Created
May 23, 2015 04:49
-
-
Save JFriel/0cb2a1954c8b8ff4a360 to your computer and use it in GitHub Desktop.
wiki scraper
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
import urllib | |
from bs4 import BeautifulSoup | |
import sys | |
import nltk | |
from nltk import word_tokenize | |
def splitParagraphIntoSentences(paragraph): | |
''' break a paragraph into sentences | |
and return a list ''' | |
import re | |
# to split by multile characters | |
# regular expressions are easiest (and fastest) | |
sentenceEnders = re.compile('[.!?]') | |
sentenceList = sentenceEnders.split(paragraph) | |
return sentenceList | |
url = "https://en.wikipedia.org/wiki/Special:Random" | |
html = urllib.urlopen(url).read() | |
soup = BeautifulSoup(html) | |
# 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) | |
#Up to here it just give a pure scrape, stored in 'text' | |
title = [] | |
for i in range(0,50): | |
if(text[i] != '-'): | |
title.append(text[i]) | |
else: | |
break | |
fulltitle = ''.join(title).encode('utf-8') | |
print fulltitle | |
tokenisedWiki = splitParagraphIntoSentences(text) | |
if(tokenisedWiki[1] == " Please improve this article by introducing more precise citations" or tokenisedWiki[1] == " Please help to improve the section, or discuss the issue on the talk page"): | |
print tokenisedWiki[2] | |
else: | |
print tokenisedWiki[1] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment