python-scripts/scripts/Email Extractor/email_extractor.py

# -*- coding: utf-8 -*-
"""Untitled0.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1BuQhjlIL_OYu39gpE2NQNZx9KJ_kPy3o
"""

import requests
from bs4 import BeautifulSoup
import urllib.request
from email_scraper import scrape_emails
import pandas as pd
from google.colab import files
 

urlid = input("Enter Website url (i.e.: example.com): ")
url = "https://"+urlid+"/"
reqs = requests.get(url)
soup = BeautifulSoup(reqs.text, 'html.parser')
 
urls = []
response = []
email = []
for link in soup.find_all('a'):
    urls.append(link.get('href'))
for i in range(len(urls)):
  if(urls[i].startswith("https://")):
    fp = urllib.request.urlopen(url+urls[i])
    mybytes = fp.read()
    mystr = mybytes.decode("utf8")
    fp.close()
    response.append(scrape_emails(mystr))
  else:
    fp = urllib.request.urlopen(url+urls[i])
    mybytes = fp.read()
    mystr = mybytes.decode("utf8")
    fp.close()
    response.append(scrape_emails(mystr))

for r in range(len(response)):
  if not response[r]:
    continue
  else:
    email.append(response[r])

df = pd.DataFrame(email, columns=["Email"])
df.to_csv('email.csv', index=False)

files.download("email.csv")

urllib.request.urlopen('https://www.youracclaim.com/badges/42b5d2d4-7c14-4c1a-b78a-adb3ac04105b/public_url').read().decode("utf-8")



import urllib.request

fp = urllib.request.urlopen("http://royninja.github.io/contact.html")
mybytes = fp.read()

mystr = mybytes.decode("utf8")
fp.close()

print(mystr)



import urllib.request

fp = urllib.request.urlopen("http://royninja.github.io/contact.html")
mybytes = fp.read()

mystr = mybytes.decode("utf8")
fp.close()

print(mystr)

webUrl = urllib.request.urlopen("https://royninja.github.io")

pip install email-scraper



scrape_emails(mystr)





import requests
from bs4 import BeautifulSoup
 
 
url = 'https://royninja.github.io/'
reqs = requests.get(url)
soup = BeautifulSoup(reqs.text, 'html.parser')
 
urls = []
for link in soup.find_all('a'):
    urls.append(link.get('href'))

urls[1]

url+urls[1]

BufautifulSoup(requests.get(url+urls[1]).text,'html.parser')

url2