crawlers

descarga_hacia_atras/laJornadaMaya/laJornadaMaya/items.py

@@ -3,12 +3,18 @@
 # Define here the models for your scraped items
 #
 # See documentation in:
-# http://doc.scrapy.org/en/latest/topics/items.html
+# https://doc.scrapy.org/en/latest/topics/items.html
 
 import scrapy
 
 
-class LajornadamayaItem(scrapy.Item):
+class NoticiasItem(scrapy.Item):
     # define the fields for your item here like:
     # name = scrapy.Field()
-    pass
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

descarga_hacia_atras/laJornadaMaya/laJornadaMaya/middlewares.py

@@ -3,7 +3,7 @@
 # Define here the models for your spider middleware
 #
 # See documentation in:
-# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
 
 from scrapy import signals
 
@@ -20,14 +20,14 @@ class LajornadamayaSpiderMiddleware(object):
         crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
         return s
 
-    def process_spider_input(response, spider):
+    def process_spider_input(self, response, spider):
         # Called for each response that goes through the spider
         # middleware and into the spider.
 
         # Should return None or raise an exception.
         return None
 
-    def process_spider_output(response, result, spider):
+    def process_spider_output(self, response, result, spider):
         # Called with the results returned from the Spider, after
         # it has processed the response.
 
@@ -35,7 +35,7 @@ class LajornadamayaSpiderMiddleware(object):
         for i in result:
             yield i
 
-    def process_spider_exception(response, exception, spider):
+    def process_spider_exception(self, response, exception, spider):
         # Called when a spider or process_spider_input() method
         # (from other spider middleware) raises an exception.
 
@@ -43,7 +43,7 @@ class LajornadamayaSpiderMiddleware(object):
         # or Item objects.
         pass
 
-    def process_start_requests(start_requests, spider):
+    def process_start_requests(self, start_requests, spider):
         # Called with the start requests of the spider, and works
         # similarly to the process_spider_output() method, except
         # that it doesn’t have a response associated.
@@ -54,3 +54,50 @@ class LajornadamayaSpiderMiddleware(object):
 
     def spider_opened(self, spider):
         spider.logger.info('Spider opened: %s' % spider.name)
+
+
+class LajornadamayaDownloaderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the downloader middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_request(self, request, spider):
+        # Called for each request that goes through the downloader
+        # middleware.
+
+        # Must either:
+        # - return None: continue processing this request
+        # - or return a Response object
+        # - or return a Request object
+        # - or raise IgnoreRequest: process_exception() methods of
+        #   installed downloader middleware will be called
+        return None
+
+    def process_response(self, request, response, spider):
+        # Called with the response returned from the downloader.
+
+        # Must either;
+        # - return a Response object
+        # - return a Request object
+        # - or raise IgnoreRequest
+        return response
+
+    def process_exception(self, request, exception, spider):
+        # Called when a download handler or a process_request()
+        # (from other downloader middleware) raises an exception.
+
+        # Must either:
+        # - return None: continue processing this exception
+        # - return a Response object: stops process_exception() chain
+        # - return a Request object: stops process_exception() chain
+        pass
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

descarga_hacia_atras/laJornadaMaya/laJornadaMaya/pipelines.py

@@ -3,9 +3,73 @@
 # 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
+# See: https://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()
 
-class LajornadamayaPipeline(object):
     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/laJornadaMaya/laJornadaMaya/settings.py

@@ -5,9 +5,9 @@
 # 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
+#     https://doc.scrapy.org/en/latest/topics/settings.html
+#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html
 
 BOT_NAME = 'laJornadaMaya'
 
@@ -19,21 +19,21 @@ NEWSPIDER_MODULE = 'laJornadaMaya.spiders'
 #USER_AGENT = 'laJornadaMaya (+http://www.yourdomain.com)'
 
 # Obey robots.txt rules
-ROBOTSTXT_OBEY = True
+# 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 https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
 # See also autothrottle settings and docs
-#DOWNLOAD_DELAY = 3
+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
+COOKIES_ENABLED = False
 
 # Disable Telnet Console (enabled by default)
 #TELNETCONSOLE_ENABLED = False
@@ -45,31 +45,31 @@ ROBOTSTXT_OBEY = True
 #}
 
 # Enable or disable spider middlewares
-# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
 #SPIDER_MIDDLEWARES = {
 #    'laJornadaMaya.middlewares.LajornadamayaSpiderMiddleware': 543,
 #}
 
 # Enable or disable downloader middlewares
-# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
 #DOWNLOADER_MIDDLEWARES = {
-#    'laJornadaMaya.middlewares.MyCustomDownloaderMiddleware': 543,
+#    'laJornadaMaya.middlewares.LajornadamayaDownloaderMiddleware': 543,
 #}
 
 # Enable or disable extensions
-# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+# See https://doc.scrapy.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 = {
-#    'laJornadaMaya.pipelines.LajornadamayaPipeline': 300,
-#}
+# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'laJornadaMaya.pipelines.JsonWriterPipeline': 300,
+}
 
 # Enable and configure the AutoThrottle extension (disabled by default)
-# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+# See https://doc.scrapy.org/en/latest/topics/autothrottle.html
 #AUTOTHROTTLE_ENABLED = True
 # The initial download delay
 #AUTOTHROTTLE_START_DELAY = 5
@@ -82,7 +82,7 @@ ROBOTSTXT_OBEY = True
 #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
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
 #HTTPCACHE_ENABLED = True
 #HTTPCACHE_EXPIRATION_SECS = 0
 #HTTPCACHE_DIR = 'httpcache'

descarga_hacia_atras/laJornadaMaya/scrapy.cfg

 # Automatically created by: scrapy startproject
 #
 # For more information about the [deploy] section see:
-# https://scrapyd.readthedocs.org/en/latest/deploy.html
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
 
 [settings]
 default = laJornadaMaya.settings

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

descarga_hacia_atras/laJornadaMaya_deprecated/laJornadaMaya/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 LajornadamayaSpiderMiddleware(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/laJornadaMaya_deprecated/laJornadaMaya/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 LajornadamayaPipeline(object):
+    def process_item(self, item, spider):
+        return item

descarga_hacia_atras/laJornadaMaya_deprecated/laJornadaMaya/settings.py

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

+import scrapy, json, re
+from datetime import datetime, date, timedelta, tzinfo
+
+"""
+Esta version descarga ingresando una fecha.
+USO:
+
+scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=22
+
+No es recomendable para fechas de mas de un mes de antiguas.
+"""
+
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+	return TAG_RE.sub('', text)
+
+
+class UTC(tzinfo):
+	"""clase para el 'time zone' (zona horaria)"""
+
+	def utcoffset(self, dt):
+		# zona horaria para yucatan (centro de mexico): utc-6
+		return timedelta(hours=-6)
+
+	def tzname(self, dt):
+		# nombre de la zona horaria
+		return 'UTC-6'
+
+
+class NoticiasItem(scrapy.Item):
+	title = scrapy.Field()
+	text = scrapy.Field()
+	date = scrapy.Field()
+	location = scrapy.Field()
+	author = scrapy.Field()
+	topic = scrapy.Field()
+	url = scrapy.Field()
+
+
+class QuotesSpider(scrapy.Spider):
+	name = "noticias"
+	
+	def start_requests(self):
+		# self.found = False
+		# self.flag = False
+		self.tz = UTC()
+		self.year = getattr(self, 'year', None)
+		self.month = getattr(self, 'month', None)
+		self.day = getattr(self, 'day', None)
+		self.req_date = date(int(self.year), int(self.month), int(self.day))
+		self.date_format = "%Y-%m-%d"
+		self.baseURL = 'https://www.lajornadamaya.mx'
+		section_list = ['yucatan', 'quintana-roo', 'campeche', 'deportes', 'nacional',
+						'internacional', 'opinion']
+		# section_list = ['deportes']
+
+		for section in section_list:
+			self.section = section
+			for count in range(0,2):
+				if ( count == 0 ):
+					yield scrapy.Request(url=self.baseURL+'/'+section, callback=self.parse_2)
+				elif (count == 1):
+					# self.section = section
+					self.page = 0
+					self.flag = False
+					self.found = False
+					page = -1
+					if not ( section == 'opinion' ):
+						while True:
+							if ( self.flag ):
+								self.flag = False
+								break
+							page+=1
+							yield scrapy.Request(url=self.baseURL+'/'+section+'?p='+str(page), callback=self.parse)
+						
+						if ( self.found ):
+							self.found = False
+							self.page -= 1
+							if ( self.page > 0 ):
+								self.page -= 1
+							
+							for pag in range(self.page, self.page+6):
+								yield scrapy.Request(url=self.baseURL+'/'+section+'?p='+str(pag), callback=self.parse_page, dont_filter=True)
+
+					else:
+						yield scrapy.Request(url=self.baseURL+'/notas?opinion', callback=self.parse_page)
+				
+	
+	def parse_2(self, response): # para las primeras noticias
+		path_list = ['//h1[@class="title"]/a/@href', '//h2[@class="title"]/a/@href']
+		link_list = []
+		for path in path_list:
+			link_list += response.xpath(path).extract()
+		
+		for link in link_list:
+			if ( link[:link.rfind('/')] == self.year+'-'+self.month.zfill(2)+'-'+self.day.zfill(2) ):
+				item = NoticiasItem()
+				
+				d = link[:link.rfind('/')]
+				if len(d) == 10:
+					d = map(int, d.split('-'))
+					d = datetime(d[0], d[1], d[2], tzinfo=self.tz).isoformat('T')
+				
+				elif len(d) == 19:
+					d, t = d.split(' ')
+					d = map(int, d.split('-'))
+					t = map(int, t.split(':'))
+					d = datetime(d[0],d[1],d[2],t[0],t[1],t[2],tzinfo=self.tz).isoformat('T')
+
+				item['date'] = d
+
+				
+				item['topic'] = response.url[response.url.rfind('/')+1:].title()
+				# yield scrapy.Request(url=self.baseURL+'/'+link, callback=self.parse_item_2)
+				request = scrapy.Request(url=self.baseURL+'/'+link, callback=self.parse_item_2)
+				request.meta['item'] = item
+				yield request
+
+
+	def parse(self, response): # para los json
+		json_response = json.loads(response.text)
+
+		if not ( response.url[response.url.rfind('/')+1:] == 'notas?opinion' ):
+			json_list = json_response
+		else:
+			json_list = json_response['articles']
+		
+		for line in json_list:
+			this_date = datetime.strptime(line['publishDate'][:line['publishDate'].rfind(' ')], self.date_format)
+			this_date = this_date.date()
+
+			if ( this_date == self.req_date ):
+				self.page = int(response.url[response.url.rfind('=')+1:])
+				self.found = True
+				self.flag = True
+				break
+			elif ( this_date < self.req_date ):
+				self.flag = True
+				break
+				
+	
+	def parse_item_2(self, response): # para las primeras noticias
+		item = response.meta['item']
+		# item = NoticiasItem()
+		text = ''
+		# item['date'] = response.url[:response.url.rfind('/')][response.url[:response.url.rfind('/')].rfind('/')+1:]
+		# item['topic'] = self.section.title()
+		item['title'] = response.xpath('//article/h1/text()').extract_first()
+		for paragraph in response.xpath('//*[@class="txt"]').extract():
+			text += remove_tags(paragraph) + '\n'
+		item['text'] = text
+		item['url'] = response.url
+		print item['title']
+		yield item
+
+
+	def parse_page(self, response): # para los json
+		json_response = json.loads(response.text)
+
+		if not ( response.url[response.url.rfind('/')+1:] == 'notas?opinion' ):
+			topic = response.url[response.url.rfind('/')+1:response.url.rfind('=')-2].title()
+			json_list = json_response
+		else:
+			json_list = json_response['articles']
+			topic = 'Opinion'
+		
+		for line in json_list:
+			this_date = datetime.strptime(line['publishDate'][:line['publishDate'].rfind(' ')], self.date_format)
+			this_date = this_date.date()
+			
+			if ( this_date == self.req_date ):
+				item = NoticiasItem()
+				# item['date'] = line['publishDate']
+				d = line['publishDate']
+				if len(d) == 10:
+					d = map(int, d.split('-'))
+					d = datetime(d[0], d[1], d[2], tzinfo=self.tz).isoformat('T')
+				
+				elif len(d) == 19:
+					d, t = d.split(' ')
+					d = map(int, d.split('-'))
+					t = map(int, t.split(':'))
+					d = datetime(d[0],d[1],d[2],t[0],t[1],t[2],tzinfo=self.tz).isoformat('T')
+
+				item['date'] = d
+
+
+				item['topic'] = topic
+				item['title'] = line['name']
+				if not ( response.url[response.url.rfind('/')+1:] == 'notas?opinion' ):
+					request = scrapy.Request(url=self.baseURL+line['url'], callback=self.parse_item)
+				else:
+					request = scrapy.Request(url=self.baseURL+'/'+line['publishDate'][:line['publishDate'].rfind(' ')]+'/'+line['uriComponent'], callback=self.parse_item)
+				request.meta['item'] = item
+				yield request
+
+
+	def parse_item(self, response): # para los json
+		item = response.meta['item']
+		text = ''
+		for paragraph in response.xpath('//*[@class="txt"]').extract():
+			text += remove_tags(paragraph) + '\n'
+		item['text'] = text
+		item['url'] = response.url
+		print item['title']
+		yield item
+

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

descarga_por_mes/proceso/proceso/spiders/noticias.py

@@ -23,6 +23,7 @@ USAGE:
 import scrapy, re, cfscrape
 from proceso.items import NoticiasItem
 from datetime import datetime, date, timedelta, tzinfo
+from scrapy.http.cookies import CookieJar
 from scrapy_splash import SplashRequest, SplashFormRequest
 
 
@@ -98,7 +99,8 @@ class QuotesSpider(scrapy.Spider):
             # yield scrapy.Request(url=login_url, callback=self.parse)
 
         token, agent = cfscrape.get_tokens(login_url, user_agent=USER_AGENT)
-
+        print token
+        print "\n"
         yield SplashRequest(url=login_url, callback=self.parse_login, endpoint='render.html', args={ 'wait': 0.5 }, cookies=token,
                     headers={'User-Agent' : agent})
 
@@ -118,14 +120,23 @@ class QuotesSpider(scrapy.Spider):
 
     def after_login(self, response):
         ## Check login succeed before going on ##
+        print response.headers
+        print "\n"
+        print response.real_url
+        print "\n"
         print response.request.headers
+        print "\n"
         cookie_list = response.request.headers.getlist('Cookie')
         cfc, cfd = cookie_list[0].split(';')
         cfc = cfc.strip().split('=')
         cfd = cfd.strip().split('=')
+        cookies = [cfc[1], cfd[1]]
         cookies = {cfc[0]: cfc[1], cfd[0]: cfd[1]}
-        session_legend = response.css('div.topnav > a').extract_first()
         
+        session_legend = response.css('div.topnav > a').extract()[-1]
+        print response.css('h1.entry-title').extract_first()
+        print "\n"
+
         if session_legend is not None:
             session_legend = remove_tags(session_legend)
 
@@ -134,13 +145,18 @@ class QuotesSpider(scrapy.Spider):
 
             else:
                 print session_legend
-                # token, agent = cfscrape.get_tokens(self.baseURL, user_agent=USER_AGENT)
+                print "\n"
+                token, agent = cfscrape.get_tokens(self.baseURL, user_agent=USER_AGENT)
+                print token
+                print "\n"
 
                 if self.stop_date is None:
                     yield scrapy.Request(url=self.baseURL, callback=self.parse)
 
                 else:
+                    self.meta = response.request.meta
                     yield SplashRequest(url=self.baseURL, callback=self.parse_with_stop_date,
+                        meta=self.meta,
                         endpoint='execute',
                         cache_args=['lua_source'],
                         args={'lua_source': script},
@@ -178,12 +194,22 @@ class QuotesSpider(scrapy.Spider):
 
 
     def parse_with_stop_date(self, response):
-        print "started"
+        print "parse_with_stop_date"
+        print "\n"
+        print response.css('h1.entry-title').extract_first()
+        # print "\n"
+        # print response.cookiejar
+        print "\n"
         print response.headers
-        session_legend = response.css('div.topnav > a').extract_first()
-
-        if session_legend is not None : print remove_tags(session_legend)
-        else : "No log in."
+        print "\n"
+        
+        # session_legend = response.css('div.topnav > a').extract()[-1]
+        # if session_legend is not None :
+        #     print remove_tags(session_legend)
+        #     print "\n"
+        # else :
+        #     print "No log in."
+        
         TO_NEXT_PAGE = True
 
         for item in response.css('div.catpor-box > div'):
@@ -203,12 +229,12 @@ class QuotesSpider(scrapy.Spider):
                     # yield scrapy.Request(url=item_link, callback=self.parse_links, cookies=cookies)
                     # yield scrapy.Request(url=item_link, callback=self.parse_links, cookies=token,
                     #                         headers={'User-Agent' : agent})
-                    # yield SplashRequest(url=item_link, callback=self.parse_links,
-                    #     endpoint='execute',
-                    #     cache_args=['lua_source'],
-                    #     args={'lua_source': script},
-                    #     headers={'User-Agent': USER_AGENT}
-                    # )
+                    yield SplashRequest(url=item_link, callback=self.parse_links,
+                        endpoint='execute',
+                        cache_args=['lua_source'],
+                        args={'lua_source': script},
+                        headers={'User-Agent': USER_AGENT}
+                    )
 
                 else:
                     TO_NEXT_PAGE = False

descarga_por_mes/proceso_prueba/proceso_prueba/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://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_por_mes/proceso_prueba/proceso_prueba/middlewares.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class ProcesoPruebaSpiderMiddleware(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(self, response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(self, response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(self, response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(self, start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)
+
+
+class ProcesoPruebaDownloaderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the downloader middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_request(self, request, spider):
+        # Called for each request that goes through the downloader
+        # middleware.
+
+        # Must either:
+        # - return None: continue processing this request
+        # - or return a Response object
+        # - or return a Request object
+        # - or raise IgnoreRequest: process_exception() methods of
+        #   installed downloader middleware will be called
+        return None
+
+    def process_response(self, request, response, spider):
+        # Called with the response returned from the downloader.
+
+        # Must either;
+        # - return a Response object
+        # - return a Request object
+        # - or raise IgnoreRequest
+        return response
+
+    def process_exception(self, request, exception, spider):
+        # Called when a download handler or a process_request()
+        # (from other downloader middleware) raises an exception.
+
+        # Must either:
+        # - return None: continue processing this exception
+        # - return a Response object: stops process_exception() chain
+        # - return a Request object: stops process_exception() chain
+        pass
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

descarga_por_mes/proceso_prueba/proceso_prueba/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://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_por_mes/proceso_prueba/proceso_prueba/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for proceso_prueba project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     https://doc.scrapy.org/en/latest/topics/settings.html
+#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'proceso_prueba'
+
+SPIDER_MODULES = ['proceso_prueba.spiders']
+NEWSPIDER_MODULE = 'proceso_prueba.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.87 Safari/537.36'
+
+# Obey robots.txt rules
+# ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+DOWNLOAD_DELAY = 1
+# 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 = True
+COOKIES_DEBUG = True
+SPLASH_COOKIES_DEBUG = True
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+SPIDER_MIDDLEWARES = {
+   # 'proceso_prueba.middlewares.ProcesoPruebaSpiderMiddleware': 543,
+   'scrapy_splash.SplashDeduplicateArgsMiddleware': 100,
+}
+
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+DOWNLOADER_MIDDLEWARES = {
+    'scrapy_splash.SplashCookiesMiddleware': 723,
+    'scrapy_splash.SplashMiddleware': 725,
+    'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
+}
+
+# Enable or disable extensions
+# See https://doc.scrapy.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'proceso_prueba.pipelines.JsonWriterPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://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 https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
+HTTPCACHE_STORAGE = 'scrapy_splash.SplashAwareFSCacheStorage'
+
+SPLASH_URL = 'http://localhost:8050/'
+
+DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'

descarga_por_mes/proceso_prueba/proceso_prueba/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_por_mes/proceso_prueba/scrapy.cfg

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