init project.

coinincome/items.py

@@ -0,0 +1,18 @@
+# -*- 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 CoinincomeItem(scrapy.Item):
+    pool_name = scrapy.Field()
+    coin = scrapy.Field()
+    income = scrapy.Field()
+    income_coin = scrapy.Field()
+    next_income_coin = scrapy.Field()
+    income_hashrate_unit = scrapy.Field()
+    pass

coinincome/middlewares.py

@@ -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 CoinincomeSpiderMiddleware(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 CoinincomeDownloaderMiddleware(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)

coinincome/pipelines.py

@@ -0,0 +1,31 @@
+# -*- 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 MySQLdb
+
+
+class CoinincomePipeline(object):
+    def process_item(self, item, spider):
+        return item
+
+
+class MySQLPipeline(object):
+    def __init__(self):
+        self.conn = MySQLdb.connect('localhost', 'root', '', 'bank', charset="utf8", use_unicode=True)
+        self.cursor = self.conn.cursor()
+
+    def process_item(self, item, spider):
+        try:
+            self.cursor.execute("""INSERT INTO xxx (pool_name, coin, income_coin, income_coin_unit)
+                            VALUES (%s, %s, %s, %s )""",
+                                (item['name'].encode('utf-8'),
+                                 item[''].encode('utf-8'),
+                                 item['phone'].encode('utf-8'),
+                                 item['address'].encode('utf-8')))
+            self.conn.commit()
+        except MySQLdb.Error as e:
+            print("Error %d: %s" % (e.args[0], e.args[1]))
+        return item

coinincome/settings.py

@@ -0,0 +1,91 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for coinincome 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 = 'coinincome'
+
+SPIDER_MODULES = ['coinincome.spiders']
+NEWSPIDER_MODULE = 'coinincome.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'coinincome (+http://www.yourdomain.com)'
+USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36'
+
+# 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 = {
+#    'coinincome.middlewares.CoinincomeSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'coinincome.middlewares.CoinincomeDownloaderMiddleware': 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 = {
+   # 'coinincome.pipelines.MySQLPipeline': 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'

coinincome/spiders/__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.

coinincome/spiders/antpool.py

@@ -0,0 +1,11 @@
+# -*- coding: utf-8 -*-
+import scrapy
+
+
+class AntpoolSpider(scrapy.Spider):
+    name = 'antpool'
+    allowed_domains = ['antpool.com']
+    start_urls = ['http://antpool.com/']
+
+    def parse(self, response):
+        pass

coinincome/spiders/btccom.py

@@ -0,0 +1,31 @@
+# -*- coding: utf-8 -*-
+import scrapy
+import json
+
+###
+# 实际上需要按缓存区分？
+# https://pool.btc.com/v1/coins-income
+# Main
+from coinincome.items import CoinincomeItem
+
+
+class BtccomSpider(scrapy.Spider):
+    name = 'btccom'
+    allowed_domains = ['btc.com']
+    start_urls = [
+        'https://pool.btc.com/v1/coins-income',
+        'https://us-pool.api.btc.com/v1/coins-income',
+        'https://eu-pool.api.btc.com/v1/coins-income'
+    ]
+
+    def parse(self, response):
+        response_body = json.loads(response.body)
+        if response_body['err_no'] == 0:
+            for coin in response_body['data']:
+                item = CoinincomeItem()
+                item['coin'] = coin
+                item['income_coin'] = response_body['data'][coin]['income_coin']
+                item['income_hashrate_unit'] = response_body['data'][coin]['income_hashrate_unit']
+                item['next_income_coin'] = response_body['data'][coin]['next_income_coin']
+                item['pool_name'] = self.name
+                yield item

coinincome/spiders/f2pool.py

@@ -0,0 +1,11 @@
+# -*- coding: utf-8 -*-
+import scrapy
+
+
+class F2poolSpider(scrapy.Spider):
+    name = 'f2pool'
+    allowed_domains = ['f2pool.com']
+    start_urls = ['http://f2pool.com/']
+
+    def parse(self, response):
+        pass

coinincome/spiders/huobipool.py

@@ -0,0 +1,11 @@
+# -*- coding: utf-8 -*-
+import scrapy
+
+
+class HuobipoolSpider(scrapy.Spider):
+    name = 'huobipool'
+    allowed_domains = ['huobipool.com']
+    start_urls = ['http://huobipool.com/']
+
+    def parse(self, response):
+        pass

coinincome/spiders/poolin.py

@@ -0,0 +1,26 @@
+# -*- coding: utf-8 -*-
+import scrapy
+import json
+
+###
+# https://api-prod.poolin.com/api/public/v2/basedata/coins/block_stats
+###
+from coinincome.items import CoinincomeItem
+
+
+class PoolinSpider(scrapy.Spider):
+    name = 'poolin'
+    allowed_domains = ['poolin.com']
+    start_urls = ['https://api-prod.poolin.com/api/public/v2/basedata/coins/block_stats']
+
+    def parse(self, response):
+        response_body = json.loads(response.body)
+        if response_body['err_no'] == 0:
+            for coin in response_body['data']:
+                item = CoinincomeItem()
+                item['coin'] = coin
+                item['income_coin'] = response_body['data'][coin]['rewards_per_unit']
+                item['income_hashrate_unit'] = response_body['data'][coin]['reward_unit']
+                item['next_income_coin'] = 0
+                item['pool_name'] = self.name
+                yield item