commit 098bc159cb2c268f9daec7f2fe6aa4ec95721c91 Author: Yohann Dedy Date: Thu May 10 19:31:59 2018 +0200 Premier commit diff --git a/CinemScraper/__init__.py b/CinemScraper/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/CinemScraper/__init__.pyc b/CinemScraper/__init__.pyc new file mode 100644 index 0000000..fc061b3 Binary files /dev/null and b/CinemScraper/__init__.pyc differ diff --git a/CinemScraper/items.py b/CinemScraper/items.py new file mode 100644 index 0000000..c1a615d --- /dev/null +++ b/CinemScraper/items.py @@ -0,0 +1,14 @@ +# -*- coding: utf-8 -*- + +# Define here the models for your scraped items +# +# See documentation in: +# https://doc.scrapy.org/en/latest/topics/items.html + +import scrapy + + +class CinemscraperItem(scrapy.Item): + # define the fields for your item here like: + # name = scrapy.Field() + pass diff --git a/CinemScraper/middlewares.py b/CinemScraper/middlewares.py new file mode 100644 index 0000000..16959e2 --- /dev/null +++ b/CinemScraper/middlewares.py @@ -0,0 +1,103 @@ +# -*- coding: utf-8 -*- + +# Define here the models for your spider middleware +# +# See documentation in: +# https://doc.scrapy.org/en/latest/topics/spider-middleware.html + +from scrapy import signals + + +class CinemscraperSpiderMiddleware(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 Response, 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 CinemscraperDownloaderMiddleware(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/CinemScraper/pipelines.py b/CinemScraper/pipelines.py new file mode 100644 index 0000000..117d04f --- /dev/null +++ b/CinemScraper/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://doc.scrapy.org/en/latest/topics/item-pipeline.html + + +class CinemscraperPipeline(object): + def process_item(self, item, spider): + return item diff --git a/CinemScraper/settings.py b/CinemScraper/settings.py new file mode 100644 index 0000000..076db23 --- /dev/null +++ b/CinemScraper/settings.py @@ -0,0 +1,90 @@ +# -*- coding: utf-8 -*- + +# Scrapy settings for CinemScraper project +# +# For simplicity, this file contains only settings considered important or +# commonly used. You can find more settings consulting the documentation: +# +# https://doc.scrapy.org/en/latest/topics/settings.html +# https://doc.scrapy.org/en/latest/topics/downloader-middleware.html +# https://doc.scrapy.org/en/latest/topics/spider-middleware.html + +BOT_NAME = 'CinemScraper' + +SPIDER_MODULES = ['CinemScraper.spiders'] +NEWSPIDER_MODULE = 'CinemScraper.spiders' + +FEED_EXPORT_ENCODING = 'utf-8' +# Crawl responsibly by identifying yourself (and your website) on the user-agent +#USER_AGENT = 'CinemScraper (+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://doc.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://doc.scrapy.org/en/latest/topics/spider-middleware.html +#SPIDER_MIDDLEWARES = { +# 'CinemScraper.middlewares.CinemscraperSpiderMiddleware': 543, +#} + +# Enable or disable downloader middlewares +# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html +#DOWNLOADER_MIDDLEWARES = { +# 'CinemScraper.middlewares.CinemscraperDownloaderMiddleware': 543, +#} + +# Enable or disable extensions +# See https://doc.scrapy.org/en/latest/topics/extensions.html +#EXTENSIONS = { +# 'scrapy.extensions.telnet.TelnetConsole': None, +#} + +# Configure item pipelines +# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html +#ITEM_PIPELINES = { +# 'CinemScraper.pipelines.CinemscraperPipeline': 300, +#} + +# Enable and configure the AutoThrottle extension (disabled by default) +# See https://doc.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://doc.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/CinemScraper/settings.pyc b/CinemScraper/settings.pyc new file mode 100644 index 0000000..d28dbf3 Binary files /dev/null and b/CinemScraper/settings.pyc differ diff --git a/CinemScraper/spiders/__init__.py b/CinemScraper/spiders/__init__.py new file mode 100644 index 0000000..ebd689a --- /dev/null +++ b/CinemScraper/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/CinemScraper/spiders/__init__.pyc b/CinemScraper/spiders/__init__.pyc new file mode 100644 index 0000000..53be15a Binary files /dev/null and b/CinemScraper/spiders/__init__.pyc differ diff --git a/CinemScraper/spiders/grabVideoData.py b/CinemScraper/spiders/grabVideoData.py new file mode 100644 index 0000000..05a1a3c --- /dev/null +++ b/CinemScraper/spiders/grabVideoData.py @@ -0,0 +1,20 @@ +# -*- coding: utf-8 -*- +import scrapy + + +class GrabvideodataSpider(scrapy.Spider): + name = 'grabVideoData' + allowed_domains = ['http://www.cinematheque.fr/'] + start_urls = ['http://www.cinematheque.fr/video/1219.html'] + + def parse(self, response): + for page in response.css("div#content"): + yield { + 'titre' : page.css('h1::text').extract_first(), + 'sous-titre' : page.css('h1 span::text').extract_first(), + 'description' : page.css('.biographies p').extract(), + 'videoSrcUrl' : page.css('iframe::attr(src)').extract_first(), + 'tags' : page.css('.tag::text').extract() + } + + diff --git a/CinemScraper/spiders/grabVideoData.pyc b/CinemScraper/spiders/grabVideoData.pyc new file mode 100644 index 0000000..7bc44dd Binary files /dev/null and b/CinemScraper/spiders/grabVideoData.pyc differ diff --git a/CinemScraper/spiders/listeVideos.py b/CinemScraper/spiders/listeVideos.py new file mode 100644 index 0000000..e25581b --- /dev/null +++ b/CinemScraper/spiders/listeVideos.py @@ -0,0 +1,18 @@ +# -*- coding: utf-8 -*- +import scrapy + + +class ListevideosSpider(scrapy.Spider): + name = 'listeVideos' + allowed_domains = ['http://www.cinematheque.fr/'] + start_urls = ['http://www.cinematheque.fr/decouvrir.html'] + + def parse(self, response): + for lien in response.xpath('//a/@href[contains(.,"video")]/../..'): + yield { + 'adresse' : lien.css('a::attr(href)').extract(), + 'dateUpload' : lien.css('::attr(data-sort)').extract(), + + } + + diff --git a/CinemScraper/spiders/listeVideos.pyc b/CinemScraper/spiders/listeVideos.pyc new file mode 100644 index 0000000..ca00c6a Binary files /dev/null and b/CinemScraper/spiders/listeVideos.pyc differ diff --git a/README.md b/README.md new file mode 100644 index 0000000..e69de29 diff --git a/scrapy.cfg b/scrapy.cfg new file mode 100644 index 0000000..bef157a --- /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 = CinemScraper.settings + +[deploy] +#url = http://localhost:6800/ +project = CinemScraper