cambios

edomex 2024 - Solicitados.csv

+Nombre,Tipo,Libre,M3,Actualizado,Nota,,,
+8 Columnas,edomex,,Si,Si,https://8columnas.com.mx/2024/02/02/,,,
+AD Noticias,edomex,,Si,Si,https://adnoticias.mx/2024/02/02/,,,
+Animal Político,Nacional,,SI,SI,https://panel.animalpolitico.com/graphql,,,
+Aristegui Noticias,Nacional,,si,si,,,,nextjs
+Callejón Informativo,edomex,,Si,Si,https://callejoninformativo.com.mx/wp-json/wp/v2/posts?after=2025-01-15T00:00:00&before=2025-01-15T23:59:59&per_page=100,Wordpress 2016-02-04,,
+Capital Estado de México,edomex,,si,si,https://www.capitaledomex.com.mx/wp-json/wp/v2/posts?after=2025-01-15T00:00:00&before=2025-01-15T23:59:59&per_page=100,2016-06-20,,wordpress
+Cuestión de Polémica,edomex,,si,si,https://www.cuestiondepolemica.com/wp-json/wp/v2/posts?after=2025-01-16T00:00:00&before=2025-01-16T23:59:59&per_page=100,2021-09-30,,wordpress
+Diario Amanecer,edomex,,si,si,https://www.diarioamanecer.com.mx/wp-json/wp/v2/posts?after=2025-01-16T00:00:00&before=2025-01-16T23:59:59&per_page=100,Wordpress 2024-11-01,,wordpress
+Diario Basta,Nacional,,Si,Si,https://diariobasta.com/2024/02/02/page/4/,,,
+Diario Basta,edomex,,Si,Si,,,,
+Diario de México,Nacional,,,,Pendiente / drupal,no,,
+Digital Mex,edomex,,,,pendiente,/estado-de-mexico?format=feed&amp,type=atom,
+El Financiero,Nacional,,Si,Si,,,,
+El Heraldo de México,Nacional,,,,pendiente,,,
+El País México,Nacional,No,,,pendiente,https://elpais.com/mexico/actualidad/,,script
+El Sol de México,Nacional,,Si,Si,,https://oem.com.mx/elsoldemexico/mexico/,,"<script id=""__NEXT_DATA__"" type=""application/json"">"
+El Sol de Toluca,edomex,,Si,Si,,,,"<script id=""__NEXT_DATA__"" type=""application/json"">"
+El Universal,Nacional,,Si,Si,,,,"https://api.queryly.com/json.aspx?queryly_key=000ca78dce0f4c6b&query=claudia&endindex=0&batchsize=20&callback=searchPage.resultcallback&showfaceted=true&extendeddatafields=creator,imageresizer,promo_image,subheadline&timezoneoffset=360&facetedkey=section|&facetedvalue=nacion|&daterange=1/1/2025,1/12/2025"
+El Universal Edomex,edomex,,Si,Si,,,,
+El Valle,edomex,,Si,Si,https://elvalle.com.mx/wp-json/wp/v2/posts?after=2025-01-15T00:00:00&before=2025-01-15T23:59:59&per_page=100,Worpress 2011-11-08,,
+Excelsior,Nacional,,,,pendiente,"https://api.imagendigital.com/v2/excelsior/nodes.json/339fd1e0444ddbbd4d4528d8df161108?fields=id,title,type,taxonomy,image.styles.thumb,image.styles.medium,image.description,url&type=article&sort=created:DESC&limit=100","https://cse.google.com/cse/element/v1?rsz=20&num=20&hl=es&source=gcsc&cselibv=5c8d58cbdc1332a7&cx=012394942619524936727:aqmfejabqhs&q=claudia&safe=active&cse_tok=AB-tC_4IakChbDiAel_KY9LEYjpb:1737063567930&lr=lang_es&gl=mx&sort=date&exp=cc&fexp=72821495,72821494&callback=google.search.cse.api13763&rurl=https://www.excelsior.com.mx/buscador?b=claudia#gsc.tab=0&gsc.q=claudia&gsc.sort=date&date=2025-01-16",
+Forbes,Nacional,,,,pendiente,,,
+Heraldo Estado de México,edomex,,,,pendiente,,,
+Impulso Estado de México,edomex,,,,https://impulsoedomex.com.mx/wp-json/wp/v2/posts?after=2019-05-01T00:00:00&before=2019-05-01T23:59:59&per_page=100,Worpress 2015-05-20,,
+La Crónica de Hoy,Nacional,,,,pendiente,,,
+La Jornada,Nacional,,Si,Si,,,,
+La Jornada Estado de México,edomex,,,,,,,
+La Noticia Es,edomex,,,,https://diariolanoticia.com.mx/index.php?rest_route=/wp/v2/posts&after=2025-01-01T00:00:00&before=2025-01-27T23:59:59,wordpress en formato 2        2021-07-15,https://diariolanoticia.com.mx/index.php?rest_route=/wp/v2/posts&orderby=date&order=asc&per_page=1,
+La razón de México,Nacional,,Si,Si,,,,
+La Tribuna Estado de México,edomex,,,,pendiente,,,
+Marcaje Legislativo,edomex,,,,wordpress con seguridad,con seguridad,,
+Milenio,Nacional,,,,pendiente,,,
+Milenio Estado de México,edomex,,,,,,,
+Plana Mayor,edomex,,,,https://www.planamayor.com.mx/wp-json/wp/v2/posts?after=2025-01-21T00:00:00&before=2025-01-21T23:59:59&per_page=100,Wordpress 2010-03-10,,
+Poder Edomex,edomex,,,,https://poderedomex.com/wp-json/wp/v2/posts?after=2025-01-21T00:00:00&before=2025-01-21T23:59:59&per_page=100,Wordpress 2018-04-30,,
+Portal,edomex,,,,,,,
+Proceso,Nacional,No,Si,No,,,,
+Puntual,edomex,,Si,Si,,,,
+Quadratín Estado de México,edomex,,,,https://edomex.quadratin.com.mx/wp-json/wp/v2/posts?after=2025-01-21T00:00:00&before=2025-01-21T23:59:59&per_page=100,Wordpress 2013-10-30,/wp-json/wp/v2/posts?order=asc&orderby=date&per_page=1,
+Reporte Indigo,Nacional,,,,https://www.reporteindigo.com/wp-json/wp/v2/posts?after=2019-05-01T00:00:00&before=2019-05-01T23:59:59&per_page=100,Wordpress 2019-05-01,,
+Sin Embargo,Nacional,,,,https://www.sinembargo.mx/wp-json/wp/v2/posts?after=2011-06-01T00:00:00&before=2011-06-01T23:59:59&per_page=100,Worpress 1 dia de atraso  2011-06-01,,
+Transeúnte,edomex,,,,https://transeuntemx.com/wp-json/wp/v2/posts?after=2025-01-20T00:00:00&before=2025-01-20T23:59:59&per_page=100,Worpress 1 dia de atraso  2016-06-20,,
+Tres PM,edomex,,,,https://www.trespm.mx/component/k2/search?searchword=%22%22&categories=&format=json&tpl=search&limit=100,feed joomla,T = epoch en millis,
+Uno más uno,Nacional,,Si,No,https://unomasuno.com.mx/wp-json/wp/v2/posts?after=2025-01-21T00:00:00&before=2025-01-21T23:59:59&per_page=100,,,

spiders/daily/impulsoEdomex/impulsoEdomex/items.py

+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class ImpulsoedomexItem(scrapy.Item):
+    date = scrapy.Field()
+    title = scrapy.Field()
+    text = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

spiders/daily/impulsoEdomex/impulsoEdomex/middlewares.py

+# Define here the models for your spider middleware
+#
+# See documentation in:
+# 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 ImpulsoedomexSpiderMiddleware:
+    # 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, 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 Request 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 ImpulsoedomexDownloaderMiddleware:
+    # 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/impulsoEdomex/impulsoEdomex/pipelines.py

+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+# useful for handling different item types with a single interface
+from itemadapter import ItemAdapter
+
+
+class ImpulsoedomexPipeline:
+    def process_item(self, item, spider):
+        return item

spiders/daily/impulsoEdomex/impulsoEdomex/settings.py

+# Scrapy settings for impulsoEdomex project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     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 = "impulsoEdomex"
+
+SPIDER_MODULES = ["impulsoEdomex.spiders"]
+NEWSPIDER_MODULE = "impulsoEdomex.spiders"
+
+
+FEED_EXPORT_ENCODING="utf-8"
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = "capitalEstadoDeMexico (+http://www.yourdomain.com)"
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = False
+
+# 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://docs.scrapy.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 https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    "impulsoEdomex.middlewares.ImpulsoedomexSpiderMiddleware": 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    "impulsoEdomex.middlewares.ImpulsoedomexDownloaderMiddleware": 543,
+#}
+
+# Enable or disable extensions
+# See https://docs.scrapy.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    "scrapy.extensions.telnet.TelnetConsole": None,
+#}
+
+# Configure item pipelines
+# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+#ITEM_PIPELINES = {
+#    "impulsoEdomex.pipelines.ImpulsoedomexPipeline": 300,
+#}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://docs.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://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
+TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
+FEED_EXPORT_ENCODING = "utf-8"

spiders/daily/impulsoEdomex/impulsoEdomex/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.

spiders/daily/impulsoEdomex/impulsoEdomex/spiders/noticias.py

+import scrapy
+import re
+import json
+from impulsoEdomex.items import ImpulsoedomexItem
+
+# Expresión regular para eliminar etiquetas HTML
+TAG_RE = re.compile(r'<[^>]+>')
+
+def remove_tags(text):
+    """Elimina etiquetas HTML del texto."""
+    if not isinstance(text, str):
+        return text  # Devuelve el valor original si no es una cadena
+    return TAG_RE.sub('', text)
+
+class NoticiasSpider(scrapy.Spider):
+    name = "noticias"
+    allowed_domains = ["impulsoedomex.com.mx"]
+    start_urls = ["https://impulsoedomex.com.mx"]
+
+    def __init__(self, year=None, month=None, day=None, *args, **kwargs):
+        super(NoticiasSpider, self).__init__(*args, **kwargs)
+        self.year = year
+        self.month = month.zfill(2) if month else None
+        self.day = day.zfill(2) if day else None
+
+        if self.year and self.month and self.day:
+            self.start_urls = [
+                f"{self.start_urls[0]}/wp-json/wp/v2/posts?"
+                f"after={self.year}-{self.month}-{self.day}T00:00:00&"
+                f"before={self.year}-{self.month}-{self.day}T23:59:59&per_page=100"
+            ]
+        else:
+            self.logger.error("Year, month, and day must be provided to generate start_urls.")
+            self.start_urls = []
+
+    def parse(self, response):
+        try:
+            data = json.loads(response.text)
+            self.logger.info(f"Received {len(data)} posts from API.")
+        except json.JSONDecodeError as e:
+            self.logger.error(f"Failed to parse JSON: {e}")
+            return
+
+        for post in data:
+            try:
+                content = post.get('content', {}).get('rendered', '').strip()
+                if content:
+                    class_list = post.get('class_list', {})
+                    topic = None
+                    if isinstance(class_list, dict):
+                        topic = class_list.get('7', '').split("category-")[1] if '7' in class_list else None
+
+                    # Preparar item
+                    item = ImpulsoedomexItem()
+                    item['date'] = post.get('date')
+                    item['title'] = remove_tags(post.get('title', {}).get('rendered', ''))
+                    item['text'] = remove_tags(content)
+                    item['topic'] = topic
+                    item['url'] = post.get('link')
+                    print(item['title'])
+                    yield item
+            except Exception as e:
+                self.logger.error(f"Error processing post {post.get('id')}: {e}")
+                continue
+                

spiders/daily/impulsoEdomex/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 = impulsoEdomex.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = impulsoEdomex