Created
May 7, 2017 16:08
-
-
Save mrecachinas/a45cc590dce1e3a7e08978aac06f832e to your computer and use it in GitHub Desktop.
The drinking game involving Wikipedia
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/env python | |
| from __future__ import print_function | |
| import urllib2 | |
| import httplib | |
| from bs4 import BeautifulSoup, SoupStrainer | |
| import string | |
| import time | |
| def get_wiki(link): | |
| try: | |
| response = urllib2.urlopen(link) | |
| return response | |
| except urllib2.URLError as e: | |
| pass | |
| except urllib2.HTTPError as e: | |
| pass | |
| except httplib.HTTPException as e: | |
| pass | |
| except Exception: | |
| import traceback | |
| print(traceback.format_exc()) | |
| def get_random_wiki(): | |
| random_link = "https://en.wikipedia.org/wiki/Special:Random" | |
| return get_wiki(random_link) | |
| def first_lowercase_link(wiki): | |
| content = BeautifulSoup(wiki).find_all(id='mw-content-text') | |
| print(content) | |
| content = content[0] | |
| prefix = "https://en.wikipedia.org" | |
| for para in content.find_all('p'): | |
| for link in para.find_all('a', href=True): | |
| if link.text and link.text[0] in string.ascii_lowercase: | |
| return (urllib2.urlparse.urljoin(prefix, link["href"]), link.text) | |
| def links_to_topic(wiki, topic=""): | |
| links = [] | |
| link = first_lowercase_link(wiki) | |
| while link and link[1].lower() != topic: | |
| links.append(link) | |
| next_wiki = get_wiki(link[0]) | |
| link = first_lowercase_link(next_wiki) | |
| if link: | |
| links.append(link) | |
| return links | |
| def test(): | |
| MAX_ITER = 10 | |
| links = {} | |
| for n in xrange(MAX_ITER): | |
| random_wiki = get_random_wiki() | |
| random_wiki_title = BeautifulSoup(random_wiki.read()).find(id="firstHeading").text | |
| links[random_wiki_title] = links_to_topic(random_wiki, topic="philosophy") | |
| print(links) | |
| if __name__ == '__main__': | |
| test() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment