merge foraneos

crawler_data.json

@@ -30,6 +30,7 @@
 {"nombre": "Notisureste", "crawler": "descarga_por_dia/notisureste", "desde": "28-11-2011", "url": "http://www.notisureste.com"},
 {"nombre": "Periodico Correo", "crawler": "descarga_por_dia/periodicoCorreo", "desde": "08-09-2013", "url": "https://periodicocorreo.com.mx"},
 {"nombre": "Periodico Victoria", "crawler": "descarga_por_dia/periodicoVictoria", "desde": "09-10-2013", "url": "http://periodicovictoria.mx"},
+{"nombre": "La Prensa Grafica", "crawler": "descarga_hacia_atras/foraneos/prensaGrafica", "url": "https://www.laprensagrafica.com"},
 {"nombre": "Proceso", "crawler": "descarga_por_mes/proceso", "desde": "11-1976", "url": "http://www.proceso.com.mx"},
 {"nombre": "Punto Medio", "crawler": "descarga_por_dia/puntoMedio", "desde": "02-08-2015", "url": "https://www.puntomedio.mx"},
 {"nombre": "Sona 89.3", "crawler": "descarga_por_dia/sona893", "desde": "09-04-2012", "url": "http://sona893.fm"},

crawler_script/crawl_backwards.py

+#!/usr/bin/python
+# -*- coding: utf-8 -*-
+import sys
+import json
+import os
+import datetime
+
+
+today = datetime.datetime.now()
+baseDir = "/home/geoint/virtualHDD/m3/noticias/"
+scrapyDir = "/home/geoint/crawlersNoticias/"
+with open(sys.argv[1]) as data_file:
+    siteList = json.load(data_file)
+    os.chdir(baseDir)
+
+    for s in siteList:
+        media = s['crawler'][s['crawler'].rfind("/")+1:]
+        try:
+            os.makedirs(media)
+        except:
+            print "ok"
+        os.chdir(media)
+
+        lstYears = os.listdir(".")
+        lstYears.sort()
+        if len(lstYears) > 0:
+            year = int(lstYears[len(lstYears)-1])
+        else:
+            year = today.date().year
+
+        print year
+        try:
+            os.makedirs(str(year))
+        except:
+            print "ok"
+
+        os.chdir(str(year))
+
+        lstDays = os.listdir(".")
+        lstDays = [l for l in lstDays if not l.startswith('.')]
+        lstDays.sort()
+        print lstDays
+
+        filename = "noticias.json"
+        if len(lstDays) > 0:
+            strDate = lstDays[len(lstDays)-1]
+            print strDate
+            strDate = strDate[:strDate.find(".")]
+            currentDate = datetime.datetime.strptime(strDate, '%Y-%m-%d')
+            scrapycommand = "scrapy crawl noticias --nolog -s filename=" + filename + " -a year=" + str(currentDate.year) + " -a month=" + str(currentDate.month) + " -a day=" + str(currentDate.day)
+
+        else:
+            scrapycommand = "scrapy crawl noticias --nolog -s filename=" + filename
+
+        mydir = os.getcwd()
+        print mydir
+        os.chdir(scrapyDir+s['crawler'])
+        print media
+        print scrapycommand
+        os.system(scrapycommand)
+        fileSize = os.stat(filename).st_size
+        if fileSize <= 3: os.system("rm " + filename)
+        else:
+            os.chdir(scrapyDir)
+            os.system("python3 parse_date_files.py " + s['crawler'])
+            os.chdir(media)
+            mediaYears = os.listdir(".")
+            mediaYears.sort()
+
+            for yy in mediaYears:
+                os.chdir(yy)
+                try:
+                   os.makedirs(baseDir + media + "/" + yy)
+                except:
+                    pass
+                mediaDays = os.listdir(".")
+                mediaDays = [l for l in mediaDays if not l.startswith('.')]
+                mediaDays.sort()
+
+                for dd in mediaDays:
+                    os.system("mv " + dd + " " + baseDir + media + "/" + yy)
+
+                os.chdir("..")
+                os.system("rm -R " + yy)
+
+            os.chdir("..")
+            os.system("rm -R " + media)
+            os.chdir(s['crawler'])
+            os.system("rm " + filename)
+            os.chdir(mydir)
+
+        os.chdir("..")
+
+# print today.year
+#	scrapy crawl noticias -t json -o $y-$m-$d.json -a year=$y -a month=$m -a day=$d      # ejecucion del crawler correspondiente segun el sitio
\ No newline at end of file

descarga_hacia_atras/foraneos/prensaGrafica/prensaGrafica/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()

descarga_hacia_atras/foraneos/prensaGrafica/prensaGrafica/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 PrensagraficaSpiderMiddleware(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/foraneos/prensaGrafica/prensaGrafica/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

descarga_hacia_atras/foraneos/prensaGrafica/prensaGrafica/settings.py

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

descarga_hacia_atras/foraneos/prensaGrafica/prensaGrafica/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/foraneos/prensaGrafica/prensaGrafica/spiders/noticias.py

+# -*- coding: utf-8 -*-
+import scrapy, re, json
+from datetime import date
+from prensaGrafica.items import NoticiasItem
+
+"""
+MEDIO:
+La Prensa Gráfica, El Salvador
+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{8}-')
+
+
+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
+
+        self.baseURL = "https://www.laprensagrafica.com"
+        self.baseURI = self.baseURL + "/ajax/get_section_news.html?viewmore=%2Fajax%2Fget_section_news.html&page="
+        self.sectionURI = "&size=6&section="
+
+        sectionList = ["elsalvador", "departamento15", "internacionales", "deportes", "economia",
+                       "opinion", "techlife", "farandula", "salud", "tendencias", "mujer", "turismo"]
+        # sectionList = ["elsalvador"]
+
+        for s in sectionList:
+            yield scrapy.Request(url=self.baseURL + "/seccion/" + s, callback=self.parse)
+
+
+    def parse(self, response):
+        searchData = ImportantData()
+        CONTINUE_SEARCHING = True
+        section = response.url[response.url.rfind("/") + 1:]
+        if section == "internacionales": section = "internacional"
+
+        if self.stopDate is None:
+            for link in response.xpath('//div[@class="col-main"]/article/div/h1/a/@href').extract():
+                yield scrapy.Request(url=self.baseURL + link, callback=self.parse_item)
+
+        else:
+            for link in response.xpath('//div[@class="col-main"]/article/div/h1/a/@href').extract():
+                res = DAT_RE.search(link)
+                if res:
+                    dat = res.group(0).replace("-", '')
+                    newsDate = date(int(dat[:4]), int(dat[4:6]), int(dat[6:]))
+                    if newsDate >= self.stopDate:
+                        yield scrapy.Request(url=self.baseURL + link, callback=self.parse_item)
+
+                    else:
+                        CONTINUE_SEARCHING = False
+                        break
+
+        if CONTINUE_SEARCHING:
+            page = 2
+            url = self.baseURI + str(page) + self.sectionURI + section
+            searchData['section'] = section
+            searchData['page'] = page
+            request = scrapy.Request(url=url, callback=self.continue_searching)
+            request.meta['item'] = searchData
+            yield request
+
+
+    def continue_searching(self, response):
+        searchData = response.meta['item']
+        CONTINUE_SEARCHING = True
+
+        linkList = response.xpath('//article/div/h1/a/@href').extract()
+
+        if len(linkList) > 0:
+            if self.stopDate is None:
+                for link in linkList:
+                    yield scrapy.Request(url=self.baseURL + link, callback=self.parse_item)
+
+            else:
+                for link in linkList:
+                    res = DAT_RE.search(link)
+                    if res:
+                        dat = res.group(0).replace("-", '')
+                        newsDate = date(int(dat[:4]), int(dat[4:6]), int(dat[6:]))
+                        if newsDate >= self.stopDate:
+                            yield scrapy.Request(url=self.baseURL + link, callback=self.parse_item)
+
+                        else:
+                            CONTINUE_SEARCHING = False
+                            break
+
+        else:
+            CONTINUE_SEARCHING = False
+
+        if CONTINUE_SEARCHING:
+            searchData['page'] += 1
+            page = searchData['page']
+            section = searchData['section']
+            url = self.baseURI + str(page) + self.sectionURI + section
+            request = scrapy.Request(url=url, callback=self.continue_searching)
+            request.meta['item'] = searchData
+            yield request
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        text = ''
+
+        "La fecha obtenida ya incluye formato y zona horaria"
+        newsData = remove_tags(response.xpath('//script[@type="application/ld+json"]').extract_first())
+        newsDict = json.loads(newsData)
+        item['date'] = newsDict['datePublished']
+        item['title'] = newsDict['headline']
+
+        try:
+            topic = response.xpath('//div[@class="news-line"]/a/text()').extract()[-1]
+        except:
+            topic = None
+        item['topic'] = topic
+
+        author = response.css('div.content-author').xpath('./p/meta[@itemprop="name"]/@content').extract_first()
+        if author is not None:
+            item['author'] = author
+
+        for p in response.css('div.news-body').css('p').extract():
+            text += remove_tags(p) + "\n"
+
+        item['text'] = text.strip()
+
+        item['url'] = response.url
+
+        yield item

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

descarga_hacia_atras/foraneos/tribunaHn/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

descarga_hacia_atras/foraneos/tribunaHn/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()

descarga_hacia_atras/foraneos/tribunaHn/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)

descarga_hacia_atras/foraneos/tribunaHn/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

descarga_hacia_atras/foraneos/tribunaHn/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'

descarga_hacia_atras/foraneos/tribunaHn/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.

descarga_hacia_atras/foraneos/tribunaHn/tribunaHn/spiders/noticias.py

+# -*- coding: utf-8 -*-
+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/"
+        # self.baseURI = self.baseURL + "/ajax/get_section_news.html?viewmore=%2Fajax%2Fget_section_news.html&page="
+        # self.sectionURI = "&size=6&section="
+
+        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=self.baseURL + s, callback=self.parse)
+
+
+    def parse(self, response):
+        # searchData = ImportantData()
+        CONTINUE_SEARCHING = True
+        linkList = response.xpath('//section[@class="section-67"]').css('article.linkbox').xpath('./a[@itemprop="url"]/@href').extract()
+        linkList.extend(response.xpath('//section[@class="section-67"]').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 continue_searching(self, response):
+    #     searchData = response.meta['item']
+    #     CONTINUE_SEARCHING = True
+    #
+    #     linkList = response.xpath('//article/div/h1/a/@href').extract()
+    #
+    #     if len(linkList) > 0:
+    #         if self.stopDate is None:
+    #             for link in linkList:
+    #                 yield scrapy.Request(url=self.baseURL + link, callback=self.parse_item)
+    #
+    #         else:
+    #             for link in linkList:
+    #                 res = DAT_RE.search(link)
+    #                 if res:
+    #                     dat = res.group(0).replace("-", '')
+    #                     newsDate = date(int(dat[:4]), int(dat[4:6]), int(dat[6:]))
+    #                     if newsDate >= self.stopDate:
+    #                         yield scrapy.Request(url=self.baseURL + link, callback=self.parse_item)
+    #
+    #                     else:
+    #                         CONTINUE_SEARCHING = False
+    #                         break
+    #
+    #     else:
+    #         CONTINUE_SEARCHING = False
+    #
+    #     if CONTINUE_SEARCHING:
+    #         searchData['page'] += 1
+    #         page = searchData['page']
+    #         section = searchData['section']
+    #         url = self.baseURI + str(page) + self.sectionURI + section
+    #         request = scrapy.Request(url=url, callback=self.continue_searching)
+    #         request.meta['item'] = searchData
+    #         yield request
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        text = ''
+
+        "La fecha obtenida ya incluye formato y zona horaria"
+        newsData = remove_tags(response.xpath('//script[@type="application/ld+json"]').extract_first())
+        newsDict = json.loads(newsData)
+        item['date'] = newsDict['datePublished']
+        item['title'] = newsDict['headline']
+
+        try:
+            topic = response.xpath('//div[@class="news-line"]/a/text()').extract()[-1]
+        except:
+            topic = None
+        item['topic'] = topic
+
+        author = response.css('div.content-author').xpath('./p/meta[@itemprop="name"]/@content').extract_first()
+        if author is not None:
+            item['author'] = author
+
+        for p in response.css('div.news-body').css('p').extract():
+            text += remove_tags(p) + "\n"
+
+        item['text'] = text.strip()
+
+        item['url'] = response.url
+
+        yield item

parse_date_files.py

 import json, os, sys
 from datetime import datetime
+from collections import OrderedDict
 
 """
 Uso:
 python parse_date_files.py <nombre_del_crawler>
 
 Ej.
-python parse_date_files.py laJornadaBC2
+python parse_date_files.py descarga_hacia_atras/laJornadaBC2
 """
 
+def dictRowGenerator(line):
+    row = []
+
+    try:
+        row.append(("date", line['date']))
+    except:
+        pass
+    try:
+        row.append(("topic", line['topic']))
+    except:
+        pass
+    try:
+        row.append(("title", line['title']))
+    except:
+        pass
+    try:
+        row.append(("author", line['author']))
+    except:
+        pass
+    try:
+        row.append(("location", line['location']))
+    except:
+        pass
+    try:
+        row.append(("text", line['text']))
+    except:
+        pass
+    try:
+        row.append(("url", line['url']))
+    except:
+        pass
+
+    return row
+
+
+info = sys.argv[1]
+media = info[info.rfind("/") + 1:]
+download_type = info[:info.rfind("/")]
 this_file_path = os.path.dirname(os.path.realpath(__file__))
-json_file_path = this_file_path+'/descarga_hacia_atras/'+sys.argv[1]
-destination_path = this_file_path+'/'+sys.argv[1]
+json_file_path = this_file_path + "/" + download_type + "/" + media
+destination_path = this_file_path + "/" + media
 
-json_file = json.loads(open(json_file_path+'/noticias.json').read())
+json_file = json.loads(open(json_file_path + "/noticias.json").read())
 date_set = set()
 
 for news in json_file:
     if news['date'] is not None:
-        news_date = news['date'][:news['date'].rfind('T')]
+        news_date = news['date'][:news['date'].rfind("T")]
         if len(news_date) > 10:
             news_date = news['date'][:news['date'].rfind(' ')]
 
         if not news_date in date_set:
             date_set.add(news_date)
             print(news_date)
+            urlSet = set()
 
             try:
-                export_file = open(destination_path+'/'+news_date[:4]+'/'+news_date+'.json', 'a')
+                export_file = open(destination_path + "/" + news_date[:4] + "/" + news_date + ".json", 'a')
             except:
-                os.makedirs(destination_path+'/'+news_date[:4])
-                export_file = open(destination_path+'/'+news_date[:4]+'/'+news_date+'.json', 'a')
+                os.makedirs(destination_path + "/" + news_date[:4])
+                export_file = open(destination_path + "/" + news_date[:4] + "/" + news_date + ".json", 'a')
 
             counter = 0
             export_file.write("[")
 
             for line in json_file:
                 if line['date'] is not None:
-                    line_date = line['date'][:line['date'].rfind('T')]
+                    line_date = line['date'][:line['date'].rfind("T")]
                     if len(line_date) > 10:
                         line_date = line['date'][:line['date'].rfind(' ')]
 
-                    if line_date == news_date:
+                    if not line['url'] in urlSet and line_date == news_date:
+                        urlSet.add(line['url'])
                         counter += 1
 
+                        auxRow = dictRowGenerator(line)
+                        row = OrderedDict(auxRow)
                         if counter == 1:
-                            export_file.write(json.dumps(line))
+                            export_file.write(json.dumps(row))
                         elif counter > 1:
-                            export_file.write(",\n" + json.dumps(line))
+                            export_file.write(",\n" + json.dumps(row))
 
             export_file.write("]")
             export_file.close()