Merge pull request #3 from codefortulsa/scrapy-doo

Scrapy doo

.gitignore

@@ -1,3 +1,4 @@
+*.pyc
 citystrugglebus.sqlite3
 staticfiles
 html

requirements.txt

@@ -3,3 +3,4 @@ dj-database-url==0.4.0
 gunicorn==19.4.5
 python-decouple==3.0
 whitenoise==2.0.6
+scrapy==1.0.5

scrapy_city/scrapy.cfg

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

scrapy_city/scrapy_city/items.py

@@ -0,0 +1,13 @@
+# -*- 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 ScrapyCityItem(scrapy.Item):
+    url = scrapy.Field()
+    html = scrapy.Field()

scrapy_city/scrapy_city/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 ScrapyCityPipeline(object):
+    def process_item(self, item, spider):
+        return item

scrapy_city/scrapy_city/settings.py

@@ -0,0 +1,85 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for scrapy_city 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 = 'scrapy_city'
+
+SPIDER_MODULES = ['scrapy_city.spiders']
+NEWSPIDER_MODULE = 'scrapy_city.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'scrapy_city (+http://www.yourdomain.com)'
+
+# 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 = {
+#    'scrapy_city.middlewares.MyCustomSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'scrapy_city.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+#ITEM_PIPELINES = {
+#    'scrapy_city.pipelines.SomePipeline': 300,
+#}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+# NOTE: AutoThrottle will honour the standard settings for concurrency and delay
+#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
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG=False
+
+# 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=0
+#HTTPCACHE_DIR='httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES=[]
+#HTTPCACHE_STORAGE='scrapy.extensions.httpcache.FilesystemCacheStorage'

scrapy_city/scrapy_city/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.

scrapy_city/scrapy_city/spiders/city_spider.py

@@ -0,0 +1,24 @@
+import scrapy
+from scrapy_city.items import ScrapyCityItem
+
+class CitySpider(scrapy.Spider):
+    name = "city"
+    allowed_domains = [
+        "nextcity.org",
+        "govtech.com"
+    ] 
+    start_urls = [
+        "http://www.nextcity.org/",
+        "http://www.govtech.com/"
+    ]
+
+    def parse(self, response):
+        # send the present page down the item pipeline
+        item = ScrapyCityItem()
+        item['url'] = response.url
+        item['html'] = response.body
+        yield item
+        # traverse the links to get the next items
+        for href in response.css("a::attr('href')"):
+            url = response.urljoin(href.extract())
+            yield scrapy.Request(url, callback=self.parse)