Basic example of using NLTK for name entity extraction.

example1.py

# forked for my own reference
import urllib.request
import urllib.parse

from bs4 import BeautifulSoup as bs
import nltk

def extract_named_ents_from_url(url):
    url_bytes = get_bytes_for_url(url)
    soup = bs(url_bytes, "lxml")
    sentences = nltk.sent_tokenize(soup.text)
    tokenized_sentences = [nltk.word_tokenize(sentence) for sentence in sentences]
    tagged_sentences = [nltk.pos_tag(sentence) for sentence in tokenized_sentences]
    chunked_sentences = nltk.ne_chunk_sents(tagged_sentences, binary=True)
    named_entities = []
    for chunked_sentence in chunked_sentences:
        return entity_names_for_tree(chunked_sentence)
    return named_entities

def get_bytes_for_url(url):
    user_agent = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.47 Safari/537.36'
    req = urllib.request.Request(url, headers={'User-Agent': user_agent})
    httpResponse = urllib.request.urlopen(req)
    return httpResponse.read()  # todo encoding?

def entity_names_for_tree(t):
    entity_names = []
    if hasattr(t, 'label') and t.label:
        if t.label() == 'NE':
            entity_names.append(' '.join([child[0] for child in t]))
        else:
            for child in t:
                entity_names.extend(entity_names_for_tree(child))
    return entity_names

named_entities = extract_named_ents_from_url('http://www.omdurman.org/columns/obama12.html')
print(named_entities)

# ['Widespread Consensus', 'Obama Promotes', 'Racism', 'Hatred', 'Israel', 'Western Civilization Home', 'Obama', 'Racism', 'Hatred', 'Israel', 'Richard Cohen', 'Brigitte Gabriel', 'Sharon Hughes', 'Charles Krauthammer', 'Kenneth Blackwell', 'Naomi Ragen', 'Debbie Schlussel', 'Ed Lasky', 'William Levinson', 'Barack', 'Catholics', 'Israel', 'United States']