Add logging and url validations

.gitignore

@@ -0,0 +1,2 @@
+__pycache__
+gfonts.json

README.md

@@ -2,16 +2,22 @@
 
 A spider that's looking for german page with google fonts hosted on google.
 
-Also look for google analytics on a website.
+Based on: https://docs.scrapy.org/en/latest/intro/tutorial.html
+
+## Usage
+
+    scrapy crawl gfonts -O gfonts.json
+
+
+## TODO
+
+Start checking for google analytics for all eu websites.
+
+## IDEAS
+
+Make it into browserextension that would notify you.
 
 ## Checking website origin:
 
 https://ipinfo.io/
 
-## TODO
-
-Start checking for google analytics.
-
-## IDEAS
-
-Make it into browserextension that would notify you.

ger_gfonts/ger_gfonts/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 GerGfontsItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

ger_gfonts/ger_gfonts/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 GerGfontsSpiderMiddleware:
+    # 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 GerGfontsDownloaderMiddleware:
+    # 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)

ger_gfonts/ger_gfonts/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 GerGfontsPipeline:
+    def process_item(self, item, spider):
+        return item

ger_gfonts/ger_gfonts/settings.py

@@ -0,0 +1,88 @@
+# Scrapy settings for ger_gfonts 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 = 'ger_gfonts'
+
+SPIDER_MODULES = ['ger_gfonts.spiders']
+NEWSPIDER_MODULE = 'ger_gfonts.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'ger_gfonts (+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 = {
+#    'ger_gfonts.middlewares.GerGfontsSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'ger_gfonts.middlewares.GerGfontsDownloaderMiddleware': 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 = {
+#    'ger_gfonts.pipelines.GerGfontsPipeline': 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'

ger_gfonts/ger_gfonts/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.

ger_gfonts/ger_gfonts/spiders/gfonts_spider.py

@@ -0,0 +1,74 @@
+import scrapy
+import socket
+import re
+import json
+from urllib.request import urlopen
+from urllib.parse import urlparse
+
+class GFontsSpider(scrapy.Spider):
+    name = "gfonts"
+    #start_urls = self.getUrls()
+    checked_domains = []
+    custom_settings = {'CLOSESPIDER_PAGECOUNT': 2000}
+
+    def __init__(self):
+        self.start_urls = self.getUrls()
+
+    def parse(self, response):
+        # check current url - german or eu (todo)
+        # check if api.gfonts.com is found
+        # @todo: check if google analytics is found
+        parsed = urlparse(response.url)
+        self.checked_domains.append(parsed.hostname)
+        self.logNewDomain(response.url)
+        if self.isGerman(response.url):
+            self.findGFonts(response)
+            self.parseOn(response)
+
+    def getCountryOfUrl(self, url):
+        ip = socket.gethostbyname(url)
+        api_url = 'https://ipinfo.io/' + ip + '/json'
+        response = urlopen(api_url)
+        data = json.load(response)
+        return data['country']
+
+    def isCountryGerman(self, url):
+        return 'DE' == self.getCountryOfUrl(url)
+
+    def isGermanTLD(self, url):
+        parts = urlparse(url)
+        tld = parts.hostname[-3:]
+        return tld == '.de'
+
+    def isGerman(self, url):
+        if not self.isGermanTLD(url):
+            return self.isCountryGerman(url)
+        return True
+
+    def findGFonts(self, response):
+        for links in response.css('head links'):
+            if 'fonts.googleapis.com' in links.attrib['href']:
+                yield {
+                    'url': response.url,
+                    'gfonts': True,
+                }
+
+    def parseOn(self, response):
+        for links in response.css('a'):
+            url = links.attrib['href']
+            # parse valid urls
+            if validators.url(url) and bool(urlparse(url).netloc):
+                current = urlparse(response.url)
+                found = urlparse(url)
+                if current.hostname != found.hostname and found.hostname not in self.checked_domains:
+                    yield response.follow(url, callback=self.parse)
+
+    def getUrls(self):
+        with open('sites.txt') as sites_file:
+            sites = sites_file.readlines()
+            return map(lambda s: 'https://' + s,sites)
+
+    def logNewDomain(self, url):
+        print('############################################')
+        print('######   ' + url + '   #######')
+        print('############################################')

ger_gfonts/ger_gfonts/spiders/sites.txt

@@ -0,0 +1,106 @@
+porsche.com
+kenhub.com
+trademachines.com
+canyon.com
+pinterest.de
+buecher.de
+conrad.com
+bosch-home.com
+kaercher.com
+mobile.de
+deutschland.de
+google.de
+amazon.de
+einreiseanmeldung.de
+bmw.de
+daad.de
+volkswagen.de
+mtu.de
+aldi.com
+degruyter.com
+web.de
+uni-assist.de
+mercedes-benz.de
+embl.de
+denic.de
+bahn.de
+dedon.de
+giz.de
+berlin.de
+giz.de
+bundestag.de
+deutsche-rentenversicherung.de
+bild.de
+tum.de
+rewe.de
+commerzbank.de
+goethe.de
+spiegel.de
+pangaea.de
+tagesshau.de
+fussball.de
+adac.de
+boys-day.de
+audi.de
+lidl.de
+ndr.de
+visitberlin.de
+gesetze-im-internet.de
+dresden.de
+baden-wuttemberg.de
+hessen.de
+sparkasse.de
+museum-folkwang.de
+posteo.de
+wetter.de
+stern.de
+biontech.de
+mediamarkt.de
+rki.de
+deutsche-bank.de
+duden.de
+magro-aktuell.de
+notebooksbilliger.de
+idealo.de
+wg-gesucht.de
+bundesregierung.de
+ebay.de
+rlp.de
+taz.de
+antolin.westermann.de
+electricbrands.de
+suedzucker.de
+wetteronline.de
+kik.de
+wetterzentrale.de
+service.bund.de
+katholisch.de
+homboldt-foundation.de
+deginvest.de
+comdirect.de
+standaard.be
+jocobs-university.de
+naspa.de
+uni-bonn.de
+zalando.de
+ausbildung.de
+uni-hamburg.de
+auswaertiges-amt.de
+jab.de
+de.dwa.de
+mdc-berlin.de
+dlr.de
+rwth-aachen.de
+studip.uni-goettingen.de
+bzga.de
+gtai.de
+bunte.de
+decathlon.de
+denbi.de
+hannover.de
+ewe.de
+impfdashboard.de
+
+
+
+ 

ger_gfonts/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 = ger_gfonts.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = ger_gfonts

ger_gfonts/sites.txt

@@ -0,0 +1,106 @@
+porsche.com
+kenhub.com
+trademachines.com
+canyon.com
+pinterest.de
+buecher.de
+conrad.com
+bosch-home.com
+kaercher.com
+mobile.de
+deutschland.de
+google.de
+amazon.de
+einreiseanmeldung.de
+bmw.de
+daad.de
+volkswagen.de
+mtu.de
+aldi.com
+degruyter.com
+web.de
+uni-assist.de
+mercedes-benz.de
+embl.de
+denic.de
+bahn.de
+dedon.de
+giz.de
+berlin.de
+giz.de
+bundestag.de
+deutsche-rentenversicherung.de
+bild.de
+tum.de
+rewe.de
+commerzbank.de
+goethe.de
+spiegel.de
+pangaea.de
+tagesshau.de
+fussball.de
+adac.de
+boys-day.de
+audi.de
+lidl.de
+ndr.de
+visitberlin.de
+gesetze-im-internet.de
+dresden.de
+baden-wuttemberg.de
+hessen.de
+sparkasse.de
+museum-folkwang.de
+posteo.de
+wetter.de
+stern.de
+biontech.de
+mediamarkt.de
+rki.de
+deutsche-bank.de
+duden.de
+magro-aktuell.de
+notebooksbilliger.de
+idealo.de
+wg-gesucht.de
+bundesregierung.de
+ebay.de
+rlp.de
+taz.de
+antolin.westermann.de
+electricbrands.de
+suedzucker.de
+wetteronline.de
+kik.de
+wetterzentrale.de
+service.bund.de
+katholisch.de
+homboldt-foundation.de
+deginvest.de
+comdirect.de
+standaard.be
+jocobs-university.de
+naspa.de
+uni-bonn.de
+zalando.de
+ausbildung.de
+uni-hamburg.de
+auswaertiges-amt.de
+jab.de
+de.dwa.de
+mdc-berlin.de
+dlr.de
+rwth-aachen.de
+studip.uni-goettingen.de
+bzga.de
+gtai.de
+bunte.de
+decathlon.de
+denbi.de
+hannover.de
+ewe.de
+impfdashboard.de
+
+
+
+ 

ger_gfonts/spiders/gfonts_spider.py

@@ -7,16 +7,16 @@ from urllib.parse import urlparse
 
 class GFontsSpider(scrapy.Spider):
     name = "gfonts"
-    start_urls = get_urls()
+    start_urls = self.getUrls()
     custom_settings = {'CLOSESPIDER_PAGECOUNT': 2000}
 
     def parse(self, response):
         # check current url - german or eu (todo)
         # check if api.gfonts.com is found
         # todo: check if google analytics is found
-        if (isGerman(response.url)):
-            findGFonts(response)
-            parseOn(response)
+        if (self.isGerman(response.url)):
+            self.findGFonts(response)
+            self.parseOn(response)
 
     def getCountryOfUrl(url):
         ip = socket.gethostbyname(url)
@@ -26,7 +26,7 @@ class GFontsSpider(scrapy.Spider):
         return data['country']
 
     def isCountryGerman(url):
-        return 'DE' === getCountryOfUrl(url)
+        return 'DE' === self.getCountryOfUrl(url)
 
     def isGermanTLD(url):
         parts = urlparse(url)
@@ -34,8 +34,8 @@ class GFontsSpider(scrapy.Spider):
         return tld === '.de'
 
     def isGerman(url):
-        if (!isGermanTLD(url)):
-            return isCountryGerman(url)
+        if (!self.isGermanTLD(url)):
+            return self.isCountryGerman(url)
         return TRUE
 
     def findGFonts(response):
@@ -45,6 +45,7 @@ class GFontsSpider(scrapy.Spider):
                     'url': response.url,
                     'gfonts': TRUE,
                 }
+
     def parseOn(response):
         for links in response.css('a'):
             url = links.attrib['href']
@@ -53,3 +54,8 @@ class GFontsSpider(scrapy.Spider):
                 found = urlparse(url)
                 if (current.hostname != found.hostname):
                     yield response.follow(url, callback=self.parse)
+
+    def getUrls():
+        with open('../sites.txt') as sites_file:
+            sites = sites_file.readlines()
+            return sites

requirements.txt

@@ -1 +1,2 @@
 scrapy
+validators