First blood

Author: Thepnathi

README.md

@@ -0,0 +1,29 @@
+import requests
+
+class check_link():
+    def __init__(self): 
+        # generates bad responses from 400 to 409 and from 501 to 503
+        self.bad_resp = list(range(400, 409)) + list(range(501, 504))
+        self.badLinks = {}
+    
+    def __str__(self):
+        # if this object is printed, print the dictionary
+        return self.badLinks
+
+    def check(self, address):   
+        # method will check a link in an address
+        # this method should be called with different addresses eachtime
+        try:
+            req = requests.get(address)
+            resp = req.status_code
+            if resp == 200:
+                return True
+            else:
+                # it's possible to get HTTP 999: access denied
+                # which isn't an error
+                if resp in self.bad_resp:
+                    self.badLinks.update({resp : address})
+                    return resp
+        except Exception as e:
+            print ("{}{}".format(e, address))
+            pass

check_link.py

@@ -0,0 +1,42 @@
+# Deploy bot for Python
+# TODO
+# [X] check all links on page for 404
+# check all images to see if they have an alt text
+# compress html
+# compress javascript
+# compress css
+
+import check_link
+from bs4 import BeautifulSoup
+import urllib.request
+from multiprocessing import Process
+
+# creates a global check_link object
+check_link_obj = check_link.check_link()
+
+def get_all_links(address):
+    # get all links on a website, return a set
+    resp = urllib.request.urlopen(address)
+    soup = BeautifulSoup(resp, 'html.parser')
+    links = soup.find_all('a')
+    return {link.get('href') for link in links
+                if link.get('href') and link.get('href')[0:4]=='http'}
+
+def threader(website):
+    # this function is used to create new threads
+    response = check_link_obj.check(website)
+    if response != True:
+        print("HTTP " + str(response) + " " +  website)
+
+def main():
+    # creates new threads of threader, starts them then joins them together
+    website = input("What is the address of the website? ")
+    all_links = get_all_links(website)
+    for i in all_links:
+        try:
+            Process(target = threader, args = (i, )).start()
+        except Exception as e:
+            pass
+
+if __name__=="__main__":
+    main()