From 098bc159cb2c268f9daec7f2fe6aa4ec95721c91 Mon Sep 17 00:00:00 2001
From: Yohann Dedy <yohann@dedy.fr>
Date: Thu, 10 May 2018 19:31:59 +0200
Subject: [PATCH] Premier commit

---
 CinemScraper/__init__.py               |   0
 CinemScraper/__init__.pyc              | Bin 0 -> 142 bytes
 CinemScraper/items.py                  |  14 ++++
 CinemScraper/middlewares.py            | 103 +++++++++++++++++++++++++
 CinemScraper/pipelines.py              |  11 +++
 CinemScraper/settings.py               |  90 +++++++++++++++++++++
 CinemScraper/settings.pyc              | Bin 0 -> 341 bytes
 CinemScraper/spiders/__init__.py       |   4 +
 CinemScraper/spiders/__init__.pyc      | Bin 0 -> 150 bytes
 CinemScraper/spiders/grabVideoData.py  |  20 +++++
 CinemScraper/spiders/grabVideoData.pyc | Bin 0 -> 1144 bytes
 CinemScraper/spiders/listeVideos.py    |  18 +++++
 CinemScraper/spiders/listeVideos.pyc   | Bin 0 -> 929 bytes
 README.md                              |   0
 scrapy.cfg                             |  11 +++
 15 files changed, 271 insertions(+)
 create mode 100644 CinemScraper/__init__.py
 create mode 100644 CinemScraper/__init__.pyc
 create mode 100644 CinemScraper/items.py
 create mode 100644 CinemScraper/middlewares.py
 create mode 100644 CinemScraper/pipelines.py
 create mode 100644 CinemScraper/settings.py
 create mode 100644 CinemScraper/settings.pyc
 create mode 100644 CinemScraper/spiders/__init__.py
 create mode 100644 CinemScraper/spiders/__init__.pyc
 create mode 100644 CinemScraper/spiders/grabVideoData.py
 create mode 100644 CinemScraper/spiders/grabVideoData.pyc
 create mode 100644 CinemScraper/spiders/listeVideos.py
 create mode 100644 CinemScraper/spiders/listeVideos.pyc
 create mode 100644 README.md
 create mode 100644 scrapy.cfg

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 0000000000000000000000000000000000000000..fc061b3de9f5571cf12cf4ab53054c514c76ef72
GIT binary patch
literal 142
zcmZSn%*)l<^f@Y-0SXv_v;z<qvjB+{28Lh_kcgiKkYGR~ip_yy`eFGwrMaoa`Yw(k
zj`}XHVfxOQd8xU<$wi3;sYR%q`1s7c%#!$cy@JXT4xnC}-29Z%oK!oI4aGpr002pa
B9-;sM

literal 0
HcmV?d00001

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 0000000000000000000000000000000000000000..d28dbf378d95c7c760521f3ce88659cd2feb3a8f
GIT binary patch
literal 341
zcmZ8c%TB{E5L_osR1mKNzfdU`nj;(#BCTCiiP}|cO7SH^jj19vZ4^5PZu~QR0P6|~
ziY1SCX1$}G@bmQe<NQmn;O7v0@A29JLJ6P|39Jcd;tL%>8GsJK^gu^Yh9Hw3{&Xh@
z<7#VaxoTe<)7r~_!q7HViMoxj(Yd#)8=k~|vX3wls^Hm-xichkKBX)#W`aIFGU+Z*
z;_UfAb>4l#7%kXxE^<{cJ{EM!ADmxCwVl~J<pPbRTB<^f*h_*f_yv27G+pdAU2SYi
pGnJ*3Ez-Xs4v96+Rok^4Ht+kTZ|hyzZOomIZheY4I3jTnN8bmLO;!K^

literal 0
HcmV?d00001

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 0000000000000000000000000000000000000000..53be15a8052d6f8510f7a6ef3fb5d80f57a94006
GIT binary patch
literal 150
zcmZSn%*)l<^f@Y-0SXv_v;z<qvjB+{28Lh_kcgiKkYGR~itT}7`eFGwrMaoa`Yw(k
zj`}XHVfxOQd8xU<$wi3;sYR%q;)2YS)S_bj`1s7c%#!$cy@JXT4xkw}x%nxjIjMFa
Jn~H&$0RVRnA=3Z=

literal 0
HcmV?d00001

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 0000000000000000000000000000000000000000..7bc44dda0ae551b0fa026a2dfdfcb64b45fe91d2
GIT binary patch
literal 1144
zcmcIjO>fgc5S_J?v`Je&gv5nQB`z)!vBIGe5keG#xb=`g5Rs6zwKvIDj_vMDnpP^O
za^l8sg*(iwqtISBfs-B2ynQ=6^L8En*z2_OpOX~UPss0AJn(=`#(xDlz=WLu48W;^
zse&wouK?EopC*AYMp1*=_7^|L^nl%WPM@6H%#@iXJ*wDqn;jI-zvkh0;FJ^2$JQsB
zDVT(^l{k&{K9eR4>m6v1*UdQhSaJ_IH$GxyPE_^dc(qz}Q(KsYrnxy=n(oxa_~h^N
zzR0-utoOV-r$wFyOcx2HAE_9>v$^;NR|-zO7}p90pD*D{0JaHNfky*il$BvYSee5$
z+PHx>H)zYFyn?w~8+7{yx4l6-H@G`+I96x(;3I1_igvlGW87hz+4IL~S&%6Rw>h5o
z`h7ANL`@FJk~1ix&3pS;>7t&)4kK7D@o7!C!(sQtmaJ?ww+8ns@~I7`&Q@g00`D`$
zPMuzueqR&02wi&MSzf`BOFy{W=k1c7txFIQIl@R3B{3<YKSM6i>6DVGbx5?uGi#)#
z%0e{xl%yl>pyCP)30moyiTDlP;DEh&T;|J#!FX`={wN;29mj9v5{y#r#<<%7`m2cX
ztvl4MF1=cnc4)jbA_%C5D&$fBq81~*oFpk&g(M+iCds1Ambrvdoy^c(c66SXE0ZNz
zxzM&i&qdOXk|oPDl;iu;#lLN3$hkod-(QE8YN@tr2eq!!1fQwqhQ+NvOuyiNRpTXl
OQH%6aJ}wlq8~z3j<`7i?

literal 0
HcmV?d00001

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 0000000000000000000000000000000000000000..ca00c6ae0b2e8cb194058c8b16ab2e82e23edeaa
GIT binary patch
literal 929
zcmcIi!EVz)5S_Kt0EJ3$=^0fV90|O)B1H(b5F`$$NHGLqR9P!~LmWA_yEASQshrAR
z@mX+(nRNu^4y*Osnc4B%H?tdlKiL1a{gLLd8zHYJ{Nae9;HjVjNZAO$0xT8G6%-+S
z1-J(Im<E!OL<7z)fATn^2W-A6k?dtz*anl97x$ZA@$L)$@F4>erp(6ZX+A4RLpg}a
z(*aDANYv0>hDr!$p3o~>5Vd2i*Xwnhm$h9PTG)%u#&f3&n>XF1D_y*xRh0+)x6p_}
zQGst6Hm~7I!P1v^tzdHg6utyd25=Qfi7bJmOGeHJ;dmDv+=%YM@l0LZhYzeiiH6L1
zhL0GvHu_}Y?EF*S)MUyUqxkWWZ^hB*T*om_Jm5q#9vdPTN$!YlNu+QV(V{ePw^<l6
zPq1+`qJ56CYu~q3V~V~rdmP)eTsujHIilyW8*(P6K1Iq#Tg~Y<8_eG}HCmErRoXh@
z6+EC^ik>x9x3Z`wr|(Yn<kd{Sl;$S6Gp%)hJLvBf^^Kc}+bxNt);P4H7v)e;hbjyX
zRU}(pMwZoPWwXrJlx3@?=qhnVmF)O9l5v!EuEMEM{ZaZa<xZIyL>I~p4%INY6ZCx(
dAEoXsiP^tmpZ<T8_{KczTk%}pEDGEUe*p)1+h+g(

literal 0
HcmV?d00001

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