Merge branch 'pruebas' into 'master'

Pruebas

See merge request !2

scripts/crawlAll.py

@@ -4,41 +4,46 @@ import datetime
 import glob
 import json
 import os
-#===============================================================================
-
 
 #===============================================================================
 def main(argv):
-	'''
+    '''
+    Main function to process directories and run crawlers.
+    '''
+    cwd = os.getcwd()
+    if len(argv) != 2 and len(argv) != 3:
+        print("Usage: " + argv[0] + " <directory> [endDate:YYYY-MM-DD]")
+    else:
+        rootdir = argv[1]
+        
+        # Ensure the log directory exists
+        if not os.path.exists(rootdir):
+            os.makedirs(rootdir)
 
+        log_filename = rootdir + "/" + datetime.datetime.today().strftime('%Y-%m-%d') + ".log"
+        with open(log_filename, "a") as logfile:
+            for path in sorted(glob.glob(f'{rootdir}/*/')):
+                print(path)
+                if not os.path.exists(path + 'settings.json'):
+                    logfile.write("\t configuration file <" + path + "settings.json> not found.\n")
+                    continue
+                with open(path + 'settings.json') as json_file:
+                    cfg = json.load(json_file)
+                    print(cfg)
+                if not cfg["enabled"]:
+                    continue
+                logfile.write("Crawler " + cfg["crawler"] + " started at: " +
+                              datetime.datetime.now().strftime("%Y-%m-%d, %H:%M:%S") + "\n")
 
-	'''
-	cwd = os.getcwd()
-	if len(argv) != 2 and len(argv) != 3:
-		print ("Usage: " + argv[0] + "<directory> [endDate:YYYY-MM-DD]")
-	else:
-		rootdir = argv[1]
-		with open(rootdir+"/"+datetime.datetime.today().strftime('%Y-%m-%d')+".log", "a") as logfile:
-			for path in sorted(glob.glob(f'{rootdir}/*/')):
-				print(path)
-				if not os.path.exists(path+'settings.json'):
-					logfile.write("\t configuration file <"+path+"settings.json> not found.\n")
-					continue
-				with open(path+'settings.json') as json_file:
-						cfg = json.load(json_file)
-						print(cfg)
-				if not cfg["enabled"]:
-					continue
-				logfile.write("Crawler "+cfg["crawler"]+" started at: " +datetime.datetime.now().strftime("%Y-%m-%d, %H:%M:%S")+"\n")
+                new_cwd = os.getcwd() + "/spiders/" + cfg["crawler"]
+                if os.path.exists(new_cwd):
+                    os.chdir(new_cwd)
+                    os.system("python3 ../../../scripts/siteCrawler.py " + path)
+                else:
+                    logfile.write("\t spider not found.\n")
+                print(os.getcwd())
+                os.chdir(cwd)
 
-				new_cwd = os.getcwd()+"/spiders/"+cfg["crawler"]
-				if os.path.exists(new_cwd):
-					os.chdir(new_cwd)
-					os.system("python3 ../../../scripts/siteCrawler.py " + path)
-				else:
-					logfile.write("\t spider not found.\n")
-				print(os.getcwd())
-				os.chdir(cwd)
 #-------------------------------------------------------------------------------
 if __name__ == "__main__":
-	main(sys.argv)
+    main(sys.argv)

spiders/backwards/elFinanciero/elFinanciero/spiders/noticias.py

@@ -84,14 +84,12 @@ class QuotesSpider(scrapy.Spider):
         self.uri_base = "http://api.elfinanciero.com.mx/public/search/typed/?_format=json&json={%22search%22:%22*%22,%22categoriesslug%22:%22"
         self.uri_page = "%22}&type=page&page="
         self.uri_complement = "&size=10"
-
-	print(self.uri_base+self.uri_page+self.uri_complement)
+        print(self.uri_base+self.uri_page+self.uri_complement)
         for s in sectionList:
             yield scrapy.Request(url=self.baseURL + s, callback=self.parse)
 
-
     def parse(self, response):
-	print(response.url)
+        print(response.url)
         searchData = ImportantData()
 
         CONTINUE_SEARCHING = True

spiders/daily/animalPolitico/animalPolitico/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 AnimalpoliticoItem(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/animalPolitico/animalPolitico/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 AnimalpoliticoSpiderMiddleware:
+    # 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 AnimalpoliticoDownloaderMiddleware:
+    # 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/animalPolitico/animalPolitico/payload_manager.py

+import json
+from datetime import datetime, timedelta
+
+
+class PayloadManager:
+    def __init__(self):
+        self.payload = {
+            "operationName": "FetchAllPostTypes",
+            "variables": {
+                "where": {
+                    "search": "",
+                    "orderby": [
+                        {
+                            "field": "DATE",
+                            "order": "DESC"
+                        }
+                    ],
+                    "dateQuery": {
+                        "inclusive": True,
+                        "after": {
+                            "day": 12,
+                            "month": 1,
+                            "year": 2025
+                        },
+                        "before": {
+                            "day": 13,
+                            "month": 1,
+                            "year": 2025
+                        }
+                    },
+                    "offsetPagination": {
+                        "size": 12,
+                        "offset": 0
+                    }
+                }
+            },
+            "query": """query FetchAllPostTypes($first: Int, $where: RootQueryToAllPostTypesConnectionWhereArgs) {
+                allPostTypes(first: $first, where: $where) {
+                    edges {
+                        node {
+                            databaseId
+                            id
+                            title
+                            slug
+                            titleHome
+                            contentTypeName
+                            uri
+                            image
+                            excerpt
+                            categoryPrimarySlug
+                            blogSlug
+                            blogIsOrganization
+                            sabuesoType
+                            date
+                            dateGmt
+                            isContentSponsored
+                            contentRendered
+                            blogId
+                            readingTime
+                            postExcerpt
+                            blogAuthor
+                            authorNote
+                            videoUrl
+                            authorName
+                            terms {
+                                edges {
+                                    node {
+                                        id
+                                        slug
+                                        name
+                                        __typename
+                                    }
+                                    __typename
+                                }
+                                __typename
+                            }
+                            relatedPosts {
+                                id
+                                databaseId
+                                title
+                                slug
+                                titleHome
+                                contentTypeName
+                                uri
+                                image
+                                sabuesoType
+                                terms {
+                                    edges {
+                                        node {
+                                            id
+                                            slug
+                                            __typename
+                                        }
+                                        __typename
+                                    }
+                                    __typename
+                                }
+                                author {
+                                    node {
+                                        name
+                                        lastName
+                                        firstName
+                                        __typename
+                                    }
+                                    __typename
+                                }
+                                featuredImage {
+                                    node {
+                                        id
+                                        sourceUrl
+                                        imageFooter
+                                        __typename
+                                    }
+                                    __typename
+                                }
+                                __typename
+                            }
+                            featuredImage {
+                                node {
+                                    id
+                                    sourceUrl(size: LARGE)
+                                    imageFooter
+                                    __typename
+                                }
+                                __typename
+                            }
+                            author {
+                                node {
+                                    name
+                                    __typename
+                                }
+                                __typename
+                            }
+                            __typename
+                        }
+                        __typename
+                    }
+                    pageInfo {
+                        offsetPagination {
+                            total
+                            __typename
+                        }
+                        __typename
+                    }
+                    __typename
+                }
+            }"""
+            }
+        
+    def get_payload(self):
+        return self.payload
+    
+    def _date_divider(tipo,date):
+        if tipo == 'd':
+            return date.strftime("%d")
+        if tipo == 'm':
+            return date.strftime("%m")
+        if tipo == 'y':
+            return date.strftime("%Y")
+    
+    def update_payload(self, inicio, fin):
+        self.payload["variables"]["where"]["dateQuery"]["after"] = {
+            "day": datetime.now().day,
+            "month": datetime.now().month,
+            "year": datetime.now().year
+        }
+        self.payload["variables"]["where"]["dateQuery"]["before"] = {
+            "day": datetime.now().day,
+            "month": datetime.now().month,
+            "year": datetime.now().year
+        }
+        return self.payload
\ No newline at end of file

spiders/daily/animalPolitico/animalPolitico/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 AnimalpoliticoPipeline:
+    def process_item(self, item, spider):
+        return item

spiders/daily/animalPolitico/animalPolitico/settings.py

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

+"""
+	Spider for jornada.com.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 json
+import re
+from animalPolitico.payload_manager import PayloadManager
+from animalPolitico.items import AnimalpoliticoItem
+
+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 = ['animalpolitico.com']
+    start_urls = ["https://panel.animalpolitico.com/graphql"]
+    
+    def start_requests(self):
+        """
+        Starts the requests for crawling the news of Animal Político.
+        
+        The method generates a payload with the query and variables for GraphQL
+        and sends a POST request to the GraphQL API. The response is processed
+        in the parse method.
+        """
+        url = self.start_urls[0]
+        self.year = getattr(self, "year", None)
+        self.month = getattr(self, "month", None)
+        self.day = getattr(self, "day", None)
+  
+        payload = {
+                    "operationName":"FetchAllPostTypes",
+                    "variables":{
+                        "where":{
+                            "search":"",
+                            "orderby":[
+                                {
+                                    "field":"DATE",
+                                    "order":"DESC"
+                                }
+                            ],
+                            "dateQuery":{
+                                "inclusive":True,
+                                "after":{
+                                    "day":int(self.day),
+                                    "month":int(self.month),
+                                    "year":int(self.year)
+                                },
+                                "before":{
+                                    "day":int(self.day),
+                                    "month":int(self.month),
+                                    "year":int(self.year)
+                                }
+                            },
+                            "offsetPagination":{
+                                "size":1000,
+                                "offset":0
+                            }
+                        }
+                    },
+                    "query":"query FetchAllPostTypes($first: Int, $where: RootQueryToAllPostTypesConnectionWhereArgs) {\n allPostTypes(first: $first, where: $where) {\n    edges {\n node {\n databaseId\n id\n title\n slug\n titleHome\n contentTypeName\n uri\n image\n excerpt\n categoryPrimarySlug\n blogSlug\n blogIsOrganization\n sabuesoType\n date\n dateGmt\n isContentSponsored\n contentRendered\n blogId\n readingTime\n postExcerpt\n blogAuthor\n authorNote\n videoUrl\n authorName\n terms {\n edges {\n node {\n id\n slug\n name\n __typename\n }\n __typename\n }\n __typename\n }\n relatedPosts {\n id\n databaseId\n title\n slug\n titleHome\n contentTypeName\n uri\n image\n sabuesoType\n terms {\n edges {\n node {\n id\n slug\n __typename\n }\n __typename\n }\n __typename\n }\n author {\n node {\n name\n lastName\n firstName\n __typename\n }\n __typename\n }\n featuredImage {\n node {\n id\n sourceUrl\n imageFooter\n __typename\n }\n __typename\n }\n __typename\n }\n featuredImage {\n node {\n id\n sourceUrl(size: LARGE)\n imageFooter\n __typename\n }\n __typename\n }\n author {\n node {\n name\n __typename\n }\n __typename\n }\n __typename\n }\n __typename\n    }\n    pageInfo {\n offsetPagination {\n total\n __typename\n }\n __typename\n    }\n    __typename\n }\n    }"
+                    }
+        headers = {
+            'Content-Type': 'application/json'
+        }
+
+        yield scrapy.Request(
+            url=url,
+            method="POST",
+            headers=headers,
+            body=json.dumps(payload),
+            callback=self.parse
+        )
+
+    def parse(self, response):
+        """
+        Parse a JSON response from Animal Político's GraphQL API.
+        
+        Yields a dictionary containing the title, topic, text, URL, and author
+        of each article in the response.
+        
+        """
+        data = json.loads(response.text)
+        
+        item = AnimalpoliticoItem()
+        
+        for edge in data.get("data", {}).get("allPostTypes", {}).get("edges", []):
+            node = edge.get("node", {})
+            item['date']  = node.get("date")
+            item['title'] = remove_tags(node.get("title"))
+            item['topic'] = remove_tags(node.get("contentTypeName"))
+            item['text']  = remove_tags(node.get("contentRendered"))
+            item['url']   = "https://"+self.allowed_domains[0]+"/" + node.get("uri")
+            item['author'] = node.get("author", {}).get("node", {}).get("name")
+            yield item

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