update

fbcrawl/items.py

@@ -0,0 +1,34 @@
+# -*- 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
+from scrapy.loader.processors import TakeFirst, Join
+
+class FbcrawlItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    source = scrapy.Field()                     # page that published the post
+
+    date = scrapy.Field(
+            output_processor=TakeFirst()
+    )       
+                                    # when was the post published
+    text = scrapy.Field(
+            output_processor=Join(separator=u'')
+    )                       # full text of the post
+
+    comments = scrapy.Field(
+            output_processor=Join(separator=u'\n')
+    )                       # full text of the post
+    commentators = scrapy.Field(
+            output_processor=Join(separator=u'\n')
+    )                       # full text of the post
+
+    like = scrapy.Field()                       # num of likes
+    share = scrapy.Field()                      # num of shares
+    num_id = scrapy.Field()                     # progressive int associated to the entry in the final table, not present in the webpage
+    

fbcrawl/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 FbcrawlSpiderMiddleware(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 FbcrawlDownloaderMiddleware(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)

fbcrawl/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 FbcrawlPipeline(object):
+    def process_item(self, item, spider):
+        return item

fbcrawl/settings.py

@@ -0,0 +1,93 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for fbcrawl 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 = 'fbcrawl'
+
+SPIDER_MODULES = ['fbcrawl.spiders']
+NEWSPIDER_MODULE = 'fbcrawl.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'fbcrawl (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = False
+
+# 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 = {
+#    'fbcrawl.middlewares.FbcrawlSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'fbcrawl.middlewares.FbcrawlDownloaderMiddleware': 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 = {
+#    'fbcrawl.pipelines.FbcrawlPipeline': 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'
+FEED_EXPORT_FIELDS = ["source", "date", "text", "commentators","comments","like", "share"] # specifies the order of the column to export as CSV
+FEED_EXPORT_ENCODING = 'utf-8'
+DUPEFILTER_DEBUG = True

fbcrawl/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.

fbcrawl/spiders/fbcrawl.py

@@ -0,0 +1,134 @@
+import scrapy
+
+from datetime import datetime
+
+
+from scrapy.loader import ItemLoader
+from scrapy.http import FormRequest
+from fbcrawl.items import FbcrawlItem
+
+
+class FacebookSpider(scrapy.Spider):
+    """
+    Parse FB pages (needs credentials)
+    """    
+    name = "fb"
+
+    def __init__(self, email='', password='', til='2004-1-1', **kwargs):
+        super(FacebookSpider, self).__init__(**kwargs)
+
+        til = til.split(sep='-')
+        self.til = datetime(int(til[0]),int(til[1]),int(til[2]))
+        
+        self.email = email
+        self.password = password
+        self.start_urls = ['https://mbasic.facebook.com']    
+
+    def parse(self, response):
+        return FormRequest.from_response(
+                response,
+                formxpath='//form[contains(@action, "login")]',
+                formdata={'email': self.email,'pass': self.password},
+                callback=self.parse_home
+        )
+  
+    def parse_home(self, response):
+        '''Parse user news feed page'''
+        if response.css('#approvals_code'):
+            # Handle 'Approvals Code' checkpoint (ask user to enter code).
+            if not self.code:
+                # Show facebook messages via logs
+                # and request user for approval code.
+                message = response.css('._50f4::text').extract()[0]
+                self.log(message)
+                message = response.css('._3-8y._50f4').xpath('string()').extract()[0]
+                self.log(message)
+                self.code = input('Enter the code: ')
+            self.code = str(self.code)
+            if not (self.code and self.code.isdigit()):
+                self.log('Bad approvals code detected.')
+                return
+            return FormRequest.from_response(
+                response,
+                formdata={'approvals_code': self.code},
+                callback=self.parse_home,
+            )
+        elif response.xpath("//div/input[@value='Ok' and @type='submit']"):
+            # Handle 'Save Browser' checkpoint.
+            return FormRequest.from_response(
+                response,
+                formdata={'name_action_selected': 'dont_save'},
+                callback=self.parse_home,
+                dont_filter=True,
+            )
+        elif response.css('button#checkpointSubmitButton'):
+            # Handle `Someone tried to log into your account` warning.
+            return FormRequest.from_response(
+                response, callback=self.parse_home, dont_filter=True,)
+        # Else go to the user profile.
+        href = 'https://mbasic.facebook.com/ivacciniealtricomplottileggendari'
+        self.logger.info('Parse function called on %s', href)
+        return scrapy.Request(
+            url=href,
+            callback=self.parse_page,
+        )
+
+
+
+    def parse_page(self, response):
+#        from scrapy.utils.response import open_in_browser
+#        open_in_browser(response)
+        
+        for post in response.xpath("//div[contains(@id,'u_0_')]"):
+#            self.logger.info('Parse function called on %s', response.url)
+#            self.logger.info('Parsing page number %d', i)
+#            from scrapy.utils.response import open_in_browser
+#            open_in_browser(response)
+            post = post.xpath("//a[contains(text(),'Notizia completa')]/@href").extract()
+#   
+            for i in range(len(post)):
+                temp_post = response.urljoin(post[i])        
+                yield scrapy.Request(temp_post, self.parse_post,dont_filter = True)            
+
+#        next_page = response.xpath("//div/a[contains(text(),'Altri')]/@href")
+#        if len(next_page) > 0:
+#            next_page = response.urljoin(next_page[0].extract())
+#            yield scrapy.Request(next_page, callback=self.parse_page)
+#    
+#        else:
+#            next_page = response.xpath("//div/a[contains(text(),'2017')]/@href")
+#            if len(next_page) > 0:
+#                next_page = response.urljoin(next_page[0].extract())
+#                yield scrapy.Request(next_page, callback=self.parse_page)
+#                
+    def parse_post(self,response):
+        new = ItemLoader(item=FbcrawlItem(),response=response)
+#        from scrapy.utils.response import open_in_browser
+#        open_in_browser(response)
+#         #        ("//div[string-length(@id)=15 or string-length(@id)=16]")
+       # new.add_xpath('comments',"//div[string-length(@id)=15 or string-length(@id)=16]//div/text()")               
+# {}' .format(next_comment_page))
+        new.add_xpath('source', '//span/strong/a/text()')
+        new.add_xpath('date', '//div/div/abbr/text()')
+        new.add_xpath('text','//div[@data-ft]//p//text()')
+        
+        next_comment_page = response.xpath("//div/div[contains(@id,'see_next')]/a/@href")
+        while len(next_comment_page) > 0:
+            next_comment_page = response.urljoin(next_comment_page[0].extract())        
+            yield scrapy.Request(next_comment_page, callback=self.parse_comments, dont_filter = True, \
+                             meta={'new':new})
+#            self.logger.info('Parsing page number %d', i)
+
+#            from scrapy.utils.response import open_in_browser
+#            open_in_browser(response)0
+#            new.load_item()
+
+
+# 
+#        yield new.load_item()
+
+    def parse_comments(self,response):
+        self.logger.info('\n\n PAGINA COMMENTI  \n\n')
+        new = response.meta['new']    
+        new.add_xpath('commentators',"//div[number(@id)>1]/div/h3/a[@href]/text()")
+        yield new.load_item()