from bs4 import BeautifulSoup
import sys
import os.path
import glob2
import re

list = []
tags = []

def processFiles(args):
    input_filemask = "log"
    directory = args[1]
    if os.path.isdir(directory):
        print ("processing a directory")
        list_of_files = glob2.glob('%s/*.%s' % (directory, input_filemask))
    else:
        print ("processing a list of files")
        list_of_files = sys.argv[1:]
    for file_name in list_of_files:
        print (file_name)
        processFile(file_name)

def has_class_but_no_id(tag): #method to return all <p></p> tags and contents
    return tag.has_attr('class') and not tag.has_attr('id')

def processFile(filename):
    soup = BeautifulSoup(open(filename), 'html.parser')
    list = soup.find_all(has_class_but_no_id)
    for tag in list:
        tags.append(str(tag))
    for result in tags:
        if result.find("iot platform") != -1:
            print(result.encode("utf-8"))

if __name__ == '__main__':
    if (len(sys.argv) > 1):
        processFiles(sys.argv)
    else:
        print ("usage message")