Created
October 8, 2010 17:38
-
-
Save rafapolo/617179 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/python | |
# -*- coding: UTF-8 -*- | |
# author: rafael polo | |
WIKI_PAGE = 'http://pt.wikipedia.org/w/index.php?title=Fisica&printable=yes' | |
print "============" | |
print "Carregando libs..." | |
import urllib2, re, htmlentitydefs | |
try: | |
import matplotlib.pyplot as plt | |
except: | |
raise | |
import networkx as nx | |
# pega html da url | |
def get_page(url): | |
opener = urllib2.build_opener() | |
opener.addheaders = [('User-agent', 'Mozilla/5.0')] | |
print "Carregando " + url | |
infile = opener.open(url) | |
return infile.read() | |
def get_first_paragraph(page): | |
# encontra tudo que estver entre <p>*</p> | |
ps = re.findall(r'<p>\s*(.+?)\s*</p>', page) | |
print "Encontrados %s parágrafos." % len(ps) | |
return decode_htmlentities(remove_html_tags(ps[0].decode("utf-8").lower())) #primeiro | |
def remove_html_tags(txt): | |
# retira tags html | |
p = re.compile(r'<[^<]*?/?>') | |
return p.sub('', txt) | |
# decodifica tag html para string | |
def substitute_entity(match): | |
ent = match.group(3) | |
if match.group(1) == "#": | |
if match.group(2) == '': | |
return unichr(int(ent)) | |
elif match.group(2) == 'x': | |
return unichr(int('0x'+ent, 16)) | |
else: | |
cp = n2cp.get(ent) | |
if cp: | |
return unichr(cp) | |
else: | |
return match.group() | |
def decode_htmlentities(string): | |
entity_re = re.compile(r'&(#?)(x?)(\d{1,5}|\w{1,8});') | |
return entity_re.subn(substitute_entity, string)[0] | |
page = get_page(WIKI_PAGE) | |
p = get_first_paragraph(page) | |
# Retira espaços extras, pontos e vírgulas. | |
pattern = re.compile(r'\s+') | |
limpo = pattern.sub(' ', p) | |
limpo = limpo.replace(',', '') | |
limpo = limpo.replace(';', '') | |
limpo = limpo.replace('.', '') | |
# Separa palavras | |
palavras = limpo.split(" ") | |
count = len(palavras) | |
print "%s palavras." % count | |
print "Gerando Grafo..." | |
G=nx.Graph() | |
palavra_anterior = "" | |
for palavra in palavras: | |
if (palavra != ""): | |
if (G.has_node(palavra)): | |
peso = G.node[palavra]['peso'] | |
peso += 1 | |
size = peso*200 | |
G.add_node(palavra, peso=peso, size=size) | |
else: | |
G.add_node(palavra, peso=1, size=200) | |
if (palavra_anterior != ""): | |
G.add_edge(palavra_anterior, palavra) | |
palavra_anterior = palavra | |
print "Renderizando..." | |
nx.draw(G, node_size=[G.node[n]['size'] for n in G.nodes()]) | |
print "Ok" | |
print "============" | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment