yucatan a la mano

deprecated_versions/yucatanALaMano_20190918/2017-03-22.json

+[]
\ No newline at end of file

deprecated_versions/yucatanALaMano_20190918/2019-09-17.json

+[]
\ No newline at end of file

deprecated_versions/yucatanALaMano_20190918/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 = yucatanALaMano.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = yucatanALaMano

deprecated_versions/yucatanALaMano_20190918/yucatanALaMano/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class NoticiasItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

deprecated_versions/yucatanALaMano_20190918/yucatanALaMano/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 YucatanalamanoSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

deprecated_versions/yucatanALaMano_20190918/yucatanALaMano/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+import json
+from collections import OrderedDict
+
+
+class JsonWriterPipeline(object):
+
+    def __init__(self, filename):
+        self.filename = filename
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # Here you get whatever value was passed through the "filename" command line parameter
+        settings = crawler.settings
+        filename = settings.get('filename')
+
+        # Instantiate the pipeline with the file name
+        return cls(filename)
+
+    def open_spider(self, spider):
+        self.counter = 0
+        self.file = open(self.filename, 'w')
+        self.file.write("[")
+
+    def close_spider(self, spider):
+        self.file.write("]")
+        self.file.close()
+
+    def process_item(self, item, spider):
+        # print("this is my item", item)
+        row = []
+        try:
+            row.append(("date", item['date']))
+        except:
+            pass
+        try:
+            row.append(("topic", item['topic']))
+        except:
+            pass
+        try:
+            row.append(("title", item['title']))
+        except:
+            pass
+        try:
+            row.append(("author", item['author']))
+        except:
+            pass
+        try:
+            row.append(("location", item['location']))
+        except:
+            pass
+        try:
+            row.append(("text", item['text']))
+        except:
+            pass
+        try:
+            row.append(("url", item['url']))
+        except:
+            pass
+
+        line = OrderedDict(row)
+
+        self.counter += 1
+        if self.counter == 1:
+            self.file.write(json.dumps(line))
+        elif self.counter > 1:
+            self.file.write(",\n" + json.dumps(line))
+
+        return item

deprecated_versions/yucatanALaMano_20190918/yucatanALaMano/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for yucatanALaMano 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 = 'yucatanALaMano'
+
+SPIDER_MODULES = ['yucatanALaMano.spiders']
+NEWSPIDER_MODULE = 'yucatanALaMano.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'yucatanALaMano (+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 = {
+#    'yucatanALaMano.middlewares.YucatanalamanoSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'yucatanALaMano.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 = {
+   'yucatanALaMano.pipelines.JsonWriterPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

deprecated_versions/yucatanALaMano_20190918/yucatanALaMano/spiders/__init__.py

+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

deprecated_versions/yucatanALaMano_20190918/yucatanALaMano/spiders/noticias.py

+# -*- coding: utf-8 -*-
+import scrapy, re
+from yucatanALaMano.items import NoticiasItem
+
+"""
+MEDIO:
+Yucatán a la Mano, Yuc.
+USO:
+scrapy crawl noticias --nolog -s filename=2017-03-22.json -a year=2017 -a month=3 -a day=22
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+
+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.yucatanalamano.com/" + year + "/" + month + "/" + day
+        # self.baseURL = "http://yucatanalamano.com/" + year + "/" + month + "/" + day
+        urlList = ["http://www.yucatanalamano.com/" + year + "/" + month + "/" + day,
+                   "http://yucatanalamano.com/" + year + "/" + month + "/" + day]
+
+        for url in urlList:
+            yield scrapy.Request(url=url, callback=self.parse)
+
+
+    def parse(self, response):
+        yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+
+        pagination = response.css('div.pagination').css('a::attr(href)').extract()
+        if len(pagination) > 0:
+            pagination = pagination[-1].strip('/')
+            pages = int(pagination[pagination.rfind('/')+1:])
+
+            for page in range(1, pages):
+                yield scrapy.Request(url=response.url+"/page/"+str(page+1), callback=self.parse_page)
+
+
+    def parse_page(self, response):
+        for link in response.css('div.bp-head').css('h2').css('a::attr(href)').extract():
+            yield scrapy.Request(url=link, callback=self.parse_item)
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        text = ''
+        title = response.xpath('//div[@class="main-col"]/div[@itemprop="name"]/text()').extract_first()
+        if title is None:
+            title = response.xpath('//div[@class="main-col"]').css('h1').extract_first()
+        if title is not None:
+            item['title'] = remove_tags(title)
+        else:
+            item['title'] = title
+
+        d = response.css('div.mom-post-meta').css('span').css('time::attr(datetime)').extract_first()
+        ## '-06:00' corresponde al UTC-6, zona horaria de yucatan (centro de mexico)
+        if d[-6:] != '-06:00':
+            d = d[:-6] + '-06:00'
+        item['date'] = d
+
+        item['topic'] = response.css('div.breadcrumbs-plus').css('span').css('a::attr(title)').extract_first()
+
+        for paragraph in response.css('div.entry-content').css('p').extract():
+            text += remove_tags(paragraph) + '\n'
+        item['text'] = text
+        item['url'] = response.url
+
+        # print item['title']
+        yield item
+

descarga_por_dia/yucatanALaMano/yucatanALaMano/spiders/noticias.py

@@ -6,7 +6,7 @@ from yucatanALaMano.items import NoticiasItem
 MEDIO:
 Yucatán a la Mano, Yuc.
 USO:
-scrapy crawl noticias --nolog -s filename=2017-03-22.json -a year=2017 -a month=3 -a day=22
+scrapy crawl noticias --nolog -s filename=2019-09-18.json -a year=2019 -a month=9 -a day=18
 """
 
 TAG_RE = re.compile(r'<[^>]+>')
@@ -22,10 +22,9 @@ class QuotesSpider(scrapy.Spider):
 		month = getattr(self, 'month', None)
 		day = getattr(self, 'day', None)
 
-        # self.baseURL = "http://www.yucatanalamano.com/" + year + "/" + month + "/" + day
-        # self.baseURL = "http://yucatanalamano.com/" + year + "/" + month + "/" + day
-        urlList = ["http://www.yucatanalamano.com/" + year + "/" + month + "/" + day,
-                   "http://yucatanalamano.com/" + year + "/" + month + "/" + day]
+
+		urlList = ["http://www.yucatanalamano.com/" + year + "/" + month + "/" + day]#,
+#		"http://yucatanalamano.com/" + year + "/" + month + "/" + day]
 
 		for url in urlList:
 			yield scrapy.Request(url=url, callback=self.parse)
@@ -33,8 +32,14 @@ class QuotesSpider(scrapy.Spider):
 
 	def parse(self, response):
 		yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+		pagination = response.css('#pagination').css('a::attr(href)').extract()
+		
+		pages = 0
+		for p in pagination:
+			pp = int(p[p.find("page/")+5:-1])
+			if pages < pp:
+				pages = pp
 
-        pagination = response.css('div.pagination').css('a::attr(href)').extract()
 		if len(pagination) > 0:
 			pagination = pagination[-1].strip('/')
 			pages = int(pagination[pagination.rfind('/')+1:])
@@ -44,34 +49,34 @@ class QuotesSpider(scrapy.Spider):
 
 
 	def parse_page(self, response):
-        for link in response.css('div.bp-head').css('h2').css('a::attr(href)').extract():
+		links = response.css('#main-content').css('li.content_in').css('h4.title').css('a::attr(href)').extract()
+
+		for link in links:
 			yield scrapy.Request(url=link, callback=self.parse_item)
 
 
 	def parse_item(self, response):
+
 		item = NoticiasItem()
 		text = ''
-        title = response.xpath('//div[@class="main-col"]/div[@itemprop="name"]/text()').extract_first()
+		title = response.xpath("//meta[@property='og:title']/@content")[0].extract()
 		if title is None:
-            title = response.xpath('//div[@class="main-col"]').css('h1').extract_first()
-        if title is not None:
-            item['title'] = remove_tags(title)
+			title = "Sin Titulo"
 		else:
+			title = remove_tags(title)
 		item['title'] = title
 
-        d = response.css('div.mom-post-meta').css('span').css('time::attr(datetime)').extract_first()
-        ## '-06:00' corresponde al UTC-6, zona horaria de yucatan (centro de mexico)
-        if d[-6:] != '-06:00':
-            d = d[:-6] + '-06:00'
+
+		d = response.xpath("//meta[@itemprop='datePublished']/@content").extract_first()
+
 		item['date'] = d
 
-        item['topic'] = response.css('div.breadcrumbs-plus').css('span').css('a::attr(title)').extract_first()
+		item['topic'] = response.css('div.post-category').css('a::text').extract_first()
 
-        for paragraph in response.css('div.entry-content').css('p').extract():
+		for paragraph in response.css('div.article-content').css('p').extract():
 			text += remove_tags(paragraph) + '\n'
 		item['text'] = text
 		item['url'] = response.url
 
-        # print item['title']
 		yield item