python-scripts/08_basic_email_web_crawler.py
2016-02-18 15:08:55 -07:00

22 lines
439 B
Python

import requests
import re
# get url
url = input('Enter a URL (include `http://`): ')
# connect to the url
website = requests.get(url)
# read html
html = website.text
# use re.findall to grab all the links
links = re.findall('"((http|ftp)s?://.*?)"', html)
emails = re.findall('([\w\.,]+@[\w\.,]+\.\w+)', html)
# print the number of links in the list
print("\nFound {} links".format(len(links)))
for email in emails:
print(email)