注释内容

Author: long.zhang

.idea/misc.xml

@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = tutorial.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = tutorial

.idea/modules.xml

@@ -0,0 +1,19 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+import scrapy
+
+class EtherscanProductRaw(scrapy.Item):
+    '''定义需要格式化的内容（或是需要保存到数据库的字段）'''
+    name = scrapy.Field()
+    TxHash = scrapy.Field()
+    Block = scrapy.Field()
+    From_account = scrapy.Field()
+    To_account = scrapy.Field()
+    Value = scrapy.Field()
+    TxFee = scrapy.Field()
+    create_time = scrapy.Field()
+    operate_type = scrapy.Field()

.idea/tutorial.iml

@@ -0,0 +1,56 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class TutorialSpiderMiddleware(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)

.idea/workspace.xml

@@ -0,0 +1,42 @@
+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+from twisted.enterprise import adbapi
+import MySQLdb.cursors
+class DBPipeline(object):
+
+    def __init__(self):
+        self.db_pool = adbapi.ConnectionPool('MySQLdb',
+                                             db='capture',
+                                             user='root',
+                                             passwd='111111',
+                                             cursorclass=MySQLdb.cursors.DictCursor,
+                                             use_unicode=True)
+
+    def process_item(self, item, spider):
+        query = self.db_pool.runInteraction(self._conditional_insert, item)
+        query.addErrback(self.handle_error)
+        return item
+
+    def _conditional_insert(self, tx, item):
+        try:
+            sql = 'select * from transfer_records where TxHash = "{TxHash}"'.format(**item)
+            print sql
+            tx.execute(sql)
+            result = tx.fetchone()
+            if result:
+                pass
+            else:
+                sql = 'insert into transfer_records(name,TxHash,Block,From_account,To_account,Value,TxFee,create_time,operate_type) values("{name}","{TxHash}","{Block}","{From_account}","{To_account}",{Value},{TxFee},"{create_time}","{operate_type}")'.format(**item)
+                tx.execute(sql)
+        except Exception,e:
+            print 'e'*20
+            print sql
+            print e
+
+    def handle_error(self, e):
+        print 'error',e

scrapy.cfg

@@ -0,0 +1,96 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for tutorial project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'tutorial'
+
+SPIDER_MODULES = ['tutorial.spiders']
+NEWSPIDER_MODULE = 'tutorial.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'tutorial (+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 http://scrapy.readthedocs.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 http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'tutorial.middlewares.TutorialSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'tutorial.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+#ITEM_PIPELINES = {
+#    'tutorial.pipelines.TutorialPipeline': 300,
+#}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://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
+
+
+#Mysql数据库的配置信息
+MYSQL_HOST = '127.0.0.1'
+MYSQL_DBNAME = 'capture'         #数据库名字，请修改
+MYSQL_USER = 'root'             #数据库账号，请修改
+MYSQL_PASSWD = '111111'         #数据库密码，请修改
+
+MYSQL_PORT = 3306               #数据库端口，在dbhelper中使用
+
+ITEM_PIPELINES = {
+    'tutorial.pipelines.DBPipeline': 300,#保存到mysql数据库
+}
+

tutorial/__init__.py

@@ -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.

tutorial/items.py

@@ -0,0 +1,102 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# @Time    : 2017/12/1 13:57
+# @Author  : long.zhang
+# @Contact : [email protected]
+# @Site    : 
+# @File    : amazon.py
+# @Software: PyCharm
+# @Desc    :
+from tutorial.items import EtherscanProductRaw
+import scrapy
+import re
+import time
+
+from bs4 import BeautifulSoup
+
+def getDict4str(strsource, match=':'):
+    outdict = {}
+    lists = strsource.split('\n')
+    for list in lists:
+        list = list.strip()
+        if list:
+            strbegin = list.find(match)
+            outdict[list[:strbegin]] = list[strbegin + 1:] if strbegin != len(list) else ''
+    return outdict
+HEADER = '''
+        accept:text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8
+        accept-encoding:gzip, deflate, br
+        accept-language:zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7
+        cache-control:max-age=0
+        upgrade-insecure-requests:1
+        User-Agent:{}
+        '''
+header = getDict4str(HEADER.format(
+    r'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'))
+
+class Etherscan(scrapy.Spider):
+    name = 'etherscan'
+    def __init__(self, id_name=None, *args, **kwargs):
+        super(Etherscan, self).__init__(*args, **kwargs)
+        self.start_urls = ['https://etherscan.io/address/{}'.format(id_name)]
+        self.id_name = id_name
+    def parse(self, response):
+        formatUrl = 'https://etherscan.io/txs?a={}&p={}'
+        soup = BeautifulSoup(response.body, 'lxml')
+        num = int(soup.find('span', {'title': "Normal Transactions"}).getText().strip('\n').strip()[:-4].strip())
+        if num%50 == 0:
+            page = num/36
+        else:
+            page = num / 36+1
+
+        for x in range(page):
+            x+=1
+            url = formatUrl.format(self.id_name, x)
+            print url
+            yield scrapy.Request(url=url, meta={"id_name": self.id_name},
+                                 callback=self.parse_url)
+    def parse_url(self, response):
+        soup = BeautifulSoup(response.body, 'lxml')
+        datas = soup.find('table', {'class': "table table-hover "}).find('tbody').findAll('tr')
+        now = time.time()
+        for sourceData in datas:
+            infos = sourceData.findAll('td')
+            if len(infos) != 8:
+                break
+            resultData = EtherscanProductRaw()
+            resultData['name'] = response.meta.get('id_name')
+            if infos[0].find('font'):
+                continue
+
+            resultData['TxHash'] = infos[0].find('span').getText().strip()
+            resultData['Block'] = int(infos[1].getText().strip())
+            resultData['From_account'] = infos[3].find('span').getText().strip()
+            resultData['To_account'] = infos[5].find('span').getText().strip()
+            value = ''.join(infos[6].getText().split(','))
+            resultData['Value'] = float(value[:-5].strip() if value.find('Ether') !=-1 else value.strip())
+            TxFee = ''.join(infos[7].getText().split(','))
+            resultData['TxFee'] = float(TxFee[:-5].strip() if TxFee.find('Ether') !=-1 else TxFee.strip())
+
+            # import pdb
+            # pdb.set_trace()
+            Age = infos[2].find('span').getText().strip()
+            pattern_hr = re.compile('\d+ hr')
+            pattern_day = re.compile('\d+ day')
+            pattern_min = re.compile('\d+ min')
+            pattern_count = re.compile('\d+')
+
+            hours = int(pattern_count.findall(pattern_hr.findall(Age)[0])[0]) if pattern_hr.findall(Age) else 0
+            day = int(pattern_count.findall(pattern_day.findall(Age)[0])[0]) if pattern_day.findall(Age) else 0
+            min = int(pattern_count.findall(pattern_min.findall(Age)[0])[0]) if pattern_min.findall(Age) else 0
+            t = now - hours*3600 - day*86400 - min*60
+            resultData['create_time'] = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(t))
+            resultData['operate_type'] = infos[4].find('span').getText().strip()
+            yield resultData
+
+
+
+
+
+
+
+