   # 'zjjtPro.pipelines.ZjjtproPipeline': 300,
+   'zjjtPro.pipelines.mysqlPileLine': 301,
+}
+
+# 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'