commit 75e9ab0d1545587a2e04887ae1db4c2407cffe9e Author: shagi Date: Sun Mar 26 12:00:27 2023 +0200 Initial Commit diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..a6c57f5 --- /dev/null +++ b/.gitignore @@ -0,0 +1 @@ +*.json diff --git a/paginas_amarillas/__init__.py b/paginas_amarillas/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/paginas_amarillas/items.py b/paginas_amarillas/items.py new file mode 100644 index 0000000..2f2d432 --- /dev/null +++ b/paginas_amarillas/items.py @@ -0,0 +1,12 @@ +# Define here the models for your scraped items +# +# See documentation in: +# https://docs.scrapy.org/en/latest/topics/items.html + +import scrapy + + +class PaginasAmarillasItem(scrapy.Item): + # define the fields for your item here like: + # name = scrapy.Field() + pass diff --git a/paginas_amarillas/middlewares.py b/paginas_amarillas/middlewares.py new file mode 100644 index 0000000..f99af8d --- /dev/null +++ b/paginas_amarillas/middlewares.py @@ -0,0 +1,103 @@ +# 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 PaginasAmarillasSpiderMiddleware: + # 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 PaginasAmarillasDownloaderMiddleware: + # 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) diff --git a/paginas_amarillas/pipelines.py b/paginas_amarillas/pipelines.py new file mode 100644 index 0000000..e36667a --- /dev/null +++ b/paginas_amarillas/pipelines.py @@ -0,0 +1,13 @@ +# 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 PaginasAmarillasPipeline: + def process_item(self, item, spider): + return item diff --git a/paginas_amarillas/settings.py b/paginas_amarillas/settings.py new file mode 100644 index 0000000..d4d0487 --- /dev/null +++ b/paginas_amarillas/settings.py @@ -0,0 +1,93 @@ +# Scrapy settings for paginas_amarillas 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 = "paginas_amarillas" + +SPIDER_MODULES = ["paginas_amarillas.spiders"] +NEWSPIDER_MODULE = "paginas_amarillas.spiders" + + +# Crawl responsibly by identifying yourself (and your website) on the user-agent +#USER_AGENT = "paginas_amarillas (+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 = { +# "paginas_amarillas.middlewares.PaginasAmarillasSpiderMiddleware": 543, +#} + +# Enable or disable downloader middlewares +# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html +#DOWNLOADER_MIDDLEWARES = { +# "paginas_amarillas.middlewares.PaginasAmarillasDownloaderMiddleware": 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 = { +# "paginas_amarillas.pipelines.PaginasAmarillasPipeline": 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 +REQUEST_FINGERPRINTER_IMPLEMENTATION = "2.7" +TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor" +FEED_EXPORT_ENCODING = "utf-8" diff --git a/paginas_amarillas/spiders/__init__.py b/paginas_amarillas/spiders/__init__.py new file mode 100644 index 0000000..ebd689a --- /dev/null +++ b/paginas_amarillas/spiders/__init__.py @@ -0,0 +1,4 @@ +# 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. diff --git a/paginas_amarillas/spiders/spider.py b/paginas_amarillas/spiders/spider.py new file mode 100644 index 0000000..551057f --- /dev/null +++ b/paginas_amarillas/spiders/spider.py @@ -0,0 +1,33 @@ +import scrapy + + +class PaginasAmarillasSpider(scrapy.Spider): + name = "paginas_amarillas" + start_urls = [ + # "https://www.paginasamarillas.es/search/peluqueria/all-ma/gipuzkoa/all-is/all-ci/all-ba/all-pu/all-nc/1?what=peluquer%C3%ADa&where=gipuzkoa&qc=true" + "https://www.paginasamarillas.es/search/dentista/all-ma/gipuzkoa/all-is/all-ci/all-ba/all-pu/all-nc/1?what=dentista&where=gipuzkoa&qc=true" + ] + + def parse(self, response): + for item in response.css('.listado-item'): + name = item.css('span[itemprop="name"]::text').get() + phone = item.css('span[itemprop="telephone"]::text').get() + address = item.css('span[itemprop="address"]') + street = address.css('span[itemprop="streetAddress"]::text').get() + postal_code = address.css('span[itemprop="postalCode"]::text').get() + locality = address.css('span[itemprop="addressLocality"]::text').get() + web = item.css('a.web[itemprop="url"]::attr(href)').get() + yield { + 'name': name, + 'phone': phone, + 'address': { + 'street': street, + 'postal_code': postal_code, + 'locality': locality, + }, + 'web': web, + } + + next_link = response.css('.pagination a::attr(href)').getall()[-1] + if next_link and not next_link.startswith('javascript'): + yield response.follow(next_link, callback=self.parse) diff --git a/readme.md b/readme.md new file mode 100644 index 0000000..367a35c --- /dev/null +++ b/readme.md @@ -0,0 +1,14 @@ +# Crawler de páginas amarillas + +## Instalación + + pip install -r requirements.txt + +## Ejecución + + scrapy crawl paginas_amarillas -O telefonos_dentistas.json + +## Configuración + +Editar el fichero paginas_amarillas/spiders/spider.py y meter en la lista +`start_urls` la primera página de la búsqueda de páginas amarillas. diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..0beacdc --- /dev/null +++ b/requirements.txt @@ -0,0 +1 @@ +Scrapy==2.8.0 diff --git a/scrapy.cfg b/scrapy.cfg new file mode 100644 index 0000000..6774077 --- /dev/null +++ b/scrapy.cfg @@ -0,0 +1,11 @@ +# Automatically created by: scrapy startproject +# +# For more information about the [deploy] section see: +# https://scrapyd.readthedocs.io/en/latest/deploy.html + +[settings] +default = paginas_amarillas.settings + +[deploy] +#url = http://localhost:6800/ +project = paginas_amarillas