Initial commit

dog_project/cmdline.py

+from scrapy.cmdline import execute
+
+import sys
+
+import os
+
+sys.path.append(os.path.dirname(os.path.abspath(__file__)))
+
+execute(['scrapy', 'crawl', 'dog_info'])
\ No newline at end of file

dog_project/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class DogProjectItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass
+
+
+class DogInfoItem(scrapy.Item):
+    name = scrapy.Field()
+    name_en = scrapy.Field()
+    guide_price = scrapy.Field()
+    avatar = scrapy.Field()

dog_project/middlewares.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class DogProjectSpiderMiddleware(object):
+    # 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, dict 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 Response, dict
+        # 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 DogProjectDownloaderMiddleware(object):
+    # 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)

dog_project/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
+import traceback
+
+import pymysql
+import logging
+import six
+
+from dog_project.items import DogInfoItem
+
+logger = logging.getLogger('dog_pipeline')
+
+MYSQL_HOST = 'localhost'
+MYSQL_DBNAME = 'dog'
+MYSQL_USER = 'root'
+MYSQL_PASSWD = 'root'
+
+table_name_dict = {
+    DogInfoItem: 'dog_info'
+}
+
+def get_table_name(item):
+    if type(item) in table_name_dict.keys():
+        return table_name_dict[type(item)]
+    return None
+
+
+class DogProjectPipeline(object):
+
+    def open_spider(self, spider):
+        self.connect = pymysql.connect(
+            host=MYSQL_HOST,
+            db=MYSQL_DBNAME,
+            user=MYSQL_USER,
+            passwd=MYSQL_PASSWD,
+            charset='utf8mb4',
+            use_unicode=True)
+        self.cursor = self.connect.cursor()
+        # logger.info('每次一个spider开启的时候，重启对应的pipleline_sql')
+
+    def process_item(self, item, spider):
+        table_name = get_table_name(item)
+        if table_name is None:
+            return
+        sql = ''
+        try:
+            # logger.info(str(item))
+            sql = self.insert_or_update_sql(item, table_name=table_name)
+            self.cursor.execute(sql)
+            self.connect.commit()
+        except Exception as error:
+            logger.debug(sql)
+            traceback.print_exc()
+
+    def insert_or_update_sql(self, item, table_name):
+
+        col_str = ''
+        row_str = ''
+        for key in item.keys():
+            col_str = col_str + " `" + key + "`,"
+            row_str = "{}{},".format(row_str, self.sql_quote(item[key]))
+        sql = "INSERT INTO {} ({}) VALUES ({}) ON DUPLICATE KEY UPDATE ".format(table_name, col_str[1:-1], row_str[:-1])
+        for (key, value) in six.iteritems(item):
+            if value is not None:
+                sql += "`{}` = {}, ".format(key, self.sql_quote(value))
+        sql = sql[:-2]
+
+        sql.replace("'None'", 'null')
+        return sql
+
+    @staticmethod
+    def sql_quote(value):
+        if value is None:
+            return 'NULL'
+        return "'{}'".format(str(value).replace("'", "''"))
+

dog_project/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for dog_project project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     https://doc.scrapy.org/en/latest/topics/settings.html
+#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'dog_project'
+
+SPIDER_MODULES = ['dog_project.spiders']
+NEWSPIDER_MODULE = 'dog_project.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'dog_project (+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://doc.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://doc.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'dog_project.middlewares.DogProjectSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'dog_project.middlewares.DogProjectDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See https://doc.scrapy.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'dog_project.pipelines.DogProjectPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://doc.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://doc.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'

dog_project/spiders/__init__.py

+# 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.

dog_project/spiders/dog.py

+import scrapy
+
+from dog_project.items import DogInfoItem
+
+
+class DogInfoSpider(scrapy.Spider):
+
+    name = 'dog_info'
+
+    start_urls = ['http://www.goupuzi.com/thread-htm-fid-4.html']
+
+
+
+    def parse(self, response):
+        for li in response.css('.breed_content li'):
+            # 狗狗名称
+            dog_name = li.css('.breed_dogs_name::text').extract()[0]
+            ch_name = dog_name[0 : dog_name.find('（')].strip()
+            en_name = dog_name[dog_name.find('（') + 1 : dog_name.find('）')].strip()
+            # 狗狗指导价
+            guide_price = li.css('.breed_dogs_guida::text').extract()[0].replace('指导价：', '').strip()
+            # 狗狗头像地址
+            avatar = li.css('.breed_conzara_l img::attr(src)').extract()[0]
+            dog_info_item = DogInfoItem()
+            dog_info_item['name'] = ch_name
+            dog_info_item['name_en'] = en_name
+            dog_info_item['guide_price'] = guide_price
+            dog_info_item['avatar'] = avatar
+            # yield dog_info_item
+            # 狗狗介绍
+            introduce = li.css('.breed_dogs_ency a')[2].css('::attr(href)').extract()[0]
+            print(introduce)
+            yield scrapy.Request(introduce, self.parse_introduction)
+
+    def parse_introduction(self, response):
+
+
+        print(response.css('.quanjieshao1 h2::text').extract())
+
+
+        pass
+

scrapy.cfg

+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
+
+[settings]
+default = dog_project.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = dog_project