mirror of
https://github.com/RussellChamp/tilde-projects.git
synced 2026-10-28 00:22:34 +00:00
51 lines
2.2 KiB
Python
51 lines
2.2 KiB
Python
import urllib
|
|
from bs4 import BeautifulSoup
|
|
import random
|
|
|
|
def get_philosophy(word, max_steps=20):
|
|
step_words = [word]
|
|
steps = 0
|
|
|
|
url = 'https://en.wikipedia.org/wiki/%s' % word
|
|
while steps < max_steps:
|
|
soup = BeautifulSoup(urllib.urlopen(url).read(), 'html.parser')
|
|
title = soup.find('h1', id='firstHeading')
|
|
content = soup.find('div', id='mw-content-text')
|
|
if not content:
|
|
break
|
|
item = [item for item in content.find_all('a') if not item.get('class') and not item.get('target') and item.get('title') and not 'Wikipedia:' in item.get('title') and not 'Category:' in item.get('title') and not 'Help:' in item.get('title') and not 'Portal:' in item.get('title') and not 'Special:' in item.get('title') and not 'Talk:' in item.get('title') and not 'Template:' in item.get('title') and not 'File:' in item.get('title') and 'Edit section:' not in item.get('title') and 'Commons:' not in item.get('title') and not item.get('title') in step_words][0]
|
|
step_words.append(item.get('title'))
|
|
#print item.get('title') + "\n"
|
|
url = 'https://en.wikipedia.org%s' % item.get('href')
|
|
steps += 1
|
|
return step_words
|
|
|
|
def containsAny(str, set):
|
|
return 1 in [c in str for c in set]
|
|
|
|
def get_philosophy_lower(word, max_steps=20):
|
|
step_words = [word]
|
|
steps = 0
|
|
|
|
url = 'https://en.wikipedia.org/wiki/%s' % word
|
|
while steps < max_steps:
|
|
soup = BeautifulSoup(urllib.urlopen(url).read(), 'html.parser')
|
|
title = soup.find('h1', id='firstHeading')
|
|
content = soup.find('div', id='mw-content-text')
|
|
if not content:
|
|
break
|
|
links = [item for item in content.find_all('a') if not item.get('class') and item.text and item.text[0].islower() and not containsAny(item.text, ':()') and item.get('title') and not containsAny(item.get('title'), ':()') and not item.get('title') in step_words]
|
|
if not links:
|
|
step_words.append("(dead end)")
|
|
break
|
|
item = links[0] #grab the first good link item
|
|
#print "Checking %s %s" % (item.get('title'), item.text)
|
|
step_words.append(item.get('title'))
|
|
if item.get('title') == 'Philosophy':
|
|
break
|
|
#print item.get('title') + "\n"
|
|
url = 'https://en.wikipedia.org%s' % item.get('href')
|
|
steps += 1
|
|
return step_words
|
|
|