leonardreidy

from bs4 import BeautifulSoup

def preproc(infile, outfile):

  #open input file for reading
  file = open(infile, 'r')

  #create BeautifulSoup object with the file contents
  soup = BeautifulSoup(file)

leonardreidy

import os

#get a list of the files in the current directory
a = os.listdir(os.getcwd())

def postproc(a):
#for every file in the directory
  for i in a:
#call the preproc function on said file and generate the appropriate outfile
    preproc(i, "out"+str(a.index(i))+".txt")

leonardreidy

import os
from bs4 import BeautifulSoup

# get a list of the files in the current directory
here = os.listdir(os.getcwd())

# define preprocessing method to extract email addresses from a given 
# html file

def preproc(infile, outfile):

leonardreidy

# A simple program to extract the administrator name, and school name from
# the html files of an online directory then output a file each for 
# the lists of names and schools using the json.dumps() approach to generate
# simple json output
def extractor(infile, outfile1, outfile2):
  file = open(infile, 'r')
	soup = BeautifulSoup(file)
	commonsoup = soup('strong')
	names = []
	schools = []

leonardreidy

# A simple python script to extract names, and emails from
# a certain online directory

import os, json
from bs4 import BeautifulSoup

#get a list of the files in the current directory
inputfiles = os.listdir(os.getcwd())

def postproc(inputfiles):

leonardreidy

#
# Note that this program does not have any error-handling code, so if it fails, 
# you will just get some error messages at the command line. It won't skip the offending
# email and move on with the task; it will fail entirely.
#
# Keep an eye on the command prompt periodically, if you don't
# know how to write error-handling code. If it does fail, as it occassionally will
# due to a server rejecting the email, or something like that, then look in your
# Gmail 'sent' folder to identify the last email sent. Then, compare to the list
# of contacts. It will almost certainly have failed because of the next email in the list.

leonardreidy

import glob
# glob does regular expression pattern matching, expansion etc, and, it returns
# a list of strings - nice and easy to work with

  
# List files starting with anything and ending with anything:
# glob.glob("*.*")
#
# to list only text files, for example, try:
# glob.glob("*.txt")

leonardreidy

#! /usr/bin/env python

# Twizzer-0-0-1.py: Simple script for pulling streaming data from Twitter using 
# the credentials of a given user. You will need a developer account for this
# to work, because of the way Twitter API 1.1 handles authentication etc. This script is 
# based on a very similar script, by YouTube user SentDex, but with some modifcations
# suggested by YouTube user Satish Chandra, and some of my own to resolve stdout encoding
# issues, and user interaction.
# 
# ROADMAP

leonardreidy

function throttle( fn, time ) {
    var t = 0;
    return function() {
        var args = arguments, ctx = this;
        clearTimeout(t);

        t = setTimeout( function() {
            fn.apply( ctx, args );
        }, time );
    };

leonardreidy

from bs4 import BeautifulSoup

# open the infile for reading
file = open(infile, 'r')
  
# convert the contents of the infile to a Beautiful Soup object
soup = BeautifulSoup(file)

# create lists, a list containing bs4.element.Tag items generated by using 
# the .select() syntax - the texts and their author names are contained in