Add files via upload

items.py

@@ -0,0 +1,14 @@
+# -*- 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 GetContactInfoItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

middlewares.py

@@ -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 GetContactInfoSpiderMiddleware(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)

motherspider.py

@@ -0,0 +1,18 @@
+# import the spiders you want to run
+from spiders.toscrape import ToScrapeSpider
+from spiders.toscrape2 import ToScrapeSpiderTwo
+
+# scrapy api imports
+# from scrapy import signals, log
+from scrapy import signals
+import logging
+from twisted.internet import reactor
+# from scrapy.crawler import Crawler
+from scrapy.crawler import CrawlerProcess
+# from scrapy.crawler import CrawlerRunner
+from scrapy.settings import Settings
+
+process = CrawlerProcess()
+process.crawl(ToScrapeSpider)
+process.crawl(ToScrapeSpiderTwo)
+process.start() # the script will block here until all crawling jobs are finished

pipelines.py

@@ -0,0 +1,11 @@
+# -*- 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
+
+
+class GetContactInfoPipeline(object):
+    def process_item(self, item, spider):
+        return item

run.sh

@@ -0,0 +1,2 @@
+#!/bin/bash
+scrapy runspider spiders/mitspider.py

settings.py

@@ -0,0 +1,102 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for get_contact_info project
+# python3 -m scrapy runspider spiders/mitspider.py  -o emails.json -L INFO
+# 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 = 'get_contact_info'
+
+SPIDER_MODULES = ['get_contact_info.spiders']
+NEWSPIDER_MODULE = 'get_contact_info.spiders'
+HTTPERROR_ALLOW_ALL = True
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'get_contact_info (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = False
+
+# Set the maximum depth of a site crawling
+DEPTH_LIMIT = 20
+
+# Set the site crawling algorithm
+# if zero (default), no priority adjustment is made from depth
+# a positive value will decrease the priority, i.e. higher depth requests will be processed later
+# ; this is commonly used when doing breadth-first crawls (BFO).
+# a negative value will increase priority, i.e., higher depth requests will be processed sooner (DFO)
+# DEPTH_PRIORITY = 1
+# SCHEDULER_DISK_QUEUE = 'scrapy.squeues.PickleFifoDiskQueue'
+# SCHEDULER_MEMORY_QUEUE = 'scrapy.squeues.FifoMemoryQueue'
+
+# 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 = True
+
+# Disable Telnet Console (enabled by default)
+TELNETCONSOLE_ENABLED = True
+
+# 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 = {
+#    'get_contact_info.middlewares.GetContactInfoSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'get_contact_info.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 = {
+#    'get_contact_info.pipelines.GetContactInfoPipeline': 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 = True
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+HTTPCACHE_ENABLED = True
+HTTPCACHE_EXPIRATION_SECS = 30
+HTTPCACHE_DIR = 'httpcache'
+HTTPCACHE_IGNORE_HTTP_CODES = []
+HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'