add爬虫

Author: LockGit

crawl_360/crawl_360/__init__.py

@@ -0,0 +1,26 @@
+# -*- 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 Crawl360Item(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass
+
+
+class ButianItem(scrapy.Item):
+    author = scrapy.Field()  # 作者
+    company_name = scrapy.Field()  # 企业名称
+    vul_name = scrapy.Field()  # SQL注入漏洞
+    vul_level = scrapy.Field()  # 高危
+    vul_type = scrapy.Field()  # 通用型
+    vul_money = scrapy.Field()  # 奖励
+    vul_find_time = scrapy.Field()  # 时间
+    link_url = scrapy.Field()  # 抓取url
+    create_time = scrapy.Field()  # 创建时间

crawl_360/crawl_360/__init__.pyc

@@ -0,0 +1,103 @@
+# -*- 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 Crawl360SpiderMiddleware(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 Crawl360DownloaderMiddleware(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)

crawl_360/crawl_360/items.py

@@ -0,0 +1,5 @@
+#!/usr/bin/env python
+# encoding: utf-8
+# author: Lock
+# time: 2018/4/28 11:35
+

crawl_360/crawl_360/items.pyc

@@ -0,0 +1,31 @@
+#!/usr/bin/env python
+# encoding: utf-8
+# author: Lock
+# time: 2018/4/28 11:36
+
+from sqlalchemy import create_engine
+from sqlalchemy.orm import sessionmaker
+from sqlalchemy.ext.declarative import declarative_base
+
+# 创建对象的基类:
+Base = declarative_base()
+
+CONFIG = {
+    'db_host': '127.0.0.1',
+    'db_user': 'root',
+    'db_pass': '',
+    'db_port': 3306,
+    'db_name': 'crawl'
+}
+
+# 初始化数据库连接:
+engine = create_engine('mysql+mysqlconnector://%s:%s@%s:%s/%s' % (
+    CONFIG.get('db_user'),
+    CONFIG.get('db_pass'),
+    CONFIG.get('db_host'),
+    CONFIG.get('db_port'),
+    CONFIG.get('db_name'),
+))
+
+# 创建DBSession类型:
+DBSession = sessionmaker(bind=engine)

crawl_360/crawl_360/middlewares.py

@@ -0,0 +1,20 @@
+# coding: utf-8
+from sqlalchemy import Column, DateTime, Integer, Numeric, String, text
+from sqlalchemy.ext.declarative import declarative_base
+
+Base = declarative_base()
+metadata = Base.metadata
+
+
+class Butian(Base):
+    __tablename__ = 'butian'
+
+    id = Column(Integer, primary_key=True)
+    author = Column(String(100), nullable=False, server_default=text("''"))
+    company_name = Column(String(100), nullable=False, server_default=text("''"))
+    vul_level = Column(String(100), nullable=False, server_default=text("''"))
+    vul_name = Column(String(100), nullable=False, server_default=text("''"))
+    vul_money = Column(Numeric(10, 2), nullable=False)
+    vul_find_time = Column(DateTime, nullable=False, server_default=text("'0000-00-00 00:00:00'"))
+    link_url = Column(String(255), nullable=False, server_default=text("''"))
+    create_time = Column(DateTime, nullable=False)

crawl_360/crawl_360/models/__init__.py

@@ -0,0 +1,29 @@
+# -*- 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
+from crawl_360.items import ButianItem
+from crawl_360.models.db import DBSession
+from crawl_360.models.models import Butian
+
+
+class Crawl360Pipeline(object):
+    def __init__(self):
+        self.db_session = DBSession()
+
+    def process_item(self, item, spider):
+        if isinstance(item, ButianItem):
+            data_item = Butian(**item)
+            # 数据入库
+            self.db_session.add(data_item)
+            try:
+                self.db_session.commit()
+            except Exception, e:
+                print e.message
+                self.db_session.rollback()
+        return item
+
+    def close_spider(self, spider):
+        self.db_session.close()

crawl_360/crawl_360/models/__init__.pyc

@@ -0,0 +1,12 @@
+CREATE TABLE butian (
+  id INT(11) UNSIGNED NOT NULL AUTO_INCREMENT COMMENT '自增id',
+  author VARCHAR(100) not null DEFAULT '' COMMENT '作者',
+  company_name VARCHAR(100) NOT NULL DEFAULT '' COMMENT '公司名',
+  vul_level VARCHAR(100) not null DEFAULT '' COMMENT '漏洞级别',
+  vul_name VARCHAR(100) not null DEFAULT '' COMMENT '漏洞名',
+  vul_money DECIMAL(10,2) not NULL DEFAULT 0 COMMENT '漏洞奖金',
+  vul_find_time DATETIME not NULL DEFAULT '0000-00-00 00:00:00' COMMENT '漏洞发现时间',
+  link_url VARCHAR(255) not null DEFAULT '' COMMENT '页面url',
+  create_time TIMESTAMP not null DEFAULT current_timestamp COMMENT '创建时间',
+  PRIMARY KEY (id)
+)ENGINE=INNODB DEFAULT CHARSET utf8;

crawl_360/crawl_360/models/db.py

@@ -0,0 +1,90 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for crawl_360 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 = 'crawl_360'
+
+SPIDER_MODULES = ['crawl_360.spiders']
+NEWSPIDER_MODULE = 'crawl_360.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'crawl_360 (+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 = {
+#    'crawl_360.middlewares.Crawl360SpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'crawl_360.middlewares.Crawl360DownloaderMiddleware': 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 = {
+    'crawl_360.pipelines.Crawl360Pipeline': 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'

crawl_360/crawl_360/models/db.pyc

@@ -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.

crawl_360/crawl_360/models/models.py

@@ -0,0 +1,34 @@
+# -*- coding: utf-8 -*-
+import scrapy
+
+from crawl_360.items import ButianItem
+import time
+
+
+class ButianSpider(scrapy.Spider):
+    name = 'butian'
+    allowed_domains = ['butian.360.cn/Loo', 'butian.360.cn']
+    start_urls = ['http://butian.360.cn/Loo/']
+
+    def parse(self, response):
+        self.logger.info('strart parse dst page ...')
+        item = ButianItem()
+        # import ipdb
+        # ipdb.set_trace()
+        for sel in response.xpath('//ul[@class="loopListBottom"]/li'):
+            item['author'] = sel.xpath('dl/dd/span[1]/text()').extract_first(default='').strip()
+            item['company_name'] = sel.xpath('dl/dd/a/text()').extract_first(default='').strip()
+            item['vul_name'] = sel.xpath('dl/dd/span[3]/text()').extract_first(default='').replace(u'的一个', '').strip()
+            item['vul_level'] = sel.xpath('dl/dd[2]/strong[@class="loopHigh"]/text()').extract_first(default='').strip()
+            item['vul_money'] = sel.xpath('dl/p[@class="loopJiangjin"]/text()').extract_first(default=0)
+            item['vul_find_time'] = sel.xpath('dl/dd[2]/em/text()').extract_first(default='').strip()
+            item['link_url'] = response.url.strip()
+            item['create_time'] = time.strftime("%Y-%m-%d %H:%M:%S")
+            self.logger.info('find item data is:%s' % (item,))
+            yield item
+
+        next_page = response.xpath(u'//div[@class="btPage page"]/a[contains(text(),"下一页")]/@href').extract_first()
+        if next_page is not None:
+            next_page = response.urljoin(next_page)
+            self.logger.info('next page url is:%s' % (next_page,))
+            yield scrapy.Request(url=next_page, callback=self.parse)

crawl_360/crawl_360/models/models.pyc

@@ -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 = crawl_360.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = crawl_360