commit f33eda3ff15c754aca4908995621796bc1b73b46 Author: Yohann Dedy Date: Tue Nov 26 22:02:40 2019 +0100 first commit diff --git a/FMScraper/__init__.py b/FMScraper/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/FMScraper/items.py b/FMScraper/items.py new file mode 100644 index 0000000..400fa03 --- /dev/null +++ b/FMScraper/items.py @@ -0,0 +1,29 @@ +# -*- coding: utf-8 -*- + +# Define here the models for your scraped items +# +# See documentation in: +# https://docs.scrapy.org/en/latest/topics/items.html + +import scrapy + + +class FmscraperItem(scrapy.Item): + # define the fields for your item here like: + # name = scrapy.Field() + pass + +class show_Item(scrapy.Item): + name = scrapy.Field() + url_page = scrapy.Field() + url_feed = scrapy.Field() + tags = scrapy.Field() + +class episode_Item(scrapy.Item): + title = scrapy.Field() + description_lead = scrapy.Field() + description_full = scrapy.Field() + url_file = scrapy.Field() + url_page = scrapy.Field() + date_diffusion = scrapy.Field() + diff --git a/FMScraper/middlewares.py b/FMScraper/middlewares.py new file mode 100644 index 0000000..956f170 --- /dev/null +++ b/FMScraper/middlewares.py @@ -0,0 +1,103 @@ +# -*- coding: utf-8 -*- + +# 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 + + +class FmscraperSpiderMiddleware(object): + # 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, dict 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, dict + # 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 FmscraperDownloaderMiddleware(object): + # 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/FMScraper/pipelines.py b/FMScraper/pipelines.py new file mode 100644 index 0000000..307f9fe --- /dev/null +++ b/FMScraper/pipelines.py @@ -0,0 +1,11 @@ +# -*- coding: utf-8 -*- + +# 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 + + +class FmscraperPipeline(object): + def process_item(self, item, spider): + return item diff --git a/FMScraper/settings.py b/FMScraper/settings.py new file mode 100644 index 0000000..d8ef655 --- /dev/null +++ b/FMScraper/settings.py @@ -0,0 +1,90 @@ +# -*- coding: utf-8 -*- + +# Scrapy settings for FMScraper 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 = 'FMScraper' + +SPIDER_MODULES = ['FMScraper.spiders'] +NEWSPIDER_MODULE = 'FMScraper.spiders' + + +# Crawl responsibly by identifying yourself (and your website) on the user-agent +#USER_AGENT = 'FMScraper (+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 = { +# 'FMScraper.middlewares.FmscraperSpiderMiddleware': 543, +#} + +# Enable or disable downloader middlewares +# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html +#DOWNLOADER_MIDDLEWARES = { +# 'FMScraper.middlewares.FmscraperDownloaderMiddleware': 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 = { +# 'FMScraper.pipelines.FmscraperPipeline': 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' diff --git a/FMScraper/spiders/__init__.py b/FMScraper/spiders/__init__.py new file mode 100644 index 0000000..ebd689a --- /dev/null +++ b/FMScraper/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/FMScraper/spiders/get_episodes.py b/FMScraper/spiders/get_episodes.py new file mode 100644 index 0000000..527ca44 --- /dev/null +++ b/FMScraper/spiders/get_episodes.py @@ -0,0 +1,36 @@ +# -*- coding: utf-8 -*- +import scrapy +from scrapy.loader import ItemLoader +from scrapy.loader.processors import Join, MapCompose, TakeFirst +from FMScraper.items import episode_Item + +class GetEpisodesSpider(scrapy.Spider): + name = 'get_episodes' + allowed_domains = ['francemusique.fr'] + start_urls = ['https://www.francemusique.fr/emissions/l-experimentale'] + + episode_xpath = '//article[@class="diffusion"]' + episode_fields = { + 'title' : '//h1[@class="cover-diffusion-main-info-title"]/text()', + 'description_lead' : '//h2[@class="content-body-chapo"]/text()', + 'description_full' : '//div[@class="content-body-article"]', + 'url_file' : '//div[@class="cover-diffusion-main-info"]//button[@class="replay-button playable"]/@data-url', +# 'url_page' : '//iframe/@src', + 'date_diffusion' : '//div[@class="cover-diffusion-text-date"]/text()', + } + + def parse(self, response): + for sel in response.xpath('//section[@class="emission-diffusions-list"]'): + url_episode = response.urljoin(sel.xpath('.//a[@class="preview-list-element-link"]/@href').extract_first()) + yield scrapy.Request(url_episode, callback = self.parse_episode) + + def parse_episode(self, response): + page_episode = scrapy.Selector(response) + for page in page_episode.xpath(self.episode_xpath): + loader = ItemLoader(item=episode_Item(), selector=page) + loader.default_output_processor = Join() + + for field, xpath in self.episode_fields.items(): + loader.add_xpath(field, xpath) + + yield loader.load_item() diff --git a/scrapy.cfg b/scrapy.cfg new file mode 100644 index 0000000..b9f0957 --- /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 = FMScraper.settings + +[deploy] +#url = http://localhost:6800/ +project = FMScraper