ΘΕΜΑ: εξαγωγή links από ιστοσελίδα

import re
import urllib.request
page = urllib.request.urlopen('https://en.wikipedia.org/wiki/Main_Page')
text = page.read().decode('utf-8')
page.close()
restr=r'(([http://])\S+(\.([a-zA-Z]|[\?-&%=]+))'
rexp = re.compile(restr,re.DOTALL|re.IGNORECASE)
import urllib.parse
a = 'https://en.wikipedia.org/wiki'
b = '/Science_fiction_film'
urllib.parse.urljoin(a,b)
c = '/Deadline_(magazine)'
urllib.parse.urljoin(a,c) 
d = '/Supersoldier'
urllib.parse.urljoin(a,d)

restr=r'(([http://])\S+(\.([a-zA-Z]|[\?-&%=]+))'
restr=r'(([http://])\S+(\.([a-zA-Z]|[\?\-&%=]+)))'

>>> import re
>>> text = open('Έγγραφα/Python_Forum/wiki.txt').read()
>>> pat = r'<a\s*href=[\'"]?([^\'" >]+)'
>>> urls = re.findall(pat, text, re.DOTALL|re.IGNORECASE)
>>> for url in urls[:5]:
	print(url)
 
 
#mw-head
#p-/wiki/Wikipedia
/wiki/Free_content
/wiki/Encyclope