Lab 6

Day4/scrape.py

@@ -9,11 +9,6 @@
 import random
 import time
 import os
-import re
-
-#from nltk.util import clean_html
-#import urllib2 
-
 
 # Open a web page
 web_address='https://polisci.wustl.edu/faculty/specialization'
@@ -29,8 +24,7 @@
 
 
 # Get the attributes
-my_a_tag=soup.find_all('a')[2]
-re.sub(r'<[^>]+>', '', str(my_a_tag)) #remove tags
+my_a_tag=soup.find_all('a')[2] #?? What is the second index for
 my_a_tag.attrs #Gives a dictionary with the attributes
 my_a_tag.attrs.keys()
 my_a_tag['alt']
@@ -42,8 +36,6 @@
 mysection=soup.find_all('div')[0]
 mysection.a #Gives the 'a' tag within the 'div' tag
 mysection.find_all('a') #Gives the list of all 'a' tags within the 'div' tag
-mysection.get_text()
-
 
 # Creating a tree of objects
 
@@ -85,3 +77,9 @@ def download_page(address,path,filename,wait=5):
 soup.prettify()
 
 
+with open('scrapetest1.csv', 'wb') as f:
+  my_writer = csv.writer(f)
+  for i in mysection:
+    my_writer.writerow([i, i-1])
+
+

Day6/lab6.py

@@ -1,5 +1,41 @@
 #Exercise 1
 #Write a function to calculate the greatest common divisor of two numbers
+
+def common_divisor(number1, number2):
+	if number1 % number2 == 0:
+		print number2
+	elif number2 % number1 == 0:
+		print number1
+	return common_divisor(number2,(number1 % number2))
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 
 #Exercise 2
 #Write a function that returns prime numbers less than 121