aristegui noticias

spiders/daily/animalPolitico/animalPolitico/spiders/noticias.py

@@ -114,7 +114,7 @@ class NoticiasSpider(scrapy.Spider):
             uri = node.get("uri")
             author_name = node.get("author", {}).get("node", {}).get("name")
             
-            if all([date, title, topic, text, uri, author_name]):  # Verificar que todos los campos existen
+            if text.strip():  # Verificar que todos los campos existen
                 item = {
                     'date': date,
                     'title': remove_tags(title),

spiders/daily/aristeguiNoticias/aristeguiNoticias/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 AristeguinoticiasItem(scrapy.Item):
+    date = scrapy.Field()
+    title = scrapy.Field()
+    text = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

spiders/daily/aristeguiNoticias/aristeguiNoticias/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 AristeguinoticiasSpiderMiddleware:
+    # 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 AristeguinoticiasDownloaderMiddleware:
+    # 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/aristeguiNoticias/aristeguiNoticias/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 AristeguinoticiasPipeline:
+    def process_item(self, item, spider):
+        return item

spiders/daily/aristeguiNoticias/aristeguiNoticias/settings.py

+# Scrapy settings for aristeguiNoticias 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 = "aristeguiNoticias"
+
+SPIDER_MODULES = ["aristeguiNoticias.spiders"]
+NEWSPIDER_MODULE = "aristeguiNoticias.spiders"
+
+FEED_EXPORT_ENCODING="utf-8"
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = "aristeguiNoticias (+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 = {
+#    "aristeguiNoticias.middlewares.AristeguinoticiasSpiderMiddleware": 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    "aristeguiNoticias.middlewares.AristeguinoticiasDownloaderMiddleware": 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 = {
+#    "aristeguiNoticias.pipelines.AristeguinoticiasPipeline": 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/aristeguiNoticias/aristeguiNoticias/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/aristeguiNoticias/aristeguiNoticias/spiders/noticias.py

+"""
+	Spider for aristeguinoticias.com
+	Author: Ulises Morales Ramirez
+	Usage:scrapy crawl noticias --nolog -O 2017-04-23.json -a year=2017 -a month=4 -a day=23 
+
+"""
+import scrapy
+import json
+import re
+from aristeguiNoticias.items import AristeguinoticiasItem
+
+TAG_RE = re.compile(r'<[^>]+>')
+
+def remove_tags(text):
+    """
+    Función que elimina las etiquetas HTML de una cadena utilizando una expresión regular.
+    
+    Parameters
+    ----------
+    text : str
+        La cadena que contiene las etiquetas HTML que se desean eliminar.
+    
+    Returns
+    -------
+    str
+        La cadena sin etiquetas HTML.
+    """
+    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 = ["aristeguinoticias.com"]
+    start_urls = ["https://aristeguinoticias.com/"]
+    categories = {
+        2907: "investigaciones-especiales",
+        3: "mexico",
+        1936: "dinero-y-economia",
+        1933: "deportes",
+        37: "mundo",
+        10: "kiosko",
+        5: "opinion",
+        1935: "cultura",
+        9798: "cultura",
+        12: "entrevistas",
+        41: "kiosko"
+    }
+    
+    
+    def start_requests(self):
+        """
+        This function is called to generate the initial requests to start crawling
+        from. It is responsible for defining the start URLs, and the callback
+        function to be used to handle the response from each of them.
+
+        :return: An iterable of Requests
+        """
+        for url in self.start_urls:
+            print(url)
+            yield scrapy.Request(url=url, callback=self.parse)
+    
+    def parse(self, response):
+        next_data_script = response.xpath('//script[@id="__NEXT_DATA__"]/text()').get()
+
+        if next_data_script:
+            try:
+                next_data_json = json.loads(next_data_script)
+                token = next_data_json["buildId"]
+                pageProps = next_data_json["props"]["pageProps"]
+
+                def extract_info(articulos):
+                    extracted_data = []
+                    for articulo in articulos:
+                        category_id = articulo.get('categories', [None])[0]
+                        category_name = self.categories.get(int(category_id), 'unknown') if category_id else 'unknown'
+                        extracted_data.append({
+                            'post_fecha': articulo.get('post_fecha'),
+                            'post_slug': articulo.get('post_slug'),
+                            'categories': category_name
+                        })
+                    return extracted_data
+                
+                all_articles = []
+                for key, value in pageProps.items():
+                    if isinstance(value, list):
+                        all_articles.extend(extract_info(value))
+
+
+                # Imprimir o procesar los datos extraídos
+                for articulo in all_articles:
+                    if articulo["post_fecha"] is None or articulo["post_slug"] is None or articulo["categories"] is None:
+                        continue
+                    final_url = f"https://aristeguinoticias.com/_next/data/{token}/es/{articulo["post_fecha"]}/{articulo["categories"]}/{articulo["post_slug"]}.json"
+                    yield scrapy.Request(url=final_url, callback=self.parse_article)
+
+                    
+                    
+            except json.JSONDecodeError as e:
+                self.log(f"Error al parsear el contenido JSON: {e}")
+                yield {"error": "No se pudo parsear el contenido JSON"}
+        else:
+            self.log("No se encontró la etiqueta <script> con id='__NEXT_DATA__'.")
+            
+            
+    def parse_article(self, response):
+        try:
+            data = json.loads(response.body)
+            page_props = data.get("pageProps", {})
+            item = AristeguinoticiasItem()
+            article_info = {
+                'slug': page_props.get('slug'),
+                'id': page_props.get('id'),
+                'fecha': page_props.get('fecha'),
+                'titulo_seccion': page_props.get('titulo_seccion'),
+                'title': page_props.get('title'),
+                'contents': ' '.join(str(content.get('content', '')) for content in page_props.get('contents', [])),
+                'author_display_name': page_props.get('author_display_name'),
+                'url': page_props.get('url_share')
+            }
+            
+            date = article_info.get("fecha")
+            title = article_info.get("title")
+            topic = article_info.get("titulo_seccion")
+            text = article_info.get("contents")
+            author_name = article_info.get("author_display_name")
+            url = article_info.get("url")
+            
+            cleaned_text = ' '.join(remove_tags(content) for content in text.splitlines())
+            
+            if cleaned_text.strip():
+                item = {
+                    'date': date,
+                    'title': remove_tags(title),
+                    'topic': remove_tags(topic),
+                    'text': cleaned_text,
+                    'url': url,
+                    'author': author_name
+                }
+                yield item
+                
+        except json.JSONDecodeError as e:
+            self.log(f"Error al parsear el contenido del artículo: {e}")

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