CFP crawler

cfp_crawler/README.md

@@ -0,0 +1,3 @@
+### Basic Usage
+
+scrapy crawl crawler

cfp_crawler/proposal/items.py

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

cfp_crawler/proposal/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 ProposalSpiderMiddleware(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 ProposalDownloaderMiddleware(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)

cfp_crawler/proposal/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: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+class ProposalPipeline(object):
+    def process_item(self, item, spider):
+        return item

cfp_crawler/proposal/settings.py

@@ -0,0 +1,90 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for proposal 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 = 'proposal'
+
+SPIDER_MODULES = ['proposal.spiders']
+NEWSPIDER_MODULE = 'proposal.spiders'
+LOG_FILE = "logs.log"
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'proposal (+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 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 = {
+#    'proposal.middlewares.ProposalSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'proposal.middlewares.ProposalDownloaderMiddleware': 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 = {
+#    'proposal.pipelines.ProposalPipeline': 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'

cfp_crawler/proposal/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.

cfp_crawler/proposal/spiders/crawler.py

@@ -0,0 +1,64 @@
+# -*- coding: utf-8 -*-
+import scrapy
+import json
+from scrapy import signals
+
+
+class CrawlerSpider(scrapy.Spider):
+    name = 'crawler'
+    allowed_domains = ['in.pycon.org']
+    url = "https://in.pycon.org"
+    proposals = []
+    file = open("proposals.json", "w")
+    def start_requests(self):
+        yield scrapy.Request(self.url + "/cfp/2018/proposals", callback = self.parse)
+
+    def parse(self, response):
+        proposal_links = response.xpath("//h3[@class='proposal--title']/a/@href").extract()
+        for link in proposal_links:
+            yield scrapy.Request(self.url + link, callback = self.parseProposal)
+
+
+
+    def parseProposal(self, response):
+        title = response.xpath("//h1[@class='proposal-title']/text()").extract()[0].strip()
+        author = response.xpath("//p[@class='text-muted']/small/b/text()").extract()[0].strip()
+        created_on = response.xpath("//p[@class='text-muted']/small/b/time/text()").extract()[0].strip()
+
+        section = response.xpath("//section[@class='col-sm-8 proposal-writeup']/div")
+        some_dic = {}
+        for div in section:
+            heading = div.xpath(".//h4[@class='heading']/b/text()").extract()[0]
+            data = self.format_data(div.xpath(".//text()").extract(), heading)
+            data = data[2:-2]
+            some_dic[heading[:-1]] = data
+
+        table = response.xpath("//table/tr")
+        for col in table:
+            heading = col.xpath(".//td/small/text()").extract()[0].strip()
+            data = col.xpath(".//td/text()").extract()[0].strip()
+            some_dic[heading[:-1]] = data
+
+        some_dic["title"] = title
+        some_dic["link_to_proposal"] = response.request.url
+        some_dic["author"] = author
+        some_dic["created_on"] = created_on
+        some_dic["Last Updated"] = response.xpath("//time/text()").extract()[0]
+
+        self.proposals.append(some_dic)
+
+    def format_data(self, data, head):
+        return " ".join([d.strip() for d in data if d != "" and d!=head ])
+
+    @classmethod
+    def from_crawler(cls, crawler, *args, **kwargs):
+        spider = super(CrawlerSpider, cls).from_crawler(crawler, *args, **kwargs)
+        crawler.signals.connect(spider.spider_closed, signals.spider_closed)
+        return spider
+
+    def spider_closed(self, spider):
+        print("Closing spider")
+        json.dump(self.proposals, self.file, indent = 2, sort_keys = True)
+
+
+