deprecated

deprecated_versions/laJornada_deprecated/laJornada/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 NoticiasItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

deprecated_versions/laJornada_deprecated/laJornada/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 LajornadaSpiderMiddleware(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)

deprecated_versions/laJornada_deprecated/laJornada/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
+
+import json
+from collections import OrderedDict
+
+
+class JsonWriterPipeline(object):
+
+    def __init__(self, filename):
+        self.filename = filename
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # Here you get whatever value was passed through the "filename" command line parameter
+        settings = crawler.settings
+        filename = settings.get('filename')
+
+        # Instantiate the pipeline with the file name
+        return cls(filename)
+
+    def open_spider(self, spider):
+        self.counter = 0
+        self.file = open(self.filename, 'w')
+        self.file.write("[")
+
+    def close_spider(self, spider):
+        self.file.write("]")
+        self.file.close()
+
+    def process_item(self, item, spider):
+        # print("this is my item", item)
+        row = []
+        try:
+            row.append(("date", item['date']))
+        except:
+            pass
+        try:
+            row.append(("topic", item['topic']))
+        except:
+            pass
+        try:
+            row.append(("title", item['title']))
+        except:
+            pass
+        try:
+            row.append(("author", item['author']))
+        except:
+            pass
+        try:
+            row.append(("location", item['location']))
+        except:
+            pass
+        try:
+            row.append(("text", item['text']))
+        except:
+            pass
+        try:
+            row.append(("url", item['url']))
+        except:
+            pass
+
+        line = OrderedDict(row)
+
+        self.counter += 1
+        if self.counter == 1:
+            self.file.write(json.dumps(line))
+        elif self.counter > 1:
+            self.file.write(",\n" + json.dumps(line))
+
+        return item

deprecated_versions/laJornada_deprecated/laJornada/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for laJornada 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 = 'laJornada'
+
+SPIDER_MODULES = ['laJornada.spiders']
+NEWSPIDER_MODULE = 'laJornada.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'laJornada (+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 = 0.5
+# 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 = {
+#    'laJornada.middlewares.LajornadaSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'laJornada.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 = {
+   'laJornada.pipelines.JsonWriterPipeline': 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'

deprecated_versions/laJornada_deprecated/laJornada/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.

deprecated_versions/laJornada_deprecated/laJornada/spiders/noticias.py

+# -*- coding: utf-8 -*-
+
+"""
+    =======================================================================
+
+    THIS VERSION OF La Jornada IS NOW DEPRECATED SINCE THE SITE'S WEB PAGE
+    NO LONGER USES THIS URL: http://www.jornada.unam.mx/.
+    THE NEW VERSION CAN BE FOUND IN THE descarga_por_dia FOLDER.
+
+    =======================================================================
+"""
+
+
+"""
+MEDIO:
+La Jornada, CDMX
+USO:
+scrapy crawl noticias --nolog -s filename=2017-03-22.json -a year=2017 -a month=3 -a day=22
+"""
+
+import scrapy, re
+from laJornada.items import NoticiasItem
+from datetime import date, datetime, timedelta, tzinfo, time
+from collections import OrderedDict
+
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+# re: r'(Twitter:\s+)?(@[\w.%+-]+.)?'
+TW_RE = re.compile(r"""
+(Twitter:           # inicio de bloque, contiene la cadena 'Twitter:' (case insensitive)
+\s+                 # cualquier espacio (\t\n\r\f), una o mas ocurrencias
+)?                  # fin de bloque, ninguna o una ocurrencia del bloque
+(@                  # inicio de bloque, contiene caracter '@'
+[\w.%+-]+           # cualquier caracter alfanumerico mas los signos (.%+-), una o mas ocurrencias
+.                   # cualquier caracter, excepto '\n'
+)?                  # fin de bloque, ninguna o una ocurrencia del bloque
+""", re.X|re.I)     # banderas: verbose|case insensitive
+
+# re: r'(Facebook|Vk):\s+[\w.%+-]+.'
+FB_RE = re.compile(r"""
+(Facebook|Vk)       # bloque, contiene la cadena 'Facebook' o 'Vk' (case insensitive)
+:                   # contiene el caracter ':'
+\s+                 # cualquier espacio (\t\n\r\f), una o mas ocurrencias
+[\w.%+-]+           # cualquier caracter alfanumerico mas los signos (.%+-), una o mas ocurrencias
+.                   # cualquier caracter, excepto '\n'
+""", re.X|re.I)     # banderas: verbose|case insensitive
+
+# re: r'\(?(Foro:\s+)?(https?:\/\/)?([w{3}.])?[\w%+-]+(\.[a-zA-Z]{2,6}){1,2}[/\w.#$%&+-]*\)?.'
+URL_RE = re.compile(r"""
+\(?                 # contiene o no caracter '(', ninguna o una vez
+(Foro:              # inicio de bloque, contiene la cadena 'Foro:' (case insensitive)
+\s+                 # cualquier espacio (\t\n\r\f), una o mas ocurrencias
+)?                  # fin de bloque, ninguna o una ocurrencia del bloque
+(http               # inicio de bloque, contiene cadena 'http'
+s?                  # contiene o no caracter 's'
+:\/\/               # contiene cadena '://'
+)?                  # fin de bloque, ninguna o una ocurrencia del bloque
+([w{3}.])?          # el caracter 'w' tres veces y/o punto (www.), ninguna o una vez
+[\w%+-]+            # cualquier caracter alfanumerico mas los signos (%+-), una o mas ocurrencias
+(\.                 # inicio de bloque, contiene caracter '.'
+[a-zA-Z]{2,6}       # 2 a 6 letras, minusculas o mayusculas
+){1,2}              # fin de bloque, bloque se repite de 1 a 2 veces
+[/\w.#$%&+-]*       # seguido de '/', cualquier caracter alfanumerico mas los signos (.#$%&+-), cero o mas ocurrencias
+\)?                 # contiene o no caracter ')', ninguna o una vez
+.                   # cualquier caracter, excepto '\n'
+""", re.X|re.I)     # banderas: verbose|case insensitive
+
+# re: r'[\w.-]+@[\w-]+(\.[a-zA-Z]{2,6}){1,2}\s?'
+EMAIL_RE = re.compile(r"""
+[\w.-]+             # cualquier caracter alfanumerico mas los signos (.-), una o mas repeticiones
+@                   # seguido de '@'
+[\w-]+              # cualquier caracter alfanumerico mas el signo '-', una o mas repeticiones
+(\.                 # inicio de bloque, contiene '.'
+[a-zA-Z]{2,6}       # 2 a 6 letras, minusculas o mayusculas
+){1,2}              # fin de bloque, bloque se repite de 1 a 2 veces
+\s?                 # cualquier espacio (\t\n\r\f), ninguna o una coincidencia
+""", re.X|re.I)     # banderas: verbose|case insensitive
+
+DIVP_RE = re.compile(r'(<div class="(credito-(autor|titulo)|hemero)">.*?<\/div>|<p class="s-s">.{,35}<\/p>|<span class="loc">.*?<\/span>)', re.S)
+TRANSLATION_RE = re.compile(r'Traducci.n.*', re.I|re.S)
+
+
+def clean_raw(rawText):
+    text = rawText.replace("* * *", '')
+    text = DIVP_RE.sub('', text)
+    text = TRANSLATION_RE.sub('', text)
+    return text
+
+
+def text_cleaning(text):
+    """
+    Function for cleaning news text
+    """
+    """
+    Elimina los espacios dobles, triples o mayores, innecesarios dentro del texto. Primero divide el texto de
+    acuerdo a los saltos de linea, despues divide cada segmento en palabras sin tomar en cuenta espacios. Luego
+    las palabras son agrupadas en nuevos segmentos con un solo espacio entre ellas y se agregan los saltos de
+    linea necesarios. 
+    """
+    newText = ''
+    counter = 0
+    text = text.replace(u'\u0164', '')
+    text = text.replace("Afp", '')
+    for segment in text.split("\n"):
+        counter += 1
+        if counter == 1:
+            newText += " ".join(segment.split())
+        elif counter > 1:
+            newText += "\n" + " ".join(segment.split())
+    """---------------------------------------------------------------------------------------------------"""
+    """
+    Elimina del texto la info de facebook, twitter, foro y correo electronico. 
+    """
+    newText = TW_RE.sub('', newText)
+    newText = FB_RE.sub('', newText)
+    newText = EMAIL_RE.sub('', newText)
+    newText = URL_RE.sub('', newText)
+    newText = TRANSLATION_RE.sub('', newText)
+    """---------------------------------------------------------------------------------------------------"""
+    return newText
+
+
+class UTC(tzinfo):
+    """clase para el 'time zone' (zona horaria)"""
+
+    def utcoffset(self, dt):
+        # zona horaria para centro de mexico: utc-6
+        return timedelta(hours=-6)
+
+    def tzname(self, dt):
+        # nombre de la zona horaria
+        return 'UTC-6'
+
+
+class QuotesSpider(scrapy.Spider):
+    name = "noticias"
+
+    def start_requests(self):
+        self.tz = UTC()
+        self.counter = 0
+        year = getattr(self, 'year', None)
+        month = getattr(self, 'month', None)
+        day = getattr(self, 'day', None)
+        self.baseURL='http://www.jornada.unam.mx/'+year+'/'+month.zfill(2)+'/'+day.zfill(2)+'/'
+
+        self.comparison_date_1 = date(2001, 12, 7)
+        self.comparison_date_2 = date(2002, 1, 8)
+        self.comparison_date_3 = date(2003, 4, 25)
+        self.comparison_date_4 = date(2004, 11, 16)
+        self.comparison_date_5 = date(2004, 12, 12)
+        self.comparison_date_6 = date(2005, 1, 31)
+        self.comparison_date_7 = date(2009, 2, 15)
+        self.date = date(int(year), int(month), int(day))
+
+        self.parse_month = {'enero': 1,      'febrero': 2,  'marzo': 3,      'abril': 4,
+                            'mayo': 5,       'junio': 6,    'julio': 7,      'agosto': 8,
+                            'septiembre': 9, 'octubre': 10, 'noviembre': 11, 'diciembre': 12}
+
+        # self.section_list = ['opinion', 'politica', 'economia', 'mundo', 'estados', 'ciencias',
+        # 										 'capital', 'sociedad', 'cultura', 'espectaculos', 'deportes']
+
+        # for section in section_list:
+            # para la fecha 2009/02/15 o menores, se tiene una estructura determinada de pagina
+            # para las fechas mayores a esa la estructura cambia
+            # if ( requested_date <= comparison_date_1 ):
+            # 	yield scrapy.Request(url=self.baseURL+section, callback=self.parse)
+            # else:
+            # 	yield scrapy.Request(url=self.baseURL+section, callback=self.parse_2)
+        if self.date <= self.comparison_date_2:
+            section_list = ['index.html', 'edito.html', 'opinion.html', 'politica.html',
+                                            'economia.html', 'cultura.html', 'espectaculos.html', 'estados.html',
+                                            'capital.html', 'mundo.html', 'soc-jus.html', 'deportes.html']
+
+            parse_s = {'index.html': 'Portada', 'edito.html': 'Editorial', 'opinion.html': 'Opinion',
+                                 'politica.html': 'Politica', 'economia.html': 'Economia',
+                                 'cultura.html': 'Cultura', 'espectaculos.html': 'Espectaculos', 'estados.html': 'Estados',
+                                 'capital.html': 'Capital', 'mundo.html': 'Mundo', 'soc-jus.html': 'Sociedad',
+                                 'deportes.html': 'Deportes'}
+
+            for s in section_list:
+                item = NoticiasItem()
+                # item['date'] = self.date
+                item['date'] = datetime.combine(self.date, time()).replace(tzinfo=self.tz).isoformat('T')
+                item['topic'] = parse_s[s]
+
+                if s == 'edito.html':
+                    request = scrapy.Request(url=self.baseURL+s, callback=self.parse_item)
+                else:
+                    request = scrapy.Request(url=self.baseURL+s, callback=self.parse)
+
+                request.meta['item'] = item
+                yield request
+
+        elif self.date > self.comparison_date_2 and self.date <= self.comparison_date_3:
+            section_list = ['index.html', 'edito.html', 'opinion.html', 'politica.html',
+                                            'economia.html', 'cultura.html', 'espectaculos.html', 'estados.html',
+                                            'capital.html', 'mundo.html', 'soc-jus.html', 'deportes.html',
+                                            'index.php', 'edito.php', 'opinion.php', 'politica.php',
+                                            'economia.php', 'cultura.php', 'espectaculos.php', 'estados.php',
+                                            'capital.php', 'mundo.php', 'soc-jus.php', 'deportes.php']
+
+            parse_s = {'index.html': 'Portada', 'edito.html': 'Editorial', 'opinion.html': 'Opinion',
+                                 'politica.html': 'Politica', 'economia.html': 'Economia',
+                                 'cultura.html': 'Cultura', 'espectaculos.html': 'Espectaculos', 'estados.html': 'Estados',
+                                 'capital.html': 'Capital', 'mundo.html': 'Mundo', 'soc-jus.html': 'Sociedad',
+                                 'deportes.html': 'Deportes',
+                                 'index.php': 'Portada', 'edito.php': 'Editorial', 'opinion.php': 'Opinion',
+                                 'politica.php': 'Politica', 'economia.php': 'Economia',
+                                 'cultura.php': 'Cultura', 'espectaculos.php': 'Espectaculos', 'estados.php': 'Estados',
+                                 'capital.php': 'Capital', 'mundo.php': 'Mundo', 'soc-jus.php': 'Sociedad',
+                                 'deportes.php': 'Deportes'}
+
+            for s in section_list:
+                item = NoticiasItem()
+                # item['date'] = self.date
+                item['date'] = datetime.combine(self.date, time()).replace(tzinfo=self.tz).isoformat('T')
+                item['topic'] = parse_s[s]
+
+                if s == 'edito.html' or s == 'correo.html' or s == 'edito.php' or s == 'correo.php':
+                    request = scrapy.Request(url=self.baseURL+s, callback=self.parse_item)
+                else:
+                    request = scrapy.Request(url=self.baseURL+s, callback=self.parse_2)
+
+                request.meta['item'] = item
+                yield request
+
+        elif self.date > self.comparison_date_3 and self.date <= self.comparison_date_6:
+            section_list = ['indexfla.php', 'edito.php', 'opinion.php', 'correo.php', 'politica.php',
+                                            'economia.php', 'cultura.php', 'espectaculos.php', 'estados.php',
+                                            'capital.php', 'mundo.php', 'soc-jus.php', 'deportes.php', 'index.php']
+
+            parse_s = {'indexfla.php': 'Portada', 'edito.php': 'Editorial',           'opinion.php': 'Opinion',
+                                 'correo.php': 'Correo',    'politica.php': 'Politica',         'economia.php': 'Economia',
+                                 'cultura.php': 'Cultura',  'espectaculos.php': 'Espectaculos', 'estados.php': 'Estados',
+                                 'capital.php': 'Capital',  'mundo.php': 'Mundo',               'soc-jus.php': 'Sociedad',
+                                 'deportes.php': 'Deportes','index.php': 'Portada'}
+
+            for s in section_list:
+                item = NoticiasItem()
+                # item['date'] = self.date
+                item['date'] = datetime.combine(self.date, time()).replace(tzinfo=self.tz).isoformat('T')
+                item['topic'] = parse_s[s]
+
+                if s == 'edito.php' or s == 'correo.php':
+                    if self.date > self.comparison_date_3 and self.date <= self.comparison_date_5:
+                        request = scrapy.Request(url=self.baseURL+s, callback=self.parse_item)
+
+                    elif self.date > self.comparison_date_5 and self.date <= self.comparison_date_6:
+                        request = scrapy.Request(url=self.baseURL+s, callback=self.parse_item_2)
+
+                else:
+                    request = scrapy.Request(url=self.baseURL+s, callback=self.parse_3)
+
+                request.meta['item'] = item
+                yield request
+
+        elif self.date > self.comparison_date_6:
+            # print 'first filter'
+            section_list = ['opinion', 'politica', 'economia', 'mundo', 'estados', 'ciencias',
+                                            'capital', 'sociedad', 'cultura', 'espectaculos', 'deportes']
+
+            for s in section_list:
+                # para las fechas menores a 2009/02/15 y mayores a 2005/01/31, se tiene una estructura determinada de pagina
+                # para las fechas mayores a esa la estructura cambia
+                if self.date <= self.comparison_date_7:
+                    yield scrapy.Request(url=self.baseURL+s, callback=self.parse_5)
+                elif self.date > self.comparison_date_7:
+                    # print 'second filter in ' + self.baseURL + s
+                    yield scrapy.Request(url=self.baseURL+s, callback=self.parse_6)
+
+
+
+    def parse(self, response):
+        item = response.meta['item']
+        if self.date <= self.comparison_date_1:
+            if item['topic'] == 'Portada':
+                path  = '//td[@rowspan="3"]'
+            else:
+                if len(response.xpath('//td[@align="center"]').css('a::attr(href)').extract()) > 0:
+                    path = '//td[@align="center"]'
+                else:
+                    path = '//td[@align="CENTER"]'
+
+        elif self.date > self.comparison_date_1 and self.date <= self.comparison_date_2:
+            if item['topic'] == 'Portada':
+                path = '//empieza'
+            else:
+                path = '//table[@bordercolor="#CCCCCC"]'
+
+        for r in response.xpath(path).css('a::attr(href)').extract():
+            if r[-5:] == '.html':
+                request = scrapy.Request(url=self.baseURL+r, callback=self.parse_item)
+                request.meta['item'] = item
+                yield request
+
+
+
+    def parse_2(self, response):
+        item = response.meta['item']
+
+        for r in response.xpath('//table[@bordercolor="#CCCCCC"]').css('a::attr(href)').extract():
+            if r[-5:] == '.html':
+                request = scrapy.Request(url=self.baseURL+r, callback=self.parse_item)
+                request.meta['item'] = item
+                yield request
+
+
+
+    def parse_3(self, response):
+        item = response.meta['item']
+        link_list = []
+        link_list.extend(response.xpath('//td[@width="100%"]').css('a::attr(href)').extract())
+        link_list.extend(response.xpath('//td[@width="52%"]').css('a::attr(href)').extract())
+        link_list.extend(response.xpath('//td[@width="24%"]').css('a::attr(href)').extract())
+        link_list.extend(response.xpath('//td[@width="646"]').css('a::attr(href)').extract())
+        link_list.extend(response.xpath('//table[@width="100%"]').css('a::attr(href)').extract())
+
+        for r in link_list:
+            if r[-11:] == '.html&fly=1' or r[-9:] == '.php&fly=' or r[-4:] == '.php':
+                if self.date > self.comparison_date_3 and self.date <= self.comparison_date_6:
+                    if self.date <= self.comparison_date_4:
+                        request = scrapy.Request(url=self.baseURL+r, callback=self.parse_item)
+                        request.meta['item'] = item
+                        yield request
+
+                    elif self.date > self.comparison_date_4 and self.date <= self.comparison_date_6:
+                        if r[:4] == 'http' and r[-4:] == '.php':
+                            this_url = r.replace('\n','')
+
+                            if self.date <= self.comparison_date_5:
+                                request = scrapy.Request(url=this_url, callback=self.parse_item)
+                            elif self.date > self.comparison_date_5 and self.date <= self.comparison_date_6:
+                                request = scrapy.Request(url=this_url, callback=self.parse_item_2)
+
+                            request.meta['item'] = item
+                            yield request
+
+                # elif self.date > self.comparison_date_5 and self.date <= self.comparison_date_6:
+                # 	request = scrapy.Request(url=self.baseURL+r, callback=self.parse_item_2)
+                # 	request.meta['item'] = item
+                # 	yield request
+
+
+
+    def parse_4(self, response):
+        print response.url
+        for r in response.xpath('//td[@width="646"]').css('a::attr(href)').extract():
+            if r[-4:] == '.php':
+                print r.replace('\n','')
+                # request = scrapy.Request(url=r.replace('\n',''), callback=self.parse_item)
+                # request.meta['item'] = item
+                # yield request
+
+
+
+    def parse_5(self, response):
+        if response.url[:response.url.rfind('/')+1] == self.baseURL:   # verifica que se conserva la misma URL base
+            section = response.url[response.url.rfind('/')+1:]
+            if section == 'opinion':   # la seccion 'opinion' tiene una estructura diferente a las otras
+                path_list = ['//*[@id="columnas"]/p/a/@href',
+                                         '//*[@id="opinion"]/p/a/@href']
+            else:
+                path_list = ['//*[@id="article_list"]/h2/a/@href',
+                                         '//*[@id="article_list"]/h3/a/@href']
+
+            for path in path_list:
+                for link in response.xpath(path).extract():
+                    yield scrapy.Request(url=self.baseURL+link, callback=self.parse_item_3)
+
+
+
+    def parse_6(self, response):
+        if response.url[:response.url.rfind('/')+1] == self.baseURL:
+            # linkSet = set()
+            # path_list = ['//*[@class="itemfirst"]/div/a/@href', '//*[@class="item start"]/div/a/@href',
+            #                          '//*[@class="item"]/div/a/@href']
+            #
+            # for path in path_list:
+            #     for link in response.xpath(path).extract():
+            #         if link not in linkSet:
+            #             linkSet.add(link)
+            #             yield scrapy.Request(url=self.baseURL+link, callback=self.parse_item_4)
+            linkSet = set()
+            linkLst = []
+            linkLst.extend(response.xpath('//*[@class="itemfirst"]/div/a/@href').extract())
+            linkLst.extend(response.xpath('//*[@class="item start"]/div/a/@href').extract())
+            linkLst.extend(response.xpath('//*[@class="item"]/div/a/@href').extract())
+
+            for l in linkLst:
+                link = self.baseURL + l
+                if not link in linkSet:
+                    linkSet.add(link)
+                    yield scrapy.Request(url=link, callback=self.parse_item_4)
+
+
+
+    def parse_item(self, response):
+        """
+        FECHAS <= 2004-12-12
+        """
+        item = response.meta['item']
+        flag = True
+        text = ''
+        try:
+            title = remove_tags(response.xpath('//font[@size="5"]').extract_first())
+            item['title'] = title
+        except:
+            try:
+                title = remove_tags(response.xpath('//p/font[@size="5"]').extract_first())
+                item['title'] = title
+            except:
+                try:
+                    title = remove_tags(response.xpath('//p/font[@size="5"]').extract()[1])
+                    item['title'] = title
+                except:
+                    try:
+                        title = remove_tags(response.xpath('//font[@size="4"]').extract_first())
+                        item['title'] = title
+                    except:
+                        try:
+                            title = remove_tags(response.xpath('//p/font[@size="4"]').extract_first())
+                            item['title'] = title
+                        except:
+                            try:
+                                title = remove_tags(response.xpath('//p/font[@size="4"][1]').extract()[1])
+                                item['title'] = title
+                            except:
+                                try:
+                                    title = remove_tags(response.xpath('//font[@size="3"]').extract_first())
+                                    item['title'] = title
+                                except:
+                                    try:
+                                        title = remove_tags(response.xpath('//p/font[@size="3"]').extract_first())
+                                        item['title'] = title
+                                    except:
+                                        try:
+                                            title = remove_tags(response.xpath('//p/font[@size="3"][1]').extract()[1])
+                                            item['title'] = title
+                                        except:
+                                            try:
+                                                title = remove_tags(response.xpath('//font[@size="+1"]').extract_first())
+                                                item['title'] = title
+                                            except:
+                                                try:
+                                                    title = remove_tags(response.xpath('//font[@size="+0"]').extract_first())
+                                                    item['title'] = title
+                                                except:
+                                                    if self.date <= date(1999, 10, 3):   # en esta fecha hay un cambio respecto a las otras en cuanto al html de la pag
+                                                        try:
+                                                            title = remove_tags(response.xpath('//center').extract_first())
+                                                            item['title'] = title
+                                                            flag = False
+                                                        except:
+                                                            pass
+                                                    else:
+                                                        pass
+
+
+        if flag:
+            if self.date <= self.comparison_date_1:
+                """
+                FECHAS > 1999-10-03 Y FECHAS <= 2001-12-07
+                """
+                for p in response.css('p').extract():
+                    # text += remove_tags(p).replace('\r','') ## no toma en cuenta los primeros indices donde esta el titulo
+                    # text = text.replace('\t','')
+                    p = clean_raw(p)
+                    newsText = remove_tags(p)
+                    text += text_cleaning(newsText)
+
+                m = re.search(title, text)
+                if title[-1] == "?": text = text[m.end()+1:]
+                else: text = text[m.end():]
+                text = text.lstrip("\n")
+                text = text.rstrip("\n")
+
+            elif self.date > self.comparison_date_1 and self.date <= self.comparison_date_3:
+                """
+                FECHAS > 2001-12-07 Y FECHAS <= 2003-04-25
+                """
+                for p in response.xpath('//table[@bordercolor="#CCCCCC"]').css('p').extract():
+                    # text += remove_tags(p).replace('\r','')
+                    # text = text.replace('\t','')
+                    p = clean_raw(p)
+                    newsText = remove_tags(p)
+                    text += text_cleaning(newsText)
+
+                m = re.search(title, text)
+                if title[-1] == "?": text = text[m.end()+1:]
+                else: text = text[m.end():]
+                text = text.lstrip("\n")
+                text = text.rstrip("\n")
+
+            elif self.date > self.comparison_date_3 and self.date <= self.comparison_date_4:
+                """
+                FECHAS > 2003-04-25 Y FECHAS <= 2004-11-16
+                """
+                p = response.css('p').extract()
+                for i in range(0, len(p)):
+                    # text += remove_tags(p[i]).replace('\r','')
+                    # text = text.replace('\t','')
+                    aux = clean_raw(p[i])
+                    newsText = remove_tags(aux).lstrip("\n")
+                    newsText = newsText.rstrip("\n")
+                    text += text_cleaning(newsText)
+
+            elif self.date > self.comparison_date_4 and self.date <= self.comparison_date_5:
+                """
+                FECHAS > 2004-11-16 Y FECHAS <= 2004-12-12
+                """
+                p = response.css('p').extract()
+                for i in range(3, len(p)):
+                    # text += remove_tags(p[i]).replace('\r','')
+                    # text = text.replace('\t','')
+                    aux = clean_raw(p[i])
+                    newsText = remove_tags(aux).lstrip("\n")
+                    newsText = newsText.rstrip("\n")
+                    text += text_cleaning(newsText)
+
+                if text == '':
+                    for i in range(0, len(p)):
+                        # text += remove_tags(p[i]).replace('\r','')
+                        # text = text.replace('\t','')
+                        aux = clean_raw(p[i])
+                        newsText = remove_tags(aux).lstrip("\n")
+                        newsText = newsText.rstrip("\n")
+                        text += text_cleaning(newsText)
+
+        else:
+            """
+            FECHAS <= 1999-10-03
+            """
+            # text = remove_tags(response.body)
+            # text = text[len(title):]
+            m = re.search(title, response.body)
+            body = response.body[m.end():]
+            body = clean_raw(body)
+            newsText = remove_tags(body).lstrip("\n")
+            newsText = newsText.rstrip("\n")
+            text += text_cleaning(newsText)
+
+        item['text'] = text
+        item['url'] = response.url
+        yield item
+
+
+
+    def parse_item_2(self, response):
+        """
+        FECHAS > 2004-12-12 Y FECHAS <= 2005-01-31
+        """
+        item = response.meta['item']
+        text = ''
+        # titleLst = []
+        # titleLst.extend(response.xpath('//*[@id="contenido"]/h1/text()').extract())
+        # titleLst.extend(response.xpath('//h1/text()').extract())
+        titleSet = set()
+        titleSet.add(response.xpath('//*[@id="contenido"]/h1').extract_first())
+        titleSet.add(response.xpath('//h1').extract_first())
+
+        for t in titleSet:
+            if t is not None and t != '':
+                title = remove_tags(t).replace('\r','')
+                title = title.replace('\t','')
+                item['title'] = title
+
+        p = response.css('p').extract()
+        for i in range(4, len(p)):
+            # text += remove_tags(p[i]).replace('\r','')
+            # text = text.replace('\t','')
+            newsText = remove_tags(p[i]).lstrip("\n")
+            newsText = newsText.rstrip("\n")
+            text += text_cleaning(newsText)
+
+        if text == '':
+            for i in range(0, len(p)):
+                # text += remove_tags(p[i]).replace('\r','')
+                # text = text.replace('\t','')
+                newsText = remove_tags(p[i]).lstrip("\n")
+                newsText = newsText.rstrip("\n")
+                text += text_cleaning(newsText)
+
+        item['text'] = text
+        item['url'] = response.url
+        yield item
+
+
+
+    def parse_item_3(self, response):
+        """
+        FECHAS > 2005-01-31 Y FECHAS <= 2009-02-15
+        """
+        item = NoticiasItem()
+        text = ''
+        titleSet = set()
+        # item['date'] = self.date
+        item['date'] = datetime.combine(self.date, time()).replace(tzinfo=self.tz).isoformat('T')
+
+        # title = response.xpath('//*[@class="documentContent"]/h1[@class="title"]/text()').extract()
+        # if len(title) > 0:
+        #     item['title'] = title[0]
+        # else:
+        #     item['title'] = response.xpath('//*[@class="documentContent"]/h1/text()').extract_first()
+        titleSet.add(response.xpath('//*[@class="documentContent"]/h1[@class="title"]').extract_first())
+        titleSet.add(response.xpath('//*[@class="documentContent"]/h1').extract_first())
+
+        for t in titleSet:
+            if t is not None and t != '':
+                title = remove_tags(t).replace('\r','')
+                title = title.replace('\t','')
+                item['title'] = title
+
+        item['topic'] = response.xpath('//*[@id="portal-breadcrumbs"]/a[2]/text()').extract_first()
+        for p in response.xpath('//*[@class="documentContent"]/p').extract():
+            # text += remove_tags(p).replace('\r','')
+            # text = text.replace('\t','')
+            newsText = remove_tags(p).lstrip("\n")
+            newsText = newsText.rstrip("\n")
+            text += text_cleaning(newsText)
+
+        item['text'] = text
+        item['url'] = response.url
+        # print item['title']
+        yield item
+
+
+    def parse_item_4(self, response):
+        """
+        FECHAS > 2009-02-15
+        """
+        d = response.xpath('//*[@class="main-fecha"]/text()').extract_first()
+        d = d.replace('de', '').replace('  ', ' ').split(' ')
+        newsDate = date(int(d[3]), self.parse_month[d[2].lower()], int(d[1]))
+
+        if newsDate == self.date:
+            item = NoticiasItem()
+            text = ''
+            # path_list = ['//*[@class="col"]/p', '//*[@class="col col1"]/p', '//*[@class="col col2"]/p']
+            # path_list = ['//*[@class="col"]', '//*[@class="col col1"]', '//*[@class="col col2"]']
+            textLst = []
+            textLst.extend(response.xpath('//*[@class="col"]').extract())
+            textLst.extend(response.xpath('//*[@class="col col1"]').extract())
+            textLst.extend(response.xpath('//*[@class="col col2"]').extract())
+
+            # item['date'] = self.date
+            item['date'] = datetime.combine(newsDate, time()).replace(tzinfo=self.tz).isoformat('T')
+            title = remove_tags(response.xpath('//*[@class="cabeza"]').extract_first())
+            item['title'] = " ".join(title.split())
+            item['topic'] = response.xpath('//*[@class="breadcrumb gui"]/span[2]/a/text()').extract_first()
+
+            author = response.xpath('//*[@class="credito-autor"]/text()').extract_first()
+            if author is None or author == '':
+                author = response.xpath('//*[@class="credito-articulo"]/text()').extract_first()
+            if author is not None and author != '':
+                item['author'] = author
+
+            location = remove_tags(response.xpath('//p[@class="s-s"]').extract_first())
+            if location is not None and location != '' and len(location) <= 35:
+                item['location'] = location
+
+            for p in textLst:
+                # text += remove_tags(p).replace('\r', '')
+                # text = text.replace('\t', '')
+                p = clean_raw(p)
+                # newsText = remove_tags(p).lstrip("\n")
+                # newsText = newsText.rstrip("\n")
+                # text += text_cleaning(newsText)
+                text += remove_tags(p)
+
+            text = text.lstrip("\n")
+            text = text.rstrip("\n")
+            text = text_cleaning(text)
+
+            item['text'] = text
+            item['url'] = response.url
+            # print item['title']
+            # print 'title: ' + item['title'] + '\nurl: ' + item['url'] + '\n'
+            yield item
+

deprecated_versions/laJornada_deprecated/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 = laJornada.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = laJornada

deprecated_versions/tribunaHn_deprecated/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 = tribunaHn.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = tribunaHn

deprecated_versions/tribunaHn_deprecated/tribunaHn/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 NoticiasItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

deprecated_versions/tribunaHn_deprecated/tribunaHn/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 TribunahnSpiderMiddleware(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)

deprecated_versions/tribunaHn_deprecated/tribunaHn/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
+
+import json
+from collections import OrderedDict
+
+
+class JsonWriterPipeline(object):
+
+    def __init__(self, filename):
+        self.filename = filename
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # Here you get whatever value was passed through the "filename" command line parameter
+        settings = crawler.settings
+        filename = settings.get('filename')
+
+        # Instantiate the pipeline with the file name
+        return cls(filename)
+
+    def open_spider(self, spider):
+        self.counter = 0
+        self.file = open(self.filename, 'w')
+        self.file.write("[")
+
+    def close_spider(self, spider):
+        self.file.write("]")
+        self.file.close()
+
+    def process_item(self, item, spider):
+        # print("this is my item", item)
+        row = []
+        try:
+            row.append(("date", item['date']))
+        except:
+            pass
+        try:
+            row.append(("topic", item['topic']))
+        except:
+            pass
+        try:
+            row.append(("title", item['title']))
+        except:
+            pass
+        try:
+            row.append(("author", item['author']))
+        except:
+            pass
+        try:
+            row.append(("location", item['location']))
+        except:
+            pass
+        try:
+            row.append(("text", item['text']))
+        except:
+            pass
+        try:
+            row.append(("url", item['url']))
+        except:
+            pass
+
+        line = OrderedDict(row)
+
+        self.counter += 1
+        if self.counter == 1:
+            self.file.write(json.dumps(line))
+        elif self.counter > 1:
+            self.file.write(",\n" + json.dumps(line))
+
+        return item

deprecated_versions/tribunaHn_deprecated/tribunaHn/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for tribunaHn 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 = 'tribunaHn'
+
+SPIDER_MODULES = ['tribunaHn.spiders']
+NEWSPIDER_MODULE = 'tribunaHn.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'tribunaHn (+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 = 0.5
+# 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 = {
+#    'tribunaHn.middlewares.TribunahnSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'tribunaHn.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 = {
+   'tribunaHn.pipelines.JsonWriterPipeline': 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'

deprecated_versions/tribunaHn_deprecated/tribunaHn/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.

deprecated_versions/tribunaHn_deprecated/tribunaHn/spiders/noticias.py

+# -*- coding: utf-8 -*-
+
+"""
+    ===============================================================================
+
+    THIS VERSION OF La Tribuna Honduras IS NOW DEPRECATED SINCE THE SITE'S WEB PAGE
+    CHANGED ITS ACCESS TO ACCES BY DAY.
+    THE NEW VERSION CAN BE FOUNd IN THE descarga_por_dia/foraneos FOLDER.
+
+    ===============================================================================
+"""
+
+import scrapy, re, json
+from datetime import date
+from tribunaHn.items import NoticiasItem
+
+"""
+MEDIO:
+La Tribuna, Honduras
+USO:
+// Si se quiere obtener todas las noticias desde las más actuales hasta las más antiguas. //
+scrapy crawl noticias --nolog -s filename=noticias.json
+-------------------------------------------------------------------------------------------------
+// Si se quiere obtener todas las noticias desde las más actuales hasta una fecha específica. //
+scrapy crawl noticias --nolog -s filename=noticias.json -a year=2018 -a month=2 -a day=29
+-------------------------------------------------------------------------------------------------
+Después será necesario hacer uso del archivo parse_date_files.py para que las noticias contenidas
+en noticias.json sean separadas en archivos por fecha.
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+DAT_RE = re.compile(r'\d{4}\/\d{2}\/\d{2}')
+
+
+class ImportantData(scrapy.Item):
+    section = scrapy.Field()
+    page = scrapy.Field()
+
+
+class QuotesSpider(scrapy.Spider):
+    name = "noticias"
+
+    def start_requests(self):
+        self.year = getattr(self, "year", None)
+        self.month = getattr(self, "month", None)
+        self.day = getattr(self, "day", None)
+
+        if self.year is not None and self.month is not None and self.day is not None:
+            self.stopDate = date(int(self.year), int(self.month), int(self.day))
+        else:
+            self.stopDate = None
+
+        baseURL = "http://www.latribuna.hn/"
+
+        sectionList = ["noticias", "honduras", "sociedad", "cafeteando", "dejenme-decirles", "desde-usa",
+                       "ecomentarios", "el-cambio-climatico", "el-dossier-de-atenea", "enfoques",
+                       "pecadillos-idiomaticos", "pildoritas", "columnistas", "editorial", "tribuna-del-pueblo",
+                       "anales-historicos", "cine", "dejando-huellas", "dia-7", "dominicales", "done-un-aula",
+                       "especiales-lt", "la-cobra-pregunta", "la-tribuna-agropecuaria", "la-tribuna-cultural",
+                       "nuestro-orgullo", "turismo"]
+        # sectionList = ["noticias"]
+
+        for s in sectionList:
+            yield scrapy.Request(url=baseURL + s, callback=self.parse)
+
+
+    def parse(self, response):
+        CONTINUE_SEARCHING = True
+        linkList = response.xpath('//div[@id="main"]').css('article.linkbox').xpath('./a[@itemprop="url"]/@href').extract()
+        linkList.extend(response.xpath('//div[@id="main"]').css('div.bottom-margin').css('div.col-sm-6').xpath('./h3/a[@itemprop="url"]/@href').extract())
+
+        if self.stopDate is None:
+            for link in linkList:
+                yield scrapy.Request(url=link, callback=self.parse_item)
+
+        else:
+            for link in linkList:
+                res = DAT_RE.search(link)
+                if res:
+                    dat = map(int, res.group(0).split("/"))
+                    newsDate = date(dat[0], dat[1], dat[2])
+                    if newsDate >= self.stopDate:
+                        yield scrapy.Request(url=link, callback=self.parse_item)
+
+                    else:
+                        CONTINUE_SEARCHING = False
+                        break
+
+        if CONTINUE_SEARCHING:
+            nextPage = response.xpath('//span[@class="next"]/a/@href').extract_first()
+            if nextPage is not None:
+                yield scrapy.Request(url=nextPage, callback=self.parse)
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        text = ''
+
+        "La fecha obtenida ya incluye formato y zona horaria"
+        item['date'] = response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
+        item['title'] = remove_tags(response.xpath('//header/h1[@itemprop="name"]').extract_first())
+
+        try:
+            topic = response.xpath('//aside[@class="tags"]/ul/li/a/text()').extract()[0]
+        except:
+            topic = None
+        item['topic'] = topic
+
+        for p in response.css('div.article-post-content').css('p').extract():
+            text += remove_tags(p) + "\n"
+
+        item['text'] = text.strip()
+
+        item['url'] = response.url
+
+        yield item