车标爬虫

NO46/chebiao/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 ChebiaoItem(scrapy.Item):
+    file_url = scrapy.Field()
+    file_name = scrapy.Field()
+    files = scrapy.Field()
+    file_path = scrapy.Field()

NO46/chebiao/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 ChebiaoSpiderMiddleware:
+    # 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 ChebiaoDownloaderMiddleware:
+    # 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)

NO46/chebiao/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
+from scrapy import Request
+from itemadapter import ItemAdapter
+from scrapy.pipelines.files import FilesPipeline
+from urllib.parse import urlparse
+import os
+from unrar import rarfile
+
+
+class ChebiaoPipeline:
+    def process_item(self, item, spider):
+        path = os.path.join(os.getcwd(), "files", item['file_path'])
+        extract_path = os.path.join(os.getcwd(), "files")
+        rf = rarfile.RarFile(path, pwd="www.chebiao.net")
+        rf.extractall(path=extract_path, pwd="www.chebiao.net")
+        return item
+
+
+class ChebiaoFilePipeline(FilesPipeline):
+
+    def get_media_requests(self, item, info):
+        print("--get_media_requests--start-----")
+        print("正在下载：", item['file_name'])
+        print("--get_media_requests--end-----")
+        yield Request(item['file_url'], meta={'title': item['file_name']})
+
+    def file_path(self, request, response=None, info=None):
+        print("--file_path--start-----")
+        file_name = request.meta.get('title') + ".rar"
+        print("--file_path--end-----")
+        return file_name
+
+    def item_completed(self, results, item, info):
+        print("--item_completed--start-----")
+        print(results)
+        print("下载完毕")
+        file_path = [x['path'] for ok, x in results if ok]
+        adapter = ItemAdapter(item)
+        adapter['file_path'] = file_path[0]
+        print("--item_completed--end--------")
+        return item

NO46/chebiao/settings.py

+# Scrapy settings for chebiao 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 = 'chebiao'
+
+SPIDER_MODULES = ['chebiao.spiders']
+NEWSPIDER_MODULE = 'chebiao.spiders'
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.81 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 = 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-Encoding': 'gzip, deflate',
+    'Accept-Language': 'zh-CN,zh;q=0.9',
+    'Host': 'www.chebiao.net',
+    'Referer': 'http://www.chebiao.net/logo.php'
+}
+
+# Enable or disable spider middlewares
+# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+# SPIDER_MIDDLEWARES = {
+#    'chebiao.middlewares.ChebiaoSpiderMiddleware': 543,
+# }
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+# DOWNLOADER_MIDDLEWARES = {
+#    'chebiao.middlewares.ChebiaoDownloaderMiddleware': 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 = {
+    'chebiao.pipelines.ChebiaoFilePipeline': 100,
+    'chebiao.pipelines.ChebiaoPipeline': 200,
+}
+FILES_STORE = './files'
+
+# 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'
+LOG_LEVEL = 'WARNING'
\ No newline at end of file

NO46/chebiao/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.

NO46/chebiao/spiders/cb.py

+import scrapy
+from chebiao.items import ChebiaoItem
+from urllib.parse import urlparse
+
+
+class CbSpider(scrapy.Spider):
+    name = 'cb'
+    allowed_domains = ['chebiao.net']
+    start_urls = ['http://www.chebiao.net/domestic.php', 'http://www.chebiao.net/es.php',
+                  'http://www.chebiao.net/jsk.php', 'http://www.chebiao.net/other.php',
+                  'http://www.chebiao.net/famous.php']
+
+    def parse(self, response):
+        down_url = "http://www.chebiao.net/download.php"
+        dds = response.xpath("//div[@class='box2']/dl/dd")
+        for dd in dds:
+            item = ChebiaoItem()
+            name = dd.xpath('./a/text()').extract()[0]
+            url = dd.xpath('./a/@href').extract()[0]
+            url = down_url + "?" + urlparse(url).query
+            item['file_name'] = name
+            item['file_url'] = url
+
+            yield item

NO46/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 = chebiao.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = chebiao