import re

import urllib

from bs4 import BeautifulSoup

url = "http://journals.plos.org/plosone/article?id=info%3Adoi/10.1371/journal.pone.0162069"

response = urllib.urlopen(url)

page = response.read()

soup = BeautifulSoup(page, "lxml")

# kill all script and style elements

for script in soup(["script", "style"]):

   script.extract()    # rip it out

# get text

text = soup.get_text()

# break into lines and remove leading and trailing space on each

#lines = (line.strip() for line in text.splitlines())

# break multi-headlines into a line each

#chunks = (phrase.strip() for line in lines for phrase in line.split("  "))

# drop blank lines

#text = 'n'.join(chunk for chunk in chunks if chunk)

#print(text)

#print type(soup)

#print soup.prettify()

#You can change the regex if it doesn't work properly.

pattern = re.compile(r"(?<=s).{0,2}w*([A-Z]{2}|([A-Z]w[A-Z]))w*.{0,2}(?=s)")

result_list1 = pattern.findall(text)

#Delete repeated elements.

result_set = set(result_list1)

result_list2 = list(result_set)

#结果暂时不理想。熟练掌握bs4以后再修改

print result_list2