commit ca57f9b604317b3e056b40276b70c98a7df61860 Author: gamerdonkey Date: Tue Jun 7 21:43:51 2022 -0500 Initial commit. diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..bdaab25 --- /dev/null +++ b/.gitignore @@ -0,0 +1 @@ +env/ diff --git a/test.py b/test.py new file mode 100644 index 0000000..2e1923e --- /dev/null +++ b/test.py @@ -0,0 +1,29 @@ +import json +import requests +import wikipediaapi + +from nltk import pos_tag, map_tag +from nltk import word_tokenize + + +def get_random_wikipedia_title(): + random_result = json.loads(requests.get('https://en.wikipedia.org/api/rest_v1/page/random/title').text) + return random_result['items'][0]['title'] + +data = "The quick brown fox jumps over the lazy dog." + +data_pos_tagged = pos_tag(word_tokenize(data)) + +for tagged_word in data_pos_tagged: + print(tagged_word) + +wikipedia = wikipediaapi.Wikipedia('en') +random_page = wikipedia.page(get_random_wikipedia_title()) + +print(random_page.title) + +random_page_summary_tagged = pos_tag(word_tokenize(random_page.summary)) +simple_tags = [(word, map_tag('en-ptb', 'universal', tag)) for word, tag in random_page_summary_tagged] + +print(random_page_summary_tagged) +print(simple_tags)