ΘΕΜΑ: Διάβασμα δεδομένων από web page.

#!/usr/bin/env python3
#-*-coding: utf-8-*-
 
import urllib.request
import re
 
 
motivo = "<li class=\"klatest-subject\">\s*.*>([\w+\s*\.?]+)</a></li>"
 
f = urllib.request.urlopen('http://python.org.gr/')
 
content = str(f.read().decode())
 
vrethikan = re.findall(motivo, content)
 
print(vrethikan)

motivo = "<li class=\"klatest-subject\">\s*.*>([\w+\s*\.?]+)</a></li>"

vrethikan = re.findall(motivo, content)

content = str(f.read().decode())

content = str(f.read().decode())

vrethikan = re.findall(motivo, content)

<li class=\"klatest-subject\">\s*.*>

([\w+\s*\.?]+)

vrethikan = re.findall(motivo, content)

content = str(f.read().decode('windows-1253'))

content = str(content.read().decode('iso-8859-7'))

"<li class=\"klatest-subject\">\s*.*>([\w+\s*\.?]+)</a></li>"

([\w+\s*\.?]+)

\s*.*

motivo = "<td.*><a.*>([\w+\s*]+)</a></td"
re.findall(motivo, selida)

motivo = "<td.*><a.*>([\w+\s*]+)</a></td"

motivo = "<td.*>.*<a.*>([\w+\s*]+)</a></td"

motivo = "<center><table\s+border=\'0\'\s+cellpadding=\'0\'\s+cellspacing=\'0\'\s+width=\'100%\'>\s+<tr><td\s+bgColor=#.*\">([\w+\s*]+)</a></td>"

motivo = "<td.*>.*<a.*>(.*)</a></td"

links_motivo = "<td.*><IMG.*><a\s*href=\"(.*)\">"

links_motivo = "<td.*><IMG.*><a\s*href=\"([.*]+)\">"

 
from bs4 import BeautifulSoup
import urllib2
 
page = urllib2.urlopen('http://www.selida.com')
html = BeautifulSoup(page)
table = html.find('table')
links = table.find_all('a')
print links

 
for link in table.find_all('a', href=True):
   print link['href']