diario de yucatan

spiders/daily/diarioYucatan/diarioYucatan/items.py

+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class DiarioyucatanItem(scrapy.Item):
+	# define the fields for your item here like:
+	# name = scrapy.Field()
+	date = scrapy.Field()
+	title = scrapy.Field()
+	text = scrapy.Field()
+	location = scrapy.Field()
+	author = scrapy.Field()
+	topic = scrapy.Field()
+	url = scrapy.Field()

spiders/daily/diarioYucatan/diarioYucatan/middlewares.py

+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+# useful for handling different item types with a single interface
+from itemadapter import is_item, ItemAdapter
+
+
+class DiarioyucatanSpiderMiddleware:
+    # 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, 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 Request 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 DiarioyucatanDownloaderMiddleware:
+    # 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)

spiders/daily/diarioYucatan/diarioYucatan/pipelines.py

+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+# useful for handling different item types with a single interface
+from itemadapter import ItemAdapter
+
+
+class DiarioyucatanPipeline:
+    def process_item(self, item, spider):
+        return item

spiders/daily/diarioYucatan/diarioYucatan/settings.py

+# Scrapy settings for diarioYucatan project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     https://docs.scrapy.org/en/latest/topics/settings.html
+#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'diarioYucatan'
+
+SPIDER_MODULES = ['diarioYucatan.spiders']
+NEWSPIDER_MODULE = 'diarioYucatan.spiders'
+
+FEED_EXPORT_ENCODING="utf-8"
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'diarioYucatan (+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://docs.scrapy.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+DOWNLOAD_DELAY = 0.25
+# 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://docs.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'diarioYucatan.middlewares.DiarioyucatanSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'diarioYucatan.middlewares.DiarioyucatanDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See https://docs.scrapy.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+#ITEM_PIPELINES = {
+#    'diarioYucatan.pipelines.DiarioyucatanPipeline': 300,
+#}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://docs.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://docs.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'
+
+# Set settings whose default value is deprecated to a future-proof value
+REQUEST_FINGERPRINTER_IMPLEMENTATION = '2.7'
+TWISTED_REACTOR = 'twisted.internet.asyncioreactor.AsyncioSelectorReactor'

spiders/daily/diarioYucatan/diarioYucatan/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.

spiders/daily/diarioYucatan/diarioYucatan/spiders/noticias.py

+"""
+	Spider for yucatan.com.mx
+	Author: Mario Chirinos Coluga
+	Usage:scrapy crawl noticias --nolog -O 2017-04-23.json -a year=2017 -a month=4 -a day=23 
+
+"""
+import scrapy
+import re
+from diarioYucatan.items import DiarioyucatanItem
+import w3lib.html
+#-------------------------------------------------------------------------------
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+	return TAG_RE.sub('', text)
+#-------------------------------------------------------------------------------
+
+
+class NoticiasSpider(scrapy.Spider):
+	name = 'noticias'
+	allowed_domains = ['yucatan.com.mx']
+	start_urls = ['http://yucatan.com.mx/']
+	
+	#-----------------------------------------------------------------------
+	def start_requests(self):
+		year = getattr(self, "year", None)
+		month = getattr(self, "month", None)
+		day = getattr(self, "day", None)
+
+		self.date = year + "-" + month.zfill(2) + "-" + self.day.zfill(2)
+		self.baseURL = "https://www.yucatan.com.mx/" + year + "/" + month.zfill(2) + "/" + self.day.zfill(2) + "/"
+		yield scrapy.Request(url=self.baseURL, callback=self.parseList)
+		
+		#-----------------------------------------------------------------------
+	def parseList(self, response):
+		print(response.url)
+		
+		for i in response.xpath('//article//h2/a/@href').extract():
+			yield scrapy.Request(url=i, callback=self.parseItem)
+			
+		next_page = response.xpath('//a[@class="next page-numbers"]/@href').extract_first()
+#		print("nextPage", next_page)
+		if next_page is not None:
+			yield scrapy.Request(url=next_page, callback=self.parseList)
+			
+	#-------------------------------------------------------------------------------
+	def parseItem(self, response):
+		print(response.url)
+#		print(response.text)
+		item = DiarioyucatanItem()
+		text = ''
+		
+		item['author'] = response.xpath('//span[@class="author vcard"]/a/text()').extract_first()
+		response.xpath('//div[class="author-bio"]').drop()
+		response.xpath('//strong[text()="TE PUEDE INTERESAR:"]/..').drop()
+		response.xpath('//aside').drop()
+		response.xpath('//script').drop()
+		response.xpath('//figure').drop()
+		response.xpath('//article//p/a[@rel="noreferrer noopener"]/..').drop()
+		for p in response.xpath('//article/div[@class="entry-content"]/div/p').extract():
+#			tt  = remove_tags(p)+ "\n"
+			tt= w3lib.html.remove_tags_with_content(p, which_ones=["script", "aside", "figure"])
+			tt= remove_tags(remove_tags(tt)).replace(u'\xa0', u' ')
+			text+=tt+"\n"
+		if text=="":
+			for p in response.xpath('//article/div[@class="entry-content"]/p').extract():
+				tt= w3lib.html.remove_tags_with_content(p, which_ones=["script", "aside", "figure"])
+				tt= remove_tags(remove_tags(tt)).replace(u'\xa0', u' ')
+				text+=tt+"\n"
+		item['title'] = response.xpath('//meta[@property="og:title"]/@content').extract_first()
+#		item['title'] = item['title'][0:item['title'].find(" |")]
+		item['date'] = response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
+		item['topic'] = response.xpath('//a[@rel="tag"]/text()').extract()
+
+		item['text']=text
+		item['url']= response.url
+#		
+#		print(item["url"])
+		print(item)
+		yield(item)

spiders/daily/diarioYucatan/scrapy.cfg

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