epoz

from __future__ import print_function
# Export details from a collection of dmp files found at a certain path to a csv file

import os
import iconclass
import sys
from progress.bar import Bar
import textbase

print('Reading files...')

epoz

import os
import xml.etree.ElementTree as ET
from progress.bar import Bar

buf = []
errors = []

def g(filepath, doc, path):
    elem = doc.find(path)
    if elem is None:

epoz

import os
import sys
import re
import math
import random
import PIL.Image
import warnings
import json
from progress.bar import Bar
import textbase

epoz

codes = ['31D11222', '34B11', '45(+26)', '45C1', '45D12', '48C7341']
codes = [urllib.quote(x) for x in codes]
paths = set()
for obj in json.loads(urllib2.urlopen('http://iconclass.org/json/?notation='+'&notation='.join(codes)).read()):
    paths.update(obj.get('p'))
    paths.add(obj.get('n'))
txts = []
kws = set()
for p in json.loads(urllib2.urlopen('http://iconclass.org/json/?notation='+'&notation='.join(paths)).read()):
    txts.append(p.get('txt').get('de', u''))

epoz

class ElasticSearchPaginatorListException(Exception):
    pass

class ElasticSearchPaginatorList(object):
    def __init__(self, client, *args, **kwargs):
        self.client = client
        self.args = args
        self.kwargs = kwargs
        self._count = None

epoz

#!./bin/python
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import A4
from reportlab.lib.units import cm
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont
from PIL import Image
import PIL
import os
import json

epoz

# Working out number of quires from a STCN collation
examples = [
  {coll:'[*]2 2*-4*4 A-3Q4 2*2 `︠LO`3Q2 3R-5S4 5T2 5V-5Y4, 2A-G4 2H2 2I4 (3Q4 blank; lacks 3*4, blank?)',
   url:'http://picarta.pica.nl/xslt/DB=3.11/XMLPRS=Y/PPN?PPN=318093766',
   req:121,
   # A-Z 23, A-Z 23, A-Q 16, Q 1, R-Z 7, A-Z 23, A-S 18, T 1, V-Y 3, A-G 7, H 1, I 1,
  },
  {coll:'A-V8 W8 X-Z8', # if W found, then noted 'loose' like A-V8 W8 X-Z8
   req:24}
]

epoz

'''
Read in a STCN data dump file, and convert it to a CSV file (delimited with tabs)
The data looks something like this:


SET: S0 [10000] TTL: 5        PPN: 339722142                            PAG: 1 .

Ingevoerd: 1996:31-01-12 Gewijzigd: 1996:07-02-12 09:12:25 Status: 1996:31-01-12

0500 Aav

epoz

#!/usr/bin/env python
# Example: python gimmesrc.py De_Cive > txt

import sys, urllib, urllib2

URL = 'http://en.wikisource.org/w/index.php?action=raw&title='

if __name__ == '__main__':
    title = sys.argv[1]
    title_parts = []

epoz

#!/usr/bin/env python
'''
Markdown Watcher and auto regenerater

While sitting in an aeroplane, I found myself editing a bunch of Markdown
files and needing to regenerate the HTML and preview in a browser.
It was tedious re-typing the 'markdown' command every time, so I made 
this little script to watch the *.markdown files and create the corresponding
.html flavour if the modification date of the markdown file is newer or the
html does not exist yet.