Version 3.0

ApplSec.py

@@ -1,61 +1,71 @@
 import re
 import requests
-import httplib2
 from datetime import date
 from bs4 import BeautifulSoup, SoupStrainer
 
-
 updatesPage = requests.get("https://support.apple.com/en-us/HT201222").text
-# currentDate = str(date.today().day) + " " + str(date.today().strftime("%B")[0:3]) + " " + str(date.today().year)
-currentDate = str(1) + " " + "Feb" + " " + str(date.today().year)
-
-
-# checks if there was a new version added today or not
-if currentDate in updatesPage:
-    wasUpdated = True
-else:
-    wasUpdated = False
-
-
-if (wasUpdated == True):
-    # if there was an update scrape all the links
-    allLinks = []
-    http = httplib2.Http()
-    status, response = http.request("https://support.apple.com/en-us/HT201222")
+currentDateFormatOne = str(date.today().day) + " " + str(date.today().strftime("%B")[0:3]) + " " + str(date.today().year)
+currentDateFormatTwo = str(date.today().strftime("%B")) + " " + str(date.today().day) + ", " + str(date.today().year)
 
-    for link in BeautifulSoup(response, features="html.parser", parse_only=SoupStrainer("a")):
-        if link.has_attr("href"):
-            allLinks.append(link["href"])
 
-    # get only the new links
-    searchResults = len(re.findall(currentDate, updatesPage)) + 22
-    newLinks = allLinks[22:searchResults]
+newHeader = []
+numberCVE = []
 
-    # scrape new links and gather info from the links
-    newHeader = []
-    numberCVE = []
+def getData(link):
+    for x in link:
+        newPage = requests.get(x)
+        soup = BeautifulSoup(newPage.content, "html.parser")
 
-    for x in newLinks:
-        newLink = requests.get(x)
-        soup = BeautifulSoup(newLink.content, "html.parser")
-
-        # get the header of the new version
+        # get the title of the new version
         allHeaders = soup.find_all("h2")
         newHeader.append(re.sub("<[^>]*?>","", str(allHeaders[1])))
 
-        # search how many CVEs there are
+        # get the number of CVEs on the page
         numberCVE.append(len(re.findall("CVE", str(soup))) - 1)
 
     for x in newHeader:
-        # if there is macOS in the header take only the first part, not the full header
+        # if there is macOS in the header take only the first part, not the full title
         if "macOS" in x:
             macosIsHere = newHeader.index(x)
             newHeader[macosIsHere] = x.split(",", 1)[0]
 
+
+allLinks = []
+for link in BeautifulSoup(updatesPage, features="html.parser", parse_only=SoupStrainer("a")):
+    # get all the links from the page
+    if link.has_attr("href"):
+        allLinks.append(link["href"])
+
+
+if currentDateFormatOne in updatesPage:
+    # get only the new links from the page
+    newLinks = allLinks[22:len(re.findall(currentDateFormatOne, updatesPage)) + 22]
+    getData(newLinks)
+
     # print results
-    results = "PATCH TIME!\n"
+    results = "RELEASED TODAY:\n"
     for x in newHeader:
         results += x + " released with " + str(numberCVE[0]) + " security fixes\n"
         numberCVE.pop(0)
+    print(results)
+
+
+updatedLinks = []
+for x in allLinks[22:42]:
+    # check if the last 20 update pages got any changes today
+    page = requests.get(x).text
+    search = "Entry added " + str(currentDateFormatTwo)
+
+    if search in page:
+        updatedLinks.append(x)
 
+if updatedLinks != []:
+    newHeader.clear()
+    getData(updatedLinks)
+
+    # print results
+    results = "UPDATED TODAY:\n"
+    for x in newHeader:
+        results += x + " was released " + str(numberCVE[0]) + " security fixes\n"
+        numberCVE.pop(0)
     print(results)