From 6aa2e7eeca82a8c728e59baa0b79a9c744d467c1 Mon Sep 17 00:00:00 2001
From: Hardik Patel <hardikp12@gmail.com>
Date: Mon, 24 Apr 2017 17:18:57 -0400
Subject: [PATCH] Adding a scrapy spider to get the data for some financial
 terms from wikipedia

---
 data/textdata/scrapy.cfg                    | 11 +++
 data/textdata/textdata/__init__.py          |  0
 data/textdata/textdata/items.py             | 14 ++++
 data/textdata/textdata/middlewares.py       | 56 +++++++++++++
 data/textdata/textdata/pipelines.py         | 11 +++
 data/textdata/textdata/settings.py          | 90 +++++++++++++++++++++
 data/textdata/textdata/spiders/__init__.py  |  4 +
 data/textdata/textdata/spiders/wikipedia.py | 88 ++++++++++++++++++++
 8 files changed, 274 insertions(+)
 create mode 100644 data/textdata/scrapy.cfg
 create mode 100644 data/textdata/textdata/__init__.py
 create mode 100644 data/textdata/textdata/items.py
 create mode 100644 data/textdata/textdata/middlewares.py
 create mode 100644 data/textdata/textdata/pipelines.py
 create mode 100644 data/textdata/textdata/settings.py
 create mode 100644 data/textdata/textdata/spiders/__init__.py
 create mode 100644 data/textdata/textdata/spiders/wikipedia.py

diff --git a/data/textdata/scrapy.cfg b/data/textdata/scrapy.cfg
new file mode 100644
index 0000000..fcc4ecb
--- /dev/null
+++ b/data/textdata/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 = textdata.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = textdata
diff --git a/data/textdata/textdata/__init__.py b/data/textdata/textdata/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/data/textdata/textdata/items.py b/data/textdata/textdata/items.py
new file mode 100644
index 0000000..1c7a813
--- /dev/null
+++ b/data/textdata/textdata/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 TextdataItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass
diff --git a/data/textdata/textdata/middlewares.py b/data/textdata/textdata/middlewares.py
new file mode 100644
index 0000000..5c87492
--- /dev/null
+++ b/data/textdata/textdata/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 TextdataSpiderMiddleware(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(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(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(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(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)
diff --git a/data/textdata/textdata/pipelines.py b/data/textdata/textdata/pipelines.py
new file mode 100644
index 0000000..cc9bd49
--- /dev/null
+++ b/data/textdata/textdata/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 TextdataPipeline(object):
+    def process_item(self, item, spider):
+        return item
diff --git a/data/textdata/textdata/settings.py b/data/textdata/textdata/settings.py
new file mode 100644
index 0000000..2b0f1a1
--- /dev/null
+++ b/data/textdata/textdata/settings.py
@@ -0,0 +1,90 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for textdata 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 = 'textdata'
+
+SPIDER_MODULES = ['textdata.spiders']
+NEWSPIDER_MODULE = 'textdata.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'textdata (+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 = {
+#    'textdata.middlewares.TextdataSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'textdata.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 = {
+#    'textdata.pipelines.TextdataPipeline': 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
+
+# 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'
diff --git a/data/textdata/textdata/spiders/__init__.py b/data/textdata/textdata/spiders/__init__.py
new file mode 100644
index 0000000..ebd689a
--- /dev/null
+++ b/data/textdata/textdata/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.
diff --git a/data/textdata/textdata/spiders/wikipedia.py b/data/textdata/textdata/spiders/wikipedia.py
new file mode 100644
index 0000000..1a585f1
--- /dev/null
+++ b/data/textdata/textdata/spiders/wikipedia.py
@@ -0,0 +1,88 @@
+import scrapy
+from scrapy.spiders import CrawlSpider
+from w3lib.html import remove_tags, remove_tags_with_content
+
+
+class WikipediaSpider(CrawlSpider):
+    name = 'wikipedia'
+    start_urls = ['https://en.wikipedia.org/wiki/Outline_of_finance']
+
+    def parse(self, response):
+        """
+        Parse the response page
+        """
+        url = response.url
+
+        if url in WikipediaSpider.start_urls:
+            return self._parse_topic_list(response)
+
+        else:
+            return self._parse_topic_response(response)
+
+    def _parse_topic_response(self, response):
+        """
+        Parse the content
+        """
+
+        # Get the title first
+        title = response.css('title::text').extract_first()
+
+        # Replace / with a space - creates issues with writing to file
+        title = title.replace('/', ' ')
+
+        content = response.css('div#mw-content-text')
+
+        # Just extract all the '<p></p>' children from this
+        text = ''
+        for child in content.xpath('//p'):
+
+            # Get the text from this child <p></p> tag
+            paragraph = child.extract()
+
+            # Remove <script>, <sup>, <math> tags with the content
+            paragraph = remove_tags_with_content(paragraph, which_ones=('script', 'sup', 'math'))
+            # Remove the rest of the tags without removing the content
+            paragraph = remove_tags(paragraph)
+
+            # Replace '&amp;' with '&'
+            paragraph = paragraph.replace('&amp;', '&')
+
+            # Replace 'U.S.' with 'US':
+            paragraph = paragraph.replace('U.S.', 'US')
+
+            # Some more replacements to improve the default tokenization
+            for c in '();.,[]"\'-:/%$+nnn':
+                paragraph = paragraph.replace(c, ' {} '.format(c))
+
+            # Add to the file
+            text += paragraph + '\n'
+
+        filename = 'wiki_data.txt'
+        f = open(filename, 'a')
+        f.write(text)
+        f.close()
+
+    def _parse_topic_list(self, response):
+        """
+        Parse various topics from the list of topics
+        """
+
+        # All of the links on this pages are in the bullet points
+        # Therefore, extract the 'ul' tags to get the list
+        content = response.css('div#mw-content-text')
+        lists = content.css('ul')
+
+        # Iterate through each list
+        for ul in lists:
+
+            # Iterate through each list item
+            for l in ul.css('li'):
+                # Extract the URL
+                url = l.css('a::attr(href)').extract_first()
+
+                # Skip external links as well as the links to the same page (e.g. TOC)
+                if url is None or 'wiki' not in url:
+                    continue
+
+                next_page = response.urljoin(url)
+                yield scrapy.Request(next_page, callback=self.parse)