You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
57 lines
1.2 KiB
Python
57 lines
1.2 KiB
Python
from jinja2 import Template
|
|
from markdown import markdown
|
|
import sys
|
|
|
|
# appending a path
|
|
sys.path.append('../')
|
|
|
|
# importing customised module
|
|
import summa.edits
|
|
from summa.edits import scored_sentences, similarity_graph
|
|
|
|
import wikipage
|
|
from wikipage.page import get_wikipage
|
|
|
|
wikipedia_page = "mushroom"
|
|
|
|
# main
|
|
# ------------------------------------------------------------------------
|
|
|
|
if __name__ == '__main__':
|
|
|
|
# --- WIKI REQUEST ---
|
|
|
|
# get text from wikipedia
|
|
print('--- WIKI ---')
|
|
page = get_wikipage(wikipedia_page)
|
|
if not page:
|
|
sys.exit("--- STOP ---")
|
|
title = '<h1>'+page.title+'</h1>'
|
|
text = page.content
|
|
|
|
# print text in terminal
|
|
print('--- TXT ---')
|
|
print(text)
|
|
|
|
# --- APPLY TEXTRANK ---
|
|
|
|
# apply textrank
|
|
graph = similarity_graph(text)
|
|
|
|
# print ranked sentences in terminal
|
|
print('--- GRAPH ---')
|
|
|
|
|
|
# for i in len(graph.nodes()):
|
|
# for j in len(graph.nodes()):
|
|
|
|
# s1 = graph.nodes()[i]
|
|
# s2 = graph.nodes()[j]
|
|
# weight = graph.edge_weight((i, j))
|
|
|
|
# print('---')
|
|
# print('1. ' + s1)
|
|
# print('2. ' + s1)
|
|
# print('similarity: ' + weight)
|
|
|