crawlers

descarga_hacia_atras/yucatanAlMinuto2/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 = yucatanAlMinuto2.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = yucatanAlMinuto2

descarga_hacia_atras/yucatanAlMinuto2/yucatanAlMinuto2/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 Yucatanalminuto2Item(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

descarga_hacia_atras/yucatanAlMinuto2/yucatanAlMinuto2/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 Yucatanalminuto2SpiderMiddleware(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)

descarga_hacia_atras/yucatanAlMinuto2/yucatanAlMinuto2/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 Yucatanalminuto2Pipeline(object):
+    def process_item(self, item, spider):
+        return item

descarga_hacia_atras/yucatanAlMinuto2/yucatanAlMinuto2/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for yucatanAlMinuto2 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 = 'yucatanAlMinuto2'
+
+SPIDER_MODULES = ['yucatanAlMinuto2.spiders']
+NEWSPIDER_MODULE = 'yucatanAlMinuto2.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'yucatanAlMinuto2 (+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 = {
+#    'yucatanAlMinuto2.middlewares.Yucatanalminuto2SpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'yucatanAlMinuto2.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 = {
+#    'yucatanAlMinuto2.pipelines.Yucatanalminuto2Pipeline': 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'

descarga_hacia_atras/yucatanAlMinuto2/yucatanAlMinuto2/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.

descarga_hacia_atras/yucatanAlMinuto2/yucatanAlMinuto2/spiders/noticias.py

+import scrapy
+from datetime import datetime, date, timedelta, tzinfo
+
+#scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=03 -a day=22
+
+import re
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+	return TAG_RE.sub('', text)
+
+
+class UTC(tzinfo):
+	"""clase para el 'time zone' (zona horaria)"""
+
+	def utcoffset(self, dt):
+		# zona horaria para yucatan (centro de mexico): utc-6
+		return timedelta(hours=-6)
+
+	def tzname(self, dt):
+		# nombre de la zona horaria
+		return 'UTC-6'
+
+
+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):
+		self.tz = UTC()
+		self.year = getattr(self, 'year', None)
+		self.month = getattr(self, 'month', None)
+		self.day = getattr(self, 'day', None)
+		self.baseURL='http://www.yucatanalminuto.com'
+		self.date = date(int(self.year), int(self.month), int(self.day))
+		urls = [
+			self.baseURL,
+								]
+		for url in urls:
+			yield scrapy.Request(url=url, callback=self.parse)
+
+
+	def parse(self, response):
+		for menu in response.css("center").css("td").css("a::attr(href)").extract():
+			if ( menu != '/' ):
+				yield scrapy.Request(url=response.url+menu, callback=self.parse_pagination)
+
+
+	def parse_pagination(self, response):
+		pagination = response.xpath('//div[@id="color_seccion"]/div[1]/p/text()').extract()
+		if ( len(pagination) > 0 ):
+			pagination = remove_tags(pagination[1])
+			pages = int(pagination[16:])
+			for page in range(0, pages):
+				if ( page == 0 ):
+					yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+				else:
+					yield scrapy.Request(url=response.url[:-1]+str(page+1), callback=self.parse_page)
+		else:
+			yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+	
+
+	def parse_page(self, response):
+		item = NoticiasItem()
+		# for post in response.xpath('//a[@class="lista_noticia"]'):
+		for post in response.xpath('//a[@class="lista_noticia"]'):
+			date = post.css('div.pad5').css('p.sec_autor2::text').extract_first()
+			news_date = datetime.strptime(date[21:31], '%Y-%m-%d').date()
+			if ( news_date == self.date ):
+				date = date[21:]
+				news_date, news_time = date.split(' ')
+				news_date = map(int, news_date.split('-'))
+				news_time = map(int, news_time.split(':'))
+				item['date'] = datetime(news_date[0],news_date[1],news_date[2],news_time[0],news_time[1],news_time[2],tzinfo=self.tz).isoformat('T')
+				# item['date'] = news_date
+				
+				item['topic'] = response.xpath('//div[@id="color_seccion"]/h1/text()').extract_first()
+				
+				request = scrapy.Request(url=self.baseURL+post.css('::attr(href)').extract_first(), callback=self.parse_item)
+				request.meta['item'] = item
+				
+				yield request
+
+
+	def parse_item(self, response):
+		text = ''
+		item = response.meta['item']
+		item['title'] = response.css("td").css("h1.noticia_titulo::text").extract_first()
+		for paragraph in response.css('div.noticia_contenido').css('p').extract():
+			text += remove_tags( paragraph ) + '\n'
+		item['text'] = text
+		item['url'] = response.url
+		# print item['title']
+		yield item
\ No newline at end of file

yucatanEnCorto2/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 = yucatanEnCorto.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = yucatanEnCorto

yucatanEnCorto2/yucatanEnCorto/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 YucatanencortoItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

yucatanEnCorto2/yucatanEnCorto/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 YucatanencortoSpiderMiddleware(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)

yucatanEnCorto2/yucatanEnCorto/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 YucatanencortoPipeline(object):
+    def process_item(self, item, spider):
+        return item

yucatanEnCorto2/yucatanEnCorto/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for yucatanEnCorto 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 = 'yucatanEnCorto'
+
+SPIDER_MODULES = ['yucatanEnCorto.spiders']
+NEWSPIDER_MODULE = 'yucatanEnCorto.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'yucatanEnCorto (+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 = {
+#    'yucatanEnCorto.middlewares.YucatanencortoSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'yucatanEnCorto.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 = {
+#    'yucatanEnCorto.pipelines.YucatanencortoPipeline': 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'

yucatanEnCorto2/yucatanEnCorto/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.

yucatanEnCorto2/yucatanEnCorto/spiders/noticias.py

+import scrapy, re
+
+
+## scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=22
+
+"""
+Crawler descarga noticias hasta el 2017.10.17
+"""
+
+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://florcastillo.mx/noticias/'+year+'/'+month+'/'+day
+		
+		yield scrapy.Request(url=self.baseURL, callback=self.parse)
+
+
+	def parse(self, response):
+		pagination = response.css('div.pagination').css('a::attr(href)').extract()
+		
+		if ( len(pagination) > 0 ):
+			pagination = pagination[-1]
+			pages = int(pagination[pagination.rfind('/')+1:])
+			
+			for page in range(0, pages):
+				if ( page == 0 ):
+					yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+				
+				else:
+					yield scrapy.Request(url=self.baseURL+"/page/"+str(page+1), callback=self.parse_page)
+		
+		else:
+			yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+
+
+	def parse_page(self, response):
+		for link in response.css('div.list-block').xpath('./h3/a/@href').extract():
+			yield scrapy.Request(url=link, callback=self.parse_item)
+
+	def parse_item(self, response):
+		item = NoticiasItem()
+		text = ''
+		item['title'] = response.css('div.post-title').css('h1.entry-title::text').extract_first()
+		
+		d = response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
+		## '-06:00' corresponde al UTC-6, zona horaria de yucatan (centro de mexico)
+		if d[-6:] != '-06:00':
+			d = d[:-6] + '-06:00'
+		item['date'] = d
+		
+		item['topic'] = response.xpath('//ul[@id="tpcrn-breadcrumbs"]/li[2]/a/text()').extract_first()[:-2]
+		
+		for paragraph in response.css('div.post_content').css('p').extract():
+			text += remove_tags(paragraph) + '\n'
+		item['text'] = text
+		item['url'] = response.url
+		
+		# print item['title']
+		yield item
+