|
1 | 1 | importrequests |
2 | 2 | importre |
3 | 3 |
|
4 | | -#get url |
5 | | -#url=input('Enter a URL (include 'http://'):')--this is wrong |
| 4 | +# get url |
6 | 5 | url=input('Enter a URL (include `http://`): ') |
7 | 6 |
|
| 7 | +# connect to the url |
| 8 | +website=requests.get(url) |
8 | 9 |
|
9 | | -#connect to the url |
10 | | -website=requests.get(url) |
| 10 | +# read html |
| 11 | +html=website.text |
11 | 12 |
|
12 | | -#read html |
13 | | -html=website.text |
14 | | - |
15 | | - |
16 | | -#use re.findall to grab all the links |
| 13 | +# use re.findall to grab all the links |
17 | 14 | links=re.findall('"((http|ftp)s?://.*?)"',html) |
| 15 | +emails=re.findall('([\w\.,]+@[\w\.,]+\.\w+)',html) |
18 | 16 |
|
19 | | -emails=re.findall('([\w\.,]+@[\w\.,]+\.\w+)',html) |
20 | 17 |
|
21 | | - |
22 | | -#prints the number of links in the list |
| 18 | +# print the number of links in the list |
23 | 19 | print("\nFound {} links".format(len(links))) |
24 | | - |
25 | 20 | foremailinemails: |
26 | | -print(email) |
| 21 | +print(email) |