tdpearson

# For background information, DOCX files are ZIP archives containing XML files.
# I had a recent project that needed comments extracted from several MS Word documents.
# This would have been painful to do manually - command line to the rescue!

find . -name "*.docx" -exec sh -c 'unzip -p $1 word/comments.xml | xmllint -xpath "//text()" -' sh {} \;

tdpearson

#!/usr/bin/env python
import boto3
from sys import argv

"""
Example of undeleting in S3 with specified key prefix
"""

def restore_bag(bagname):
    """ undelete derivative bag """

tdpearson

from jinja2 import Environment

mytemp = """ 
   my box number is {{ "%(box)04d"|format(box=mybox) }}
""" 

print Environment().from_string(mytemp).render(mybox=456)

# my box number is 0456

tdpearson

purchases = [12, 43, 13, 465, 1, 13]
n = 2
d = 3


class Prizes(object):
    def __init__(self, purchases1, n1, d1):
        self.pu = purchases1
        self.n = n1
        self.d = d1

tdpearson

import requests
from bs4 import BeautifulSoup

# Iterate over author pages
for page in range(1, 2):  #TODO: update to number of pages + 1 (i.e. 15 pages would be 16)
    data = {"gruppo": "autori",
            "iniziale": "all",
            "pag": page}
    response = requests.post("http://digiliblt.lett.unipmn.it/testi.php", data=data)
    soup = BeautifulSoup(response.text, "lxml")

tdpearson

import pandas as pd

df = pd.DataFrame.from_csv(r"append_test.txt", sep='\t')

frames = []
for meeting in range(len(df.T)):  # iterate over recorded attendances
    attendees = df[df.T.iloc[meeting] == 1].index  # get attendees for specific meeting
    frames.append(pd.DataFrame(index=attendees, columns=attendees).fillna(1))  # create frame from attendees

# sum up jointly attended meetings