diarioamanecer

spiders/daily/diarioAmanecer/diarioAmanecer/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 DiarioamanecerItem(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/diarioAmanecer/diarioAmanecer/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 DiarioamanecerSpiderMiddleware:
+    # 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 DiarioamanecerDownloaderMiddleware:
+    # 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/diarioAmanecer/diarioAmanecer/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 DiarioamanecerPipeline:
+    def process_item(self, item, spider):
+        return item

spiders/daily/diarioAmanecer/diarioAmanecer/settings.py

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

+import scrapy
+import json
+import re
+from diarioAmanecer.items import DiarioamanecerItem
+
+# Expresión regular para eliminar etiquetas HTML
+TAG_RE = re.compile(r'<[^>]+>')
+
+def remove_tags(text):
+
+    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 = ["www.diarioamanecer.com.mx", "diarioamanecer.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"https://www.diarioamanecer.com.mx/wp-json/wp/v2/posts?after={self.year}-{self.month}-{self.day}T00:00:00&before={self.year}-{self.month}-{self.day}T23:59:59&per_page=1"
+            ]
+
+    def parse(self, response):
+        data = json.loads(response.text)
+        for post in data:
+            # Validar que el contenido no esté vacío
+            content = post.get('content', {}).get('rendered', '').strip()
+            if not content:
+                self.logger.info(f"Post {post.get('id')} skipped due to empty content.")
+                continue
+            
+            # Obtener el séptimo elemento de class_list si existe
+            class_list = post.get('class_list', [])
+            topic = class_list[7] if len(class_list) > 7 else None
+            
+            # Obtener el enlace del autor
+            author_link = post.get('_links', {}).get('author', [{}])[0].get('href')
+            
+            # Crear un item con los campos requeridos
+            item = DiarioamanecerItem()
+            item['date'] = post.get('date')
+            item['title'] = remove_tags(post.get('title', {}).get('rendered', ''))
+            item['text'] = remove_tags(content)
+            item['topic'] = topic.split("category-")[1]
+            item['url'] = post.get('link')
+            #item['author'] = author_link
+            print(author_link)
+            if author_link:
+                # Hacer una solicitud adicional para obtener el nombre del autor
+                yield scrapy.Request(url=author_link, callback=self.parse_author, meta={'item': item})
+            else:
+                yield item  # Si no hay URL del autor, se devuelve el item sin autor
+
+    def parse_author(self, response):
+        item = response.meta['item']  # Recupera el item pasado a través de meta
+        author_data = json.loads(response.text)
+        item['author'] = author_data.get('name', 'Unknown')  # Asigna el nombre del autor o 'Unknown' si no está disponible
+        
+        yield item  # Devuelve el item completo con el nombre del autor incluido
+
+

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