Add VulDB Spider (#23)

* Add OBS Vigilance Spider

* Add VulDB spider

Co-authored-by: karimhabush <37211852+karimhabush@users.noreply.github.com>

main.py

@@ -3,6 +3,7 @@
 from spiders.CISASpider import CisaSpider
 from spiders.CertFrSpider import CertFrSpider
 from spiders.DgssiSpider import DgssiSpider
+from spiders.VulDBSpider import VulDBSpider
 from spiders.ZDISpider import ZDISpider
 from scrapy.crawler import CrawlerProcess
 from datetime import datetime, timezone
@@ -12,7 +13,7 @@
 
 def main():
     now = datetime.now(timezone.utc).strftime("%d/%m/%Y %H:%M:%S")
-    item = f"""<div id="top"></div>\n\n## CyberOwl \n ![cyberowl](docs/images/logo.png)\n> Last Updated {now} UTC \n\nA daily updated summary of the most frequent types of security incidents currently being reported from different sources.\n\n--- \n\n### :kangaroo: Jump to \n | CyberOwl Sources | Description |\n|---|---|\n| [US-CERT](#us-cert-arrow_heading_up) | United States Computer Emergency and Readiness Team. |\n| [MA-CERT](#ma-cert-arrow_heading_up) | Moroccan Computer Emergency Response Team. |\n| [CERT-FR](#cert-fr-arrow_heading_up) | The French national government Computer Security Incident Response Team. |\n| [IBM X-Force Exchange](#ibmcloud-arrow_heading_up) | A cloud-based threat intelligence platform that allows to consume, share and act on threat intelligence. |\n| [ZeroDayInitiative](#zerodayinitiative-arrow_heading_up) | An international software vulnerability initiative that was started in 2005 by TippingPoint. |\n| [OBS Vigilance](#obs-vigilance-arrow_heading_up) |Vigilance is an initiative created by OBS (Orange Business Services) since 1999 to watch public vulnerabilities and then offer security fixes, a database and tools to remediate them. |\n\n> Suggest a source by opening an [issue](https://github.com/karimhabush/cyberowl/issues)! :raised_hands:\n\n"""
+    item = f"""<div id="top"></div>\n\n## CyberOwl \n ![cyberowl](docs/images/logo.png)\n> Last Updated {now} UTC \n\nA daily updated summary of the most frequent types of security incidents currently being reported from different sources.\n\n--- \n\n### :kangaroo: Jump to \n | CyberOwl Sources | Description |\n|---|---|\n| [US-CERT](#us-cert-arrow_heading_up) | United States Computer Emergency and Readiness Team. |\n| [MA-CERT](#ma-cert-arrow_heading_up) | Moroccan Computer Emergency Response Team. |\n| [CERT-FR](#cert-fr-arrow_heading_up) | The French national government Computer Security Incident Response Team. |\n| [IBM X-Force Exchange](#ibmcloud-arrow_heading_up) | A cloud-based threat intelligence platform that allows to consume, share and act on threat intelligence. |\n| [ZeroDayInitiative](#zerodayinitiative-arrow_heading_up) | An international software vulnerability initiative that was started in 2005 by TippingPoint. |\n| [OBS Vigilance](#obs-vigilance-arrow_heading_up) |Vigilance is an initiative created by OBS (Orange Business Services) since 1999 to watch public vulnerabilities and then offer security fixes, a database and tools to remediate them. |\n| [VulDB](#vuldb-arrow_heading_up) | Number one vulnerability database documenting and explaining security vulnerabilities, threats, and exploits since 1970. |\n\n> Suggest a source by opening an [issue](https://github.com/karimhabush/cyberowl/issues)! :raised_hands:\n\n"""
 
     with open("README.md", "w", encoding="utf-8") as f:
         f.write(item)
@@ -26,6 +27,7 @@ def main():
         process.crawl(IBMCloudSpider)
         process.crawl(ZDISpider)
         process.crawl(VigilanceSpider)
+        process.crawl(VulDBSpider)
         process.start()
 
     except Exception:

spiders/VulDBSpider.py

@@ -0,0 +1,43 @@
+from urllib import response
+import scrapy
+from mdtemplate import Template
+from datetime import date
+
+
+class VulDBSpider(scrapy.Spider):
+    name = 'VulDB'
+    start_urls = [
+        'https://vuldb.com/?live.recent'
+    ]
+    def parse(self, response):
+        if('cached' in response.flags):
+            return
+        num_bulletins=0
+        _data = []
+        print(response.css("table>tr").extract())
+        for bulletin in response.css("table>tr"):
+            if num_bulletins==0:
+                num_bulletins+=1
+                continue
+            LINK = "https://vuldb.com/"+bulletin.xpath("descendant-or-self::td[4]//@href").get()
+            DATE = str(date.today())+" at "+bulletin.xpath("descendant-or-self::td[1]//text()").get()
+            TITLE = bulletin.xpath("descendant-or-self::td[4]//text()").get().replace(
+                "\n", "").replace("\t", "").replace("\r", "").replace("  ", "").replace("|","-")
+            DESC = "Visit link for details"
+            ITEM = {
+                "_title": TITLE,
+                "_link": LINK,
+                "_date": DATE,
+                "_desc": DESC
+            }
+
+            _data.append(ITEM)
+            num_bulletins += 1
+            if num_bulletins >= 11:
+                break
+
+        _to_write = Template("VulDB", _data)
+
+        with open("README.md", "a", encoding="utf-8") as f:
+            f.write(_to_write._fill_table())
+            f.close()