FilesExpand file tree

master

/

08_basic_email_web_crawler.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

21 lines (15 loc) · 439 Bytes

master

/

08_basic_email_web_crawler.py

Copy path

Top

File metadata and controls

• Code
• Blame

21 lines (15 loc) · 439 Bytes

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

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)