new heraldo leon

spiders/daily/heraldoLeon/heraldoLeon/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
+# https://docs.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()
+class HeraldoleonItem(scrapy.Item):
+	# define the fields for your item here like:
+	# name = scrapy.Field()
+	date = scrapy.Field()
+	title = scrapy.Field()
+	text = scrapy.Field()
+	location = scrapy.Field()
+	author = scrapy.Field()
+	topic = scrapy.Field()
+	url = scrapy.Field()

spiders/daily/heraldoLeon/heraldoLeon/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
+# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
 
 from scrapy import signals
 
+# useful for handling different item types with a single interface
+from itemadapter import is_item, ItemAdapter
+
 
-class HeraldoleonSpiderMiddleware(object):
+class HeraldoleonSpiderMiddleware:
     # 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.
@@ -20,30 +21,29 @@ class HeraldoleonSpiderMiddleware(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.
 
-        # Must return an iterable of Request, dict or Item objects.
+        # Must return an iterable of Request, or item objects.
         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.
 
-        # Should return either None or an iterable of Response, dict
-        # or Item objects.
+        # Should return either None or an iterable of Request 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 HeraldoleonSpiderMiddleware(object):
 
     def spider_opened(self, spider):
         spider.logger.info('Spider opened: %s' % spider.name)
+
+
+class HeraldoleonDownloaderMiddleware:
+    # 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)

spiders/daily/heraldoLeon/heraldoLeon/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
+# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
 
-    @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)
+# useful for handling different item types with a single interface
+from itemadapter import ItemAdapter
 
-    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 HeraldoleonPipeline:
     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

spiders/daily/heraldoLeon/heraldoLeon/settings.py

-# -*- coding: utf-8 -*-
-
 # Scrapy settings for heraldoLeon 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
+#     https://docs.scrapy.org/en/latest/topics/settings.html
+#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html
 
 BOT_NAME = 'heraldoLeon'
 
 SPIDER_MODULES = ['heraldoLeon.spiders']
 NEWSPIDER_MODULE = 'heraldoLeon.spiders'
 
-
+FEED_EXPORT_ENCODING="utf-8"
 # Crawl responsibly by identifying yourself (and your website) on the user-agent
 #USER_AGENT = 'heraldoLeon (+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://docs.scrapy.org/en/latest/topics/settings.html#download-delay
 # See also autothrottle settings and docs
-DOWNLOAD_DELAY = 0.5
+#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
+#COOKIES_ENABLED = False
 
 # Disable Telnet Console (enabled by default)
 #TELNETCONSOLE_ENABLED = False
@@ -45,31 +43,31 @@ COOKIES_ENABLED = False
 #}
 
 # Enable or disable spider middlewares
-# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
 #SPIDER_MIDDLEWARES = {
 #    'heraldoLeon.middlewares.HeraldoleonSpiderMiddleware': 543,
 #}
 
 # Enable or disable downloader middlewares
-# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
 #DOWNLOADER_MIDDLEWARES = {
-#    'heraldoLeon.middlewares.MyCustomDownloaderMiddleware': 543,
+#    'heraldoLeon.middlewares.HeraldoleonDownloaderMiddleware': 543,
 #}
 
 # Enable or disable extensions
-# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+# See https://docs.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 = {
-   'heraldoLeon.pipelines.JsonWriterPipeline': 300,
-}
+# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+#ITEM_PIPELINES = {
+#    'heraldoLeon.pipelines.HeraldoleonPipeline': 300,
+#}
 
 # Enable and configure the AutoThrottle extension (disabled by default)
-# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
 #AUTOTHROTTLE_ENABLED = True
 # The initial download delay
 #AUTOTHROTTLE_START_DELAY = 5
@@ -82,9 +80,13 @@ ITEM_PIPELINES = {
 #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://docs.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'
+
+# Set settings whose default value is deprecated to a future-proof value
+REQUEST_FINGERPRINTER_IMPLEMENTATION = '2.7'
+TWISTED_REACTOR = 'twisted.internet.asyncioreactor.AsyncioSelectorReactor'

spiders/daily/heraldoLeon/heraldoLeon/spiders/noticias.py

-# -*- coding: utf-8 -*-
-import scrapy, re
-from heraldoLeon.items import NoticiasItem
-
 """
-MEDIO:
-El Heraldo de León, Guanajuato 
-USO:
-scrapy crawl noticias --nolog -s filename=2018-01-29.json -a year=2018 -a month=1 -a day=29
+	Spider for heraldoleon.mx
+	Author: Mario Chirinos Coluga
+	Usage:scrapy crawl noticias --nolog -O 2017-04-23.json -a year=2017 -a month=4 -a day=23 
+
 """
 
+import scrapy
+import re
+from heraldoLeon.items import HeraldoleonItem
+#-------------------------------------------------------------------------------
 TAG_RE = re.compile(r'<[^>]+>')
 def remove_tags(text):
-    return TAG_RE.sub('', text)
-
-LOC_RE = re.compile(r'.+?(\d{1,2}-?[a-zA-Z]+)?\s?\.-\s?')
-DAT_RE = re.compile(r'\s?(\d{1,2}-?[a-zA-Z]+)?\s?\.-\s?')
-TRASH_RE = re.compile(r'#[^\}]+\}')
-
-
-class QuotesSpider(scrapy.Spider):
-    name = "noticias"
-
-    def start_requests(self):
-        year = getattr(self, "year", None)
-        month = getattr(self, "month", None)
-        day = getattr(self, "day", None)
-
-        self.baseURL = "http://www.heraldoleon.mx/" + year + "/" + month + "/" + day
-
-        yield scrapy.Request(url=self.baseURL, callback=self.parse)
-
-
-    def parse(self, response):
-        yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
-
-        lastPage = response.xpath('//*[@class="page-nav td-pb-padding-side"]/a[@class="last"]/@href').extract_first()
-        if lastPage is None:
-            lastPage = response.xpath('//*[@class="page-nav td-pb-padding-side"]/a/@href').extract()[-1]
-        if lastPage is not None and lastPage != '':
-            lastPage = lastPage.strip('/')
-            lastPage = int(lastPage[lastPage.rfind('/')+1:])
-
-            for page in range(1, lastPage):
-                yield scrapy.Request(url=self.baseURL + "/page/" + str(page+1), callback=self.parse_page)
-
-
-    def parse_page(self, response):
-        for link in response.xpath('//*[@class="td-block-row"]').css('h3').css('a::attr(href)').extract():
-            yield scrapy.Request(url=link, callback=self.parse_item)
-
-
-    def parse_item(self, response):
-        item = NoticiasItem()
-        text = ''
-
-        "La fecha obtenida ya incluye formato y zona horaria"
-        item['date'] = response.xpath('//time[@class="entry-date updated td-module-date"]/@datetime').extract_first()
-        item['title'] = remove_tags(response.xpath('//header[@class="td-post-title"]/h1').extract_first())
-        item['topic'] = response.xpath('//ul[@class="td-category"]/li/a/text()').extract_first()
-
-        author = response.xpath('//pre[@style="text-align: justify;"]/text()').extract_first()
-        if author is not None and author != '':
-            item['author'] = " ".join(author.split("\n")[0].split())
-
-        bodyText = response.xpath('//*[@class="td-post-content"]/p').extract()
-        for i in range(0, len(bodyText)):
-            p = remove_tags(bodyText[i])
-            if i <= 1:
-                p = p.lstrip()
-                result = LOC_RE.match(p)
-                if result:
-                    item['location'] = DAT_RE.sub('', result.group(0))
-                    p = LOC_RE.sub('', p)
-
-            text += p + "\n"
-        item['text'] = TRASH_RE.sub('', text).strip()
-
-        item['url'] = response.url
-
-        yield item
+	return TAG_RE.sub('', text)
+#-------------------------------------------------------------------------------
+class NoticiasSpider(scrapy.Spider):
+	name = 'noticias'
+	allowed_domains = ['heraldoleon.mx']
+	start_urls = ['http://heraldoleon.mx/']
+
+	def start_requests(self):
+		self.year = getattr(self, "year", None)
+		self.month = getattr(self, "month", None)
+		self.day = getattr(self, "day", None)
+
+		self.baseURL = "http://www.heraldoleon.mx/" + self.year + "/" + self.month + "/" + self.day
+
+		yield scrapy.Request(url=self.baseURL, callback=self.parse)
+	#-----------------------------------------------------------------------
+	def parse(self, response):
+		print(response.url)
+
+		for link in response.xpath('//h3[@class="entry-title td-module-title"]/a/@href').extract():
+			yield scrapy.Request(url=link, callback=self.parse_item)
+			
+		next_page = response.xpath('//div[@class="page-nav td-pb-padding-side"]/a/i[@class="td-icon-menu-right"]/../@href').extract_first()
+		print("nextPage", next_page)
+		if next_page is not None:
+			yield scrapy.Request(url=next_page, callback=self.parse)
+	#-------------------------------------------------------------------------------
+	def parse_item(self, response):
+#		print(response.url)
+		item = HeraldoleonItem()
+		item['date'] = response.xpath("//meta[@property='article:published_time']/@content").extract_first()
+		item['title'] = response.xpath('//h1[@class="entry-title"]/text()').extract_first()
+		text=""
+		for p in response.xpath('//div[@class="td-post-content"]/p/text()').extract():
+			nt = remove_tags(p).replace("\n","").replace("\r","").strip()
+			text+=nt
+			if len(nt)>0:
+				text+="\n"
+		item['text'] = text.strip()
+		item['topic'] = ", ".join(response.xpath('//ul[@class="td-tags td-post-small-box clearfix"]/li/a/text()').extract())
+		item['url'] = response.url
+
+		item["author"]=", ".join(response.xpath('//div[@class="td-post-source-via "]/div/a/text()').extract())
+		item["location"]=""
+		print(self.allowed_domains, item["title"])
+		yield item

spiders/daily/heraldoLeon/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 = heraldoLeon.settings