Generate Wordcloud from Wikipedia Article

projects/Wikipedia Search Wordcloud/README.md

@@ -0,0 +1,12 @@
+# Wordcloud Images for Wikipedia Article
+Python script that prompts the user for an input, searches for the corresponding article on wikipedia and generates a wordcloud based on the searched article.
+
+### Prerequisites
+`pip install` the models in `requirements.txt` from your command prompt.
+
+### How to run the script
+Run like any other python file. Upon executing, the wordcloud image will be saved to the current directory. The script will also prompt a y/n if the user wants to see the generated image during execution.
+![script execution](script_execution.jpg)
+
+## *Author Name*
+[Naman Shah](https://github.com/namanshah01)

projects/Wikipedia Search Wordcloud/requirements.txt

@@ -0,0 +1,17 @@
+beautifulsoup4==4.9.1
+certifi==2020.6.20
+chardet==3.0.4
+cycler==0.10.0
+idna==2.10
+kiwisolver==1.2.0
+matplotlib==3.3.1
+numpy==1.19.1
+Pillow==7.2.0
+pyparsing==2.4.7
+python-dateutil==2.8.1
+requests==2.24.0
+six==1.15.0
+soupsieve==2.0.1
+urllib3==1.25.10
+wikipedia==1.4.0
+wordcloud==1.8.0

projects/Wikipedia Search Wordcloud/wiki-search-cloud.py

@@ -0,0 +1,44 @@
+from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator
+import matplotlib.pyplot as plt
+import wikipedia
+import sys
+import warnings
+# supressing unnecessary warnings
+warnings.filterwarnings("ignore")
+
+
+# function to search the wikipedia article and generate the wordcloud
+def gen_cloud(topic):
+    try:
+        content = str(wikipedia.page(topic).content)
+    except:
+        print("Error, try searching something else...")
+        sys.exit()
+    STOPWORDS.add('==')
+    stopwords = set(STOPWORDS)
+    wordcloud = WordCloud(stopwords=stopwords, max_words=200, background_color="black", width=600, height=350).generate(content)
+    return wordcloud
+
+
+# function to save the wordcloud to current directory
+def save_cloud(wordcloud):
+    wordcloud.to_file("./wordcloud.png")
+
+
+# function to display the wordcloud with matplotlib
+def show_cloud(wordcloud):
+    plt.imshow(wordcloud, interpolation='bilinear')
+    plt.axis("off")
+    plt.show()
+
+
+# driver code
+if __name__ == '__main__':
+    topic = input("What do you want to search: ").strip()
+    wordcloud = gen_cloud(topic)
+    save_cloud(wordcloud)
+    print("Wordcloud saved to current directory as wordcloud.png")
+    desc = input("Do you wish to see the output(y/n): ")
+    if desc == 'y':
+        show_cloud(wordcloud)
+    sys.exit()