sitio Proceso

otros_sitios/proceso/proceso/items.py

+# -*- 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 ProcesoItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

otros_sitios/proceso/proceso/middlewares.py

+# -*- 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 ProcesoSpiderMiddleware(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)

otros_sitios/proceso/proceso/pipelines.py

+# -*- 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 ProcesoPipeline(object):
+    def process_item(self, item, spider):
+        return item

otros_sitios/proceso/proceso/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for proceso 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 = 'proceso'
+
+SPIDER_MODULES = ['proceso.spiders']
+NEWSPIDER_MODULE = 'proceso.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'proceso (+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 = {
+   # 'proceso.middlewares.ProcesoSpiderMiddleware': 543,
+   'scrapy_splash.SplashDeduplicateArgsMiddleware': 100,
+}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+DOWNLOADER_MIDDLEWARES = {
+   # 'proceso.middlewares.MyCustomDownloaderMiddleware': 543,
+   'scrapy_splash.SplashCookiesMiddleware': 723,
+   'scrapy_splash.SplashMiddleware': 725,
+   'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
+}
+
+# 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 = {
+#    'proceso.pipelines.ProcesoPipeline': 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'
+HTTPCACHE_STORAGE = 'scrapy_splash.SplashAwareFSCacheStorage'
+
+SPLASH_URL = 'http://localhost:8050/'
+
+DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'

otros_sitios/proceso/proceso/spiders/__init__.py

+# 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.

otros_sitios/proceso/proceso/spiders/noticias.py

+import scrapy
+
+## scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=22
+
+import re
+from scrapy_splash import SplashRequest
+
+"""
+Para este sitio se hace uso de scrapy-splash porque el contenido es cargago a traves de javascript
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+	return TAG_RE.sub('', text)
+
+
+class NoticiasItem(scrapy.Item):
+	title = scrapy.Field()
+	text = scrapy.Field()
+	date = scrapy.Field()
+	location = scrapy.Field()
+	author = scrapy.Field()
+	topic = scrapy.Field()
+	url = scrapy.Field()
+
+
+class QuotesSpider(scrapy.Spider):
+	name = "noticias"
+	
+	def start_requests(self):
+		year = getattr(self, 'year', None)
+		# month = getattr(self, 'month', None)
+		# day = getattr(self, 'day', None)
+		self.baseURL='http://hemeroteca.proceso.com.mx/?page_id=111058&edicion=mexico&page='
+		this_year = 2017
+		
+		while this_year >= int(year):
+			yield scrapy.Request(url=self.baseURL+str(year), callback=self.parse)
+			this_year -= 1
+
+
+	def parse(self, response):
+		for link in response.xpath('//*[@class="catpor-post-thumb"]/a/@href').extract():
+			yield scrapy.Request(url=link, callback=self.parse_2)
+
+
+	def parse_2(self, response):
+		for link in response.xpath('//*[@class="post-container clearfix"]/h2/a/@href').extract():
+			# yield scrapy.Request(url=link, callback=self.parse_item)
+			yield SplashRequest(url=link, callback=self.parse_item, endpoint='render.html', args={ 'wait': 0.5 })
+
+
+	def parse_item(self, response):
+		item = NoticiasItem()
+		text = ''
+		item['date'] = response.xpath('//div[@id="primary"]/div/div/div/div/span[@class="published"]/text()').extract_first()
+		item['title'] = response.xpath('//div[@id="primary"]/div/h1/text()').extract_first()
+		item['topic'] = response.xpath('//span[@class="entry-categories"]/text()').extract_first()
+		for paragraph in response.xpath('//div[@id="primary"]/div/div/div/div[@class="entry-content"]/div/p').extract():
+			text += remove_tags(paragraph) + '\n'
+		item['text'] = text
+		item['url'] = response.url
+		# print item['title']
+		yield item
+

otros_sitios/proceso/scrapy.cfg

+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = proceso.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = proceso