Merge branch 'master' of https://mit.cs.uchicago.edu/mawh/project_kitty

README.txt

+WikiWikiHow.py - contains code to creates the user interface, including a window to enter query and filters, along with the display of results. TO USE WikiWikiHow, type: python3 WikiWikiHow.py
+
+SearchResults.py
+	- SearchResults class, which takes query and filters input and returns a list of Article objects that match the query and filters
+	- Article class, each instance of which corresponds to one article in the SearchResults output. Articles also contain lists of related articles, which are filtered by relevance.
+	- OuterArticle class, which allows for some filtering to be done before BeautifulSoup objects are made. This saves computational power.
+	
+old - a directory containing old test files and individual group members' work that was later added to the main file
+
+inappropriate_words.py - contains a function that creates a list of words that will be selected out if Child Safe mode is turned on. I would advise against opening this file since it's basically just a very long list of vulgar words.

SearchResults.py

@@ -172,9 +172,8 @@ class SearchResults:
     def passes_all_filters(self, article):
         if 'Main-Page' in article.url:
             return False
-        if 'child_safe' in self.__filters:
-            if self.__filters['child_safe']:
-                self.__forbidden_words += inappropriate_words_lst
+        if self.__filters['child_safe']:
+            self.__forbidden_words += inappropriate_words_lst
         if 'pct_helpful' in self.__filters:
             try:
                 if int(article.pct_helpful) < self.__filters['pct_helpful']:
@@ -194,13 +193,13 @@ class SearchResults:
             for w in self.__required_words:
                 W = w[0].upper() + w[1:]
                 wl = w[0].lower() + w[1:]
-                if W not in article.words and wl not in article.words:
+                if W not in article.words_lst and wl not in article.words_lst:
                     return False
         if len(self.__forbidden_words) != 0:
             for w in self.__forbidden_words:
                 W = w[0].upper() + w[1:]
                 wl = w[0].lower() + w[1:]
-                if W in article.words or wl in article.words:
+                if W in article.words_lst or wl in article.words_lst:
                     return False
         if self.__filters['q_verif']:
             try:
@@ -280,7 +279,7 @@ class Article:
         self.languages = self.find_languages(self.__soup)
         self.verif = self.expert_data(self.__soup)
         self.view = self.__repr__()
-        self.words = self.scrape_words(self.url, self.__soup)
+        self.words, self.words_lst = self.scrape_words(self.url, self.__soup)
         self.tags = self.find_common_words(self.words)
         self.link_family = self.all_peripheral_links(self.__soup, self.url)
         self.related_articles = []
@@ -450,7 +449,7 @@ class Article:
             for x in t:
                 x = x.strip()
                 text.append(x)
-        return " ".join(text)
+        return (" ".join(text), text)
 
 
     def all_peripheral_links(self, soup, url):

WikiWikiHow.py

@@ -35,7 +35,7 @@ def __main__(filters = {}):
         [sg.Spin([i for i in range(100)], initial_value=0, key = "num_voters"), sg.Text('Number of people who voted on helpfulness')],
         [sg.Spin([i for i in range(100)], initial_value=0, key = "num_sources"), sg.Text('Number of sources cited')],
         [sg.Spin([i for i in range(100)], initial_value=0, key = "num_views"), sg.Text('Views')],
-        [sg.Combo(['English', 'Español', 'Português', 'Italiano', 'Français', 'русский язык', 'Deutsch', '简体中文', 'Nederlands', 'Čeština', 'Bahasa', '日本語', 'हिंदी', 'ภาษาไทย',' العَرَبِيةُ', 'Tiếng Việt', '한국말', 'Türkçe',' فارسی'], key = 'language'), sg.Text('Available in')]]
+        [sg.Combo(['Español', 'Português', 'Italiano', 'Français', 'русский язык', 'Deutsch', '简体中文', 'Nederlands', 'Čeština', 'Bahasa', '日本語', 'हिंदी', 'ภาษาไทย',' العَرَبِيةُ', 'Tiếng Việt', '한국말', 'Türkçe',' فارسی'], key = 'language'), sg.Text('Available in (Defaults to English)')]]
  
     window = sg.Window('WikiHow Search and Filters', layout)
     results_pg_active = False