初始化

.idea/.gitignore

+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/

.idea/deployment.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="PublishConfigData" autoUpload="Always" serverName="souhcars_linux" remoteFilesAllowedToDisappearOnAutoupload="false">
+    <serverData>
+      <paths name="souhcars_linux">
+        <serverdata>
+          <mappings>
+            <mapping deploy="/souhcars" local="$PROJECT_DIR$" web="/" />
+          </mappings>
+        </serverdata>
+      </paths>
+    </serverData>
+    <option name="myAutoUpload" value="ALWAYS" />
+  </component>
+</project>
\ No newline at end of file

.idea/inspectionProfiles/Project_Default.xml

+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="22">
+            <item index="0" class="java.lang.String" itemvalue="zipp" />
+            <item index="1" class="java.lang.String" itemvalue="SQLAlchemy" />
+            <item index="2" class="java.lang.String" itemvalue="wcwidth" />
+            <item index="3" class="java.lang.String" itemvalue="sqlacodegen" />
+            <item index="4" class="java.lang.String" itemvalue="urllib3" />
+            <item index="5" class="java.lang.String" itemvalue="pycrypto" />
+            <item index="6" class="java.lang.String" itemvalue="locust" />
+            <item index="7" class="java.lang.String" itemvalue="jupyter-core" />
+            <item index="8" class="java.lang.String" itemvalue="pycairo" />
+            <item index="9" class="java.lang.String" itemvalue="jupyter-client" />
+            <item index="10" class="java.lang.String" itemvalue="MarkupSafe" />
+            <item index="11" class="java.lang.String" itemvalue="pygobject" />
+            <item index="12" class="java.lang.String" itemvalue="chardet" />
+            <item index="13" class="java.lang.String" itemvalue="Django" />
+            <item index="14" class="java.lang.String" itemvalue="PyYAML" />
+            <item index="15" class="java.lang.String" itemvalue="certifi" />
+            <item index="16" class="java.lang.String" itemvalue="pyDes" />
+            <item index="17" class="java.lang.String" itemvalue="PyMySQL" />
+            <item index="18" class="java.lang.String" itemvalue="pytz" />
+            <item index="19" class="java.lang.String" itemvalue="requests" />
+            <item index="20" class="java.lang.String" itemvalue="djangorestframework" />
+            <item index="21" class="java.lang.String" itemvalue="idna" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>
\ No newline at end of file

.idea/inspectionProfiles/profiles_settings.xml

+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>
\ No newline at end of file

.idea/misc.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.7 (souhcars)" project-jdk-type="Python SDK" />
+</project>
\ No newline at end of file

.idea/modules.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/souhcars.iml" filepath="$PROJECT_DIR$/.idea/souhcars.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file

.idea/souhcars.iml

+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="Python 3.7 (souhcars)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>
\ No newline at end of file

.idea/sshConfigs.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="SshConfigs">
+    <configs>
+      <sshConfig authType="PASSWORD" host="47.100.68.39" id="8dd09262-fa1d-4e37-872c-8714176cc970" port="22" nameFormat="DESCRIPTIVE" username="root" useOpenSSHConfig="true" />
+    </configs>
+  </component>
+</project>
\ No newline at end of file

.idea/vcs.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>
\ No newline at end of file

.idea/webServers.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="WebServers">
+    <option name="servers">
+      <webServer id="b8ac0761-a4fd-456b-a030-372b2f3716e8" name="souhcars_linux">
+        <fileTransfer rootFolder="/usr/local/python/" accessType="SFTP" host="47.100.68.39" port="22" sshConfigId="8dd09262-fa1d-4e37-872c-8714176cc970" sshConfig="root@47.100.68.39:22 password">
+          <advancedOptions>
+            <advancedOptions controlEncoding="UTF-8" dataProtectionLevel="Private" keepAliveTimeout="0" passiveMode="true" shareSSLContext="true" />
+          </advancedOptions>
+        </fileTransfer>
+      </webServer>
+    </option>
+  </component>
+</project>
\ No newline at end of file

begin.py

+from scrapy import cmdline
+
+cmdline.execute('scrapy crawl souh_cars'.split())
\ No newline at end of file

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 = souhcars.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = souhcars

souhcars/items.py

+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class BrandItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    brand_id = scrapy.Field()  # 品牌
+    brand_name = scrapy.Field()  # 品牌名称
+
+
+class SeriesItem(scrapy.Item):
+    brand_id = scrapy.Field()
+    maker_name = scrapy.Field()
+    maker_id = scrapy.Field()
+    series_id = scrapy.Field()
+    series_name = scrapy.Field()
+
+
+class StyleItem(scrapy.Item):
+    series_id = scrapy.Field()
+    style_id = scrapy.Field()
+    style_name = scrapy.Field()
+    conf = scrapy.Field()

souhcars/middlewares.py

+# 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 SouhcarsSpiderMiddleware:
+    # 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 SouhcarsDownloaderMiddleware:
+    # 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)

souhcars/pipelines.py

+# 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
+import pymysql as pymysql
+
+import souhcars.items
+
+
+class SouhcarsPipeline:
+    def __init__(self):
+        self.host = "47.100.68.39"
+        self.port = 3310
+        self.database = "db_spider"
+        self.user = "root"
+        self.password = "dip-test"
+        self.con = pymysql.connect(host=self.host, port=self.port, database=self.database, user=self.user,
+                                   password=self.password)
+        self.cu = self.con.cursor()
+        print("实例化了数据库")
+
+    def process_item(self, item, spider):
+        if isinstance(item, souhcars.items.BrandItem):
+            sql_q = 'select id from t_brand_souh where brand_id = "{}"'.format(item['brand_id'])
+            sql = 'insert into t_brand_souh (brand_id, brand_name) values ("{}","{}")' \
+                .format(item['brand_id'], item['brand_name'])
+            self.con.ping(reconnect=True)
+            self.cu.execute(sql_q)
+            if str(self.cu.fetchone()) != 'None':
+                return
+            self.cu.execute(sql)
+            self.con.commit()
+
+        elif isinstance(item, souhcars.items.SeriesItem):
+            sql_q = 'select id from t_series_souh where series_id = "{}"'.format(item['series_id'])
+            sql = 'insert into t_series_souh (brand_id, maker_id, maker_name, series_id, series_name)' \
+                  ' values ("{}","{}","{}","{}","{}")'.format(item['brand_id'], item['maker_id'], item['maker_name'],
+                                                              item['series_id'], item['series_name'])
+            self.con.ping(reconnect=True)
+            self.cu.execute(sql_q)
+            if str(self.cu.fetchone()) != 'None':
+                return
+            self.cu.execute(sql)
+            self.con.commit()
+
+        elif isinstance(item, souhcars.items.StyleItem):
+            sql_q = 'select id from t_style_souh where style_id = "{}"'.format(item['style_id'])
+            sql = 'insert into t_style_souh (series_id, style_id, style_name, conf)' \
+                  ' values ("{}","{}","{}","{}")'.format(item['series_id'], item['style_id'], item['style_name'],
+                                                         item['conf'])
+            self.con.ping(reconnect=True)
+            self.cu.execute(sql_q)
+            if str(self.cu.fetchone()) != 'None':
+                return
+            self.cu.execute(sql)
+            self.con.commit()
+
+    def __del__(self):
+        self.cu.close()
+        self.con.close()

souhcars/settings.py

+# Scrapy settings for souhcars 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 = 'souhcars'
+
+SPIDER_MODULES = ['souhcars.spiders']
+NEWSPIDER_MODULE = 'souhcars.spiders'
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+# USER_AGENT = 'souhcars (+http://www.yourdomain.com)'
+USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) ' \
+             'Chrome/99.0.4844.82 Safari/537.36'
+
+# 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 = 1
+# 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
+LOG_LEVEL = "INFO"
+# Override the default request headers:
+DEFAULT_REQUEST_HEADERS = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
+                  'Chrome/99.0.4844.82 Safari/537.36'
+}
+
+# Enable or disable spider middlewares
+# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+# SPIDER_MIDDLEWARES = {
+#    'souhcars.middlewares.SouhcarsSpiderMiddleware': 543,
+# }
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+# DOWNLOADER_MIDDLEWARES = {
+#    'souhcars.middlewares.SouhcarsDownloaderMiddleware': 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 = {
+    'souhcars.pipelines.SouhcarsPipeline': 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'

souhcars/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.

souhcars/spiders/souh_cars.py

+import json
+import re
+from json import JSONDecodeError
+
+import scrapy
+
+from souhcars.items import BrandItem, SeriesItem, StyleItem
+from scrapy.spidermiddlewares.httperror import HttpError
+from twisted.internet.error import DNSLookupError, TCPTimedOutError
+
+
+class SouhCarsSpider(scrapy.Spider):
+    name = 'souh_cars'
+    allowed_domains = ['auto.sohu.com']
+    start_urls = ['http://db.auto.sohu.com/home/']
+
+    def parse(self, response, **kwargs):
+        # flag = 0
+        all_brand_li = response.xpath('//*[@id="treeNav"]/ul/li[@class="close_child"]')
+        for i in all_brand_li:
+            # 保存品牌
+            brand = BrandItem()
+            brand['brand_name'] = i.xpath('h4/a/text()').extract()[1]
+            brand['brand_id'] = i.xpath('h4/a').attrib.get('id')
+            yield brand
+
+            # 保存车系
+            all_maker_li = i.xpath("ul")
+            series = SeriesItem()
+            series['brand_id'] = i.xpath('h4/a').attrib.get('id')
+            for j in all_maker_li:
+                series['maker_id'] = j.xpath('li[@class="con_tit"]/a').attrib.get('id')
+                series['maker_name'] = j.xpath('li[@class="con_tit"]/a/text()').extract()[1].strip()
+                all_series_li = j.xpath('li/a[@class="model-a"]')
+                for k in all_series_li:
+                    try:
+                        series['series_name'] = k.xpath('text()').extract()[1].strip()
+                    except IndexError as e:
+                        print(e)
+                        return
+                    series['series_id'] = k.attrib.get('id')
+                    yield series
+                    # 车的参数配置信息地址
+                    style_url ='http:'+ k.attrib.get('href') +'/trim.html'
+                    yield scrapy.Request(url=style_url, callback=self.parse_years, errback=self.parse_err)
+
+    def parse_years(self, response, **kwargs):
+        all_year = response.xpath('//*[@id="yearp"]/a[@target="_blank"]/text()')
+        # 如果只有一个年款，那么上面方式查不到年款，如果查不到，就是用下面方式再查一次
+        if len(all_year) == 0:
+            # print(response.url)
+            all_year = response.xpath('//*[@id="yearp"]/a/text()')
+        for i in all_year:
+            style_url2 = response.url.replace('trim.html', 'trim_year{}.html'.format(i.root[0:4]))
+            yield scrapy.Request(url=style_url2, callback=self.parse_style, errback=self.parse_err)
+
+    def parse_style(self, response, **kwargs):
+        regex = re.compile(r"var trimParam = ([\s\S]*?)}];")
+        try:
+            all_style = json.loads(response.selector.re(regex)[0] + "}]")
+        except JSONDecodeError as e:
+            print(e)
+            print(response.selector.re(regex)[0])
+            print(response.url)
+            return
+        for i in all_style:
+            style = StyleItem()
+            style['style_id'] = i.get('SIP_T_ID')
+            style['style_name'] = i.get('subbrandName') + ' ' + i.get('modelName') + ' ' + str(i.get('SIP_T_YEAR'))\
+                                  + '款 ' + i.get('SIP_T_NAME')
+            style['series_id'] = i.get('SIP_T_MODELID')
+            style['conf'] = str(i).replace("\"", "\\\"")
+            yield style
+
+    def parse_err(self, failure):
+        if failure.check(HttpError):
+            response = failure.value.response
+            print('HttpError on {0}'.format(response.url))
+
+        elif failure.check(DNSLookupError):
+            request = failure.request
+            print('DNSLookupError on {0}'.format(request.url))
+
+        elif failure.check(TimeoutError, TCPTimedOutError):
+            request = failure.request
+            print('TimeoutError on {0}'.format(request.url))
\ No newline at end of file