From 9c176dcbe6b90577090c2fe1bff9e887c13fb648 Mon Sep 17 00:00:00 2001
From: Lio Novelli <liopold@drunomics.com>
Date: Wed, 2 Feb 2022 19:35:03 +0100
Subject: [PATCH] proper file structure

---
 .gitignore                                    |   2 +
 .../ger_gfonts/spiders/gfonts_spider.py       |  64 +++++++++++
 ger_gfonts/ger_gfonts/spiders/sites.txt       | 106 ++++++++++++++++++
 3 files changed, 172 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 ger_gfonts/ger_gfonts/spiders/gfonts_spider.py
 create mode 100644 ger_gfonts/ger_gfonts/spiders/sites.txt

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..2c5cee7
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,2 @@
+__pycache__
+gfonts.txt
diff --git a/ger_gfonts/ger_gfonts/spiders/gfonts_spider.py b/ger_gfonts/ger_gfonts/spiders/gfonts_spider.py
new file mode 100644
index 0000000..5dad952
--- /dev/null
+++ b/ger_gfonts/ger_gfonts/spiders/gfonts_spider.py
@@ -0,0 +1,64 @@
+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()
+    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
+        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']
+            if (bool(urlparse(url).netloc)):
+                current = urlparse(response.url)
+                found = urlparse(url)
+                if (current.hostname != found.hostname):
+                    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)
diff --git a/ger_gfonts/ger_gfonts/spiders/sites.txt b/ger_gfonts/ger_gfonts/spiders/sites.txt
new file mode 100644
index 0000000..e98e4f3
--- /dev/null
+++ b/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
+
+
+
+