Create emails_from_url.py

web_programming/emails_from_url.py

@@ -0,0 +1,87 @@
+"""Get the site emails from URL."""
+__author__ = "Muhammad Umer Farooq"
+__license__ = "MIT"
+__version__ = "1.0.0"
+__maintainer__ = "Muhammad Umer Farooq"
+__email__ = "[email protected]"
+__status__ = "Production"
+
+import re
+import requests
+from urllib import parse
+from html.parser import HTMLParser
+
+
+class Parser(HTMLParser):
+    ''' class use to parse HTML
+         handle_starttag  function takes url from
+         anchor tag
+    '''
+    def __init__(self, domain):
+        HTMLParser.__init__(self)
+        self.data = []
+        self.domain = domain
+
+    def handle_starttag(self, tag, attrs):
+        # Only parse the 'anchor' tag.
+        if tag == "a":
+            # Check the list of defined attributes.
+            for name, value in attrs:
+                # If href is defined, and not empty nor # print it.
+                if name == "href" and value != "#" and value != '':
+                    # If not already in data.
+                    if value not in self.data:
+                        url = parse.urljoin(self.domain, value)
+                        self.data.append(url)
+
+
+# Get main domain name (example.com)
+def get_domain_name(url):
+    return '.'.join(get_sub_domain_name(url).split('.')[-2:])
+
+
+# Get sub domain name (sub.example.com)
+def get_sub_domain_name(url):
+        return parse.urlparse(url).netloc
+
+if __name__ == '__main__':
+    # Get the url
+    url = "https://github.com"
+    # Get the base domain from the url
+    domain = get_domain_name(url)
+
+    # Initialize the parser
+    parser = Parser(domain)
+
+    # Validate Email regx.
+    emailRegx = '[a-zA-Z0-9]+@' + domain
+
+    # Open URL
+    r = requests.get(url)
+
+    # pass the raw HTML to the parser to get links
+    parser.feed(r.text)
+
+    # Store Email Data structure.
+    Emails = []
+    # Get links and loop through
+    for link in parser.data:
+        # open URL.
+        # read = requests.get(link)
+        read = requests.get(link)
+        # Get the valid email.
+        email = re.findall(emailRegx, read.text)
+        # If not in list then append it.
+        if email not in Emails:
+            Emails.append(email)
+
+    ValidEmails = []
+
+    # Remove duplicates email address.
+    for Email in Emails:
+        for e in Email:
+            if e not in ValidEmails:
+                ValidEmails.append(e)
+
+    # Finally print list of email.
+    print(ValidEmails)