Ajustes.

README.md

@@ -78,11 +78,20 @@ Se incluyen los siguientes medios:
 
 	```bash
 	cd laJornadaBC
-	scrapy crawl noticias -t json --nolog -o noticias.json -a seccion=<categoria>
+	scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=4 -a day=26
+	```
+	No se encontró notas antes del 2015.02.09.
+	Esta versión descarga por fecha. Se recomienda usar principalmente para fechas recientes.
+* [La Jornada Baja California 2](http://jornadabc.mx)
+
 
-	donde <categoria> puede ser uno de los siguientes:
-	[ baja-california, chihuahua, mexico, mundo, cultura, espectaculos, deportes ]
+	Uso:
+
+	```bash
+	cd laJornadaBC2
+	scrapy crawl noticias -t json --nolog -o noticias.json
 	```
+	Esta versión descarga todas las noticias de cada las categorías.
 * [La Jornada Guerrero](http://www.lajornadaguerrero.com.mx)
 
 

laJornadaAgs/laJornadaAgs/spiders/noticias.py

@@ -8,6 +8,7 @@ TAG_RE = re.compile(r'<[^>]+>')
 def remove_tags(text):
     return TAG_RE.sub('', text)
 
+
 class NoticiasItem(scrapy.Item):
     title = scrapy.Field()
     text = scrapy.Field()
@@ -17,19 +18,21 @@ class NoticiasItem(scrapy.Item):
     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://www.lja.mx/'+year+'/'+month+'/'+day
+		self.baseURL='http://www.lja.mx/'+year+'/'+month.zfill(2)+'/'+day.zfill(2)
 		urls = [
 			self.baseURL,
                 ]
 		for url in urls:
 			yield scrapy.Request(url=url, callback=self.parse)
 
+
 	def parse(self, response):
 		pagination = response.css('div.pagination').css('a::attr(href)').extract()
 		if ( len(pagination) > 0 ):
@@ -39,14 +42,16 @@ class QuotesSpider(scrapy.Spider):
 				if ( page == 0 ):
 					yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
 				else:
-					yield scrapy.Request(url=response.url+"/page/"+str(page+1), callback=self.parse_page)
+					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.xpath('//li[@class="infinite-post"]/a/@href').extract():
 		 	yield scrapy.Request(url=link, callback=self.parse_item)
 
+
 	def parse_item(self, response):
 		item = NoticiasItem()
 		text = ''

laJornadaBC/laJornadaBC/spiders/noticias.py

 import scrapy
 
-# scrapy crawl noticias -t json --nolog -o noticias.json -a seccion=<categoria>
+"""
+USO:
 
-# donde <categoria> es una de las siguientes:
-# [ baja-california, chihuahua, mexico, mundo,
-#   cultura, espectaculos, deportes ]
+scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=2 -a day=21
+"""
 
 import re
 
@@ -26,27 +26,50 @@ class NoticiasItem(scrapy.Item):
 class QuotesSpider(scrapy.Spider):
 	name = 'noticias'
 	def start_requests(self):
-		self.section = getattr(self, 'seccion', None)
-		self.baseURL='http://jornadabc.mx'
-		# section_list = 
-		# for section in section_list:
-		# 	self.section = section
-		yield scrapy.Request(url=self.baseURL+'/seccion/'+self.section, callback=self.parse)
+		self.section = ''
+		self.page = 0
+		self.count = 0
+		self.found = False
+		self.year = getattr(self, 'year', None)
+		self.month = getattr(self, 'month', None)
+		self.day = getattr(self, 'day', None)
+		self.baseURL = 'http://jornadabc.mx'
+		section_list = ['baja-california', 'chihuahua', 'mexico', 'mundo'
+						'cultura', 'espectaculos', 'deportes']
+		
+		for section in section_list:
+			self.section = section
+			self.page = 0
+			self.count = 0
+			page = -1
+			while True:
+				if ( self.found ):
+					break
+				page += 1
+				yield scrapy.Request(url=self.baseURL+'/seccion/'+section+'?page='+str(page), callback=self.parse, dont_filter=True)
+			
+			self.page -= self.count
+			if ( self.page > 0 ):
+				self.page -= 1
+			
+			for pag in range(self.page, self.page+25):
+				yield scrapy.Request(url=self.baseURL+'/seccion/'+section+'?page='+str(pag), callback=self.parse_page, dont_filter=True)				
+
 
 
 	def parse(self, response):
-		pagination = response.xpath('//ul[@class="pager"]/li[@class="pager-last odd last"]/a/@href').extract()
-		if ( len(pagination) > 0 ):
-			pagination = pagination[0]
-			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+'/seccion/'+self.section+'?page='+str(page), callback=self.parse_page, dont_filter=True)
+		if ( self.section == 'espectaculos' or self.section == 'deportes' ):
+			path = '//*[@class="region region-soft-first"]'
 		else:
-			yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+			path = '//*[@class="region region-hard-first"]'
 
+		for link in response.xpath(path).css('div.views-row').xpath('./*[@class="views-field views-field-title"]/span[@class="field-content"]/a/@href').extract():
+			link_date = link[:link.rfind('/')][link[:link.rfind('/')].rfind('/')+1:]   # filtra la fecha del link
+			if ( link_date == self.day.zfill(2)+'-'+self.month.zfill(2)+'-'+self.year ):
+				self.page = int(response.url[response.url.rfind('=')+1:])
+				self.count += 1
+				self.found = True
+				break
 
 
 	def parse_page(self, response):
@@ -56,6 +79,8 @@ class QuotesSpider(scrapy.Spider):
 			path = '//*[@class="region region-hard-first"]'
 
 		for link in response.xpath(path).css('div.views-row').xpath('./*[@class="views-field views-field-title"]/span[@class="field-content"]/a/@href').extract():
+			link_date = link[:link.rfind('/')][link[:link.rfind('/')].rfind('/')+1:]   # filtra la fecha del link
+			if ( link_date == self.day.zfill(2)+'-'+self.month.zfill(2)+'-'+self.year ):
 				yield scrapy.Request(url=self.baseURL+link, callback=self.parse_item)
 
 
@@ -74,5 +99,5 @@ class QuotesSpider(scrapy.Spider):
 			text += paragraph
 		item['text'] = text
 		item['url'] = response.url
-		print item['title']
+		# print item['title']
 		yield item

laJornadaBC2/laJornadaBC2/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 Lajornadabc2Item(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

laJornadaBC2/laJornadaBC2/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 Lajornadabc2SpiderMiddleware(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)

laJornadaBC2/laJornadaBC2/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 Lajornadabc2Pipeline(object):
+    def process_item(self, item, spider):
+        return item

laJornadaBC2/laJornadaBC2/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for laJornadaBC2 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 = 'laJornadaBC2'
+
+SPIDER_MODULES = ['laJornadaBC2.spiders']
+NEWSPIDER_MODULE = 'laJornadaBC2.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'laJornadaBC2 (+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 = {
+#    'laJornadaBC2.middlewares.Lajornadabc2SpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'laJornadaBC2.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 = {
+#    'laJornadaBC2.pipelines.Lajornadabc2Pipeline': 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'

laJornadaBC2/laJornadaBC2/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.

laJornadaBC2/laJornadaBC2/spiders/noticias.py

+import scrapy
+
+"""
+USO:
+
+scrapy crawl noticias -t json --nolog -o noticias.json
+"""
+
+import re
+
+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):
+		self.section = ''
+		self.baseURL = 'http://jornadabc.mx'
+		section_list = ['baja-california', 'chihuahua', 'mexico', 'mundo'
+						'cultura', 'espectaculos', 'deportes']
+		for section in section_list:
+			self.section = section
+			yield scrapy.Request(url=self.baseURL+'/seccion/'+section, callback=self.parse)
+
+
+	def parse(self, response):
+		pagination = response.xpath('//ul[@class="pager"]/li[@class="pager-last odd last"]/a/@href').extract()
+		if ( len(pagination) > 0 ):
+			pagination = pagination[0]
+			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+'/seccion/'+self.section+'?page='+str(page), callback=self.parse_page, dont_filter=True)
+		else:
+			yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+
+
+
+	def parse_page(self, response):
+		if ( self.section == 'espectaculos' or self.section == 'deportes' ):
+			path = '//*[@class="region region-soft-first"]'
+		else:
+			path = '//*[@class="region region-hard-first"]'
+
+		for link in response.xpath(path).css('div.views-row').xpath('./*[@class="views-field views-field-title"]/span[@class="field-content"]/a/@href').extract():
+			yield scrapy.Request(url=self.baseURL+link, callback=self.parse_item)
+
+
+	def parse_item(self, response):
+		item = NoticiasItem()
+		text = ''
+		item['date'] = response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
+		title = response.xpath('//*[@class="block-content"]/h1/a/text()').extract()
+		if ( len(title) > 0 ):
+			item['title'] = title[0]
+		else:
+			item['title'] = response.xpath('//*[@class="block-content"]/h1/text()').extract_first()
+
+		item['topic'] = response.xpath('//span[@class="section"]/text()').extract_first()
+		for paragraph in response.xpath('//*[@class="field-item even"]/p/text()').extract():
+			text += paragraph
+		item['text'] = text
+		item['url'] = response.url
+		# print item['title']
+		yield item

laJornadaBC2/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 = laJornadaBC2.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = laJornadaBC2