Resubmitting MP3

textmining_processing.py

@@ -0,0 +1,60 @@
+
+import pickle
+import string
+
+"""
+Finding  the longest word
+"""
+plays = ['geschwister.txt', 'berlichingen.txt', 'iphigenie.txt']
+prose = ['reinekefuchs.txt']
+book = ['werther1.txt', 'werther2.txt']
+
+
+def clean_text(file_name):
+    input_file = open(file_name, 'rb')
+    text = pickle.load(input_file)
+    if file_name in plays:
+        start = text.find('Personen')  # beginning of play
+    elif file_name in prose:
+        start = text.find('Inhalt')  # beginning of prose
+    elif file_name in book:
+        start = text.find('Ausgabe')  # beginning of prose
+    text = text[start:]
+    text = text.replace(',', '')
+    text = text.replace('.', '')
+    text = text.replace('--', ' ')
+    text = text.replace('!', '')
+    text = text.replace('?', '')
+    text = text.replace(')', '')
+    text = text.replace('(', '')
+    text = text.replace("'", '')
+    print(file_name)
+    return text
+
+
+def longest_words(text):
+    text = text.split()
+    # print(text)
+    words = []
+    for word in text:
+        length = len(word)
+        words.append((length, word))
+        words.sort(reverse=True)
+    print(words)
+    top = words[0:4]
+    return top
+
+
+def final_analysis(text):
+    clean = clean_text(text)
+    top = longest_words(clean)
+    for pair in top:
+        print(pair)
+
+
+# final_analysis('berlichingen.txt')
+final_analysis('geschwister.txt')
+# final_analysis('iphigenie.txt')
+# final_analysis('reinekefuchs.txt')
+# final_analysis('werther1.txt')
+# final_analysis('werther2.txt')

textmining_requests.py

@@ -0,0 +1,32 @@
+import pickle
+import requests
+
+geschwister = requests.get('http://www.gutenberg.org/cache/epub/2406/pg2406.txt').text
+f = open('geschwister.txt', 'wb')
+pickle.dump(geschwister, f)
+f.close()
+
+berlichingen = requests.get('http://www.gutenberg.org/cache/epub/2321/pg2321.txt').text
+f = open('berlichingen.txt', 'wb')
+pickle.dump(berlichingen, f)
+f.close()
+
+reinekefuchs = requests.get('http://www.gutenberg.org/cache/epub/2228/pg2228.txt').text
+f = open('reinekefuchs.txt', 'wb')
+pickle.dump(reinekefuchs, f)
+f.close()
+
+iphigenie = requests.get('http://www.gutenberg.org/cache/epub/2054/pg2054.txt').text
+f = open('iphigenie.txt', 'wb')
+pickle.dump(iphigenie, f)
+f.close()
+
+werther1 = requests.get('http://www.gutenberg.org/cache/epub/2407/pg2407.txt').text
+f = open('werther1.txt', 'wb')
+pickle.dump(werther1, f)
+f.close()
+
+werther2 = requests.get('http://www.gutenberg.org/cache/epub/2408/pg2408.txt').text
+f = open('werther2.txt', 'wb')
+pickle.dump(werther2, f)
+f.close()