Spaces:
Running
Running
| from selenium import webdriver | |
| from selenium.webdriver.common.by import By | |
| from selenium.webdriver.common.keys import Keys | |
| from bs4 import BeautifulSoup | |
| import time | |
| # !pip install tensorflow tensorflow-hub | |
| import tensorflow as tf | |
| import tensorflow_hub as hub | |
| import numpy as np | |
| # !pip install jellyfish | |
| import jellyfish | |
| # Load the pre-trained Universal Sentence Encoder | |
| embed = hub.load("https://tfhub.dev/google/universal-sentence-encoder/4") | |
| def calculate_jaro_similarity(str1, str2): | |
| jaro_similarity = jellyfish.jaro_distance(str1, str2) | |
| return jaro_similarity | |
| def most_similar_sentence(target_topic, labels_list): | |
| # Encode the context sentence and all sentences in the list | |
| context_embedding = embed([target_topic])[0] | |
| sentence_embeddings = embed(labels_list) | |
| # Calculate cosine similarities between the context sentence and each sentence in the list | |
| similarities = np.inner(context_embedding, sentence_embeddings) | |
| # Find the index of the most similar sentence | |
| most_similar_index = np.argmax(similarities) | |
| return labels_list[most_similar_index], similarities[most_similar_index], most_similar_index | |
| def search_wikipedia(query, driver): | |
| # Go to Wikipedia's main page | |
| driver.get("https://www.wikipedia.org/") | |
| # Find the search bar using its name | |
| search_bar = driver.find_element(By.NAME, "search") | |
| # Send the query to the search bar and hit Enter | |
| search_bar.send_keys(query) | |
| search_bar.send_keys(Keys.RETURN) | |
| return driver | |
| def get_topic_context(driver): | |
| # Find the first paragraph of the main article | |
| first_paragraph = driver.find_element(By.CSS_SELECTOR, "div.mw-parser-output > p:not(.mw-empty-elt)").text | |
| context_sentence = first_paragraph.split(". ")[0] | |
| # print(context_sentence) | |
| return context_sentence | |
| def search_wikipedia(query, driver): | |
| # Go to Wikipedia's main page | |
| driver.get("https://www.wikipedia.org/") | |
| # Find the search bar using its name | |
| search_bar = driver.find_element(By.NAME, "search") | |
| # Send the query to the search bar and hit Enter | |
| search_bar.send_keys(query) | |
| search_bar.send_keys(Keys.RETURN) | |
| return driver | |
| def get_topic_context(driver): | |
| # Find the first paragraph of the main article | |
| first_paragraph = driver.find_element(By.CSS_SELECTOR, "div.mw-parser-output > p:not(.mw-empty-elt)").text | |
| context_sentence = first_paragraph.split(". ")[0] | |
| # print(context_sentence) | |
| return context_sentence | |
| def play_wiki_game(starting_topic: str, target_topic: str, limit: int = 100): | |
| ##### Setup Chrome options | |
| chrome_options = webdriver.ChromeOptions() | |
| chrome_options.add_argument("--headless") # Ensure GUI is off | |
| chrome_options.add_argument("--no-sandbox") | |
| chrome_options.add_argument("--disable-dev-shm-usage") | |
| driver = webdriver.Chrome(options = chrome_options) | |
| topic = starting_topic | |
| num_pages = 0 | |
| used_topics = [] | |
| used_links = [] | |
| start_time = time.time() | |
| ### BEGIN ### | |
| print("-" * 150) | |
| print(f"\nStarting!\n") | |
| print("-" * 150) | |
| driver = search_wikipedia(starting_topic, driver) | |
| used_links.append(driver.current_url) | |
| while True: | |
| # increment the page tracking by 1 for each new page | |
| num_pages += 1 | |
| # if not the first page, navigate to the new page | |
| if num_pages > 1: | |
| driver.get(next_link) | |
| context_sentence = get_topic_context(driver) | |
| links_texts = [] | |
| current_url = driver.current_url | |
| current_url_suffix = str(current_url).split("/")[-1] | |
| ### Use BeautifulSoup and Requests instead of Selenium for link extraction | |
| current_page = driver.page_source # html from Selenium instead of BeautifulSoup | |
| soup = BeautifulSoup(current_page, 'html.parser') | |
| links = soup.find_all('a') | |
| # Iterate through the links and extract their URLs | |
| for link in links: | |
| link_url = link.get('href') | |
| if link_url and link_url.startswith("/wiki/"): | |
| link_url = "https://en.wikipedia.org" + link_url | |
| link_text = link.text.strip() # Get the text and remove leading/trailing spaces | |
| # make sure they are both not None | |
| if link_text and current_url_suffix not in link_url: | |
| if link_url not in used_links and link_text not in used_topics: | |
| # eliminates topic duplicates, non-wiki links, and wiki-help pages (non-content pages) | |
| if topic.lower() not in link_url.lower() and "en.wikipedia.org/wiki/" in link_url and ":" not in "".join(link_url.split("/")[1:]) and "Main_Page" != str(link_url.split("/")[-1]): | |
| links_texts.append((link_url, link_text)) | |
| best_label, best_score, loc_idx = most_similar_sentence(target_topic = target_topic, labels_list = [text for link, text in links_texts]) | |
| print(f"\nPage: {num_pages}") | |
| print(f"Current topic: '{topic.title()}'") | |
| print(f"Current URL: '{current_url}'") | |
| print(f"Current Topic Context: '{context_sentence}'") | |
| print(f"Next topic: '{best_label.title()}'. Semantic similarity to '{target_topic.title()}': {round((best_score * 100), 2)}%") | |
| next_link, topic = links_texts[loc_idx] | |
| # print(next_link) | |
| # if target_topic.lower() in topic.lower():# or best_score > float(0.85): | |
| if target_topic.lower() == topic.lower() or calculate_jaro_similarity(target_topic.lower(), topic.lower()) > 0.9 or best_score > float(0.90): # if topic text is identical or at least 90% the same spelling | |
| print("\n" + "-" * 150) | |
| print(f"\nFrom '{starting_topic.title()}', to '{target_topic.title()}' in {num_pages} pages, {round(time.time() - start_time, 2)} seconds!") | |
| print(f"Starting topic: '{starting_topic.title()}': '{used_links[0]}'") | |
| print(f"Target topic: '{target_topic.title()}': '{used_links[-1]}'\n") | |
| print("-" * 150) | |
| break | |
| ##### ADD DRAMATIC DELAY HERE ##### | |
| # time.sleep(0.5) | |
| # time.sleep(10) | |
| if num_pages == limit: | |
| print("\n" + "-" * 150) | |
| print(f"\nUnfortunately, the model couldn't get from '{starting_topic.title()}', to '{target_topic.title()}' in {num_pages} pages or less.") | |
| print(f"In {round(time.time() - start_time, 2)} seconds, it got from '{starting_topic.title()}': '{used_links[0]}', to '{target_topic.title()}': '{used_links[-1]}'") | |
| print(f"\nTry a different combination to see if it can do it!\n") | |
| print("-" * 150) | |
| break | |
| used_links.append(next_link) | |
| used_topics.append(topic) | |
| driver.quit() | |
| ###### Example | |
| # starting_topic = "soulja boy" | |
| # target_topic = "test" | |
| # play_wiki_game(starting_topic = starting_topic, target_topic = target_topic, limit = 50) |