This code snippet gives a demo of
Code
UrlHandler.py
__init__.py
- creating and importing module
- raw string to ignore escape characters in a string e.g. file location
- reading bytes from a URL
- parsing bytes and converting them into string words
Code
UrlHandler.py
__author__ = 'akhtar' from urllib.request import urlopen def rawStringExample(): path = r"C:\Program Files\Microsoft Office\Office14\1033" print(path) def readingURL(url='http://techmightsolutions.blogspot.com/'): story_words =[] with urlopen(url) as story: for line in story: line_word = line.decode('utf-8').split() for word in line_word: story_words.append(word) return story_words def getWordCount(url='http://techmightsolutions.blogspot.com/'): return len(str(readingURL(url)))
__init__.py
__author__ = 'akhtar' from com.techmight.UrlHandler import readingURL, getWordCount def main(): print(readingURL()) print(getWordCount("http://timesofindia.indiatimes.com")) if __name__ == '__main__': main()