Das deutsche Python-Forum

Code: Alles auswählen

#!/usr/bin/python
# vim: set fileencoding=utf-8 :
import cgi
import cgitb; cgitb.enable()
import os, re, pickle
from random import choice

print "content-type: text/html; charset=utf-8\r\n\r\n"

def main():
    depth = 3
    fs = cgi.FieldStorage()
    nametype = fs["type"].value
    if not re.match("^[a-z]+$", nametype): return
    namedata = pickle.load(open(os.path.join("names/", nametype + ".pickle")))
    print "<ul>"
    for i in range(10):
        print "<li>" + generate_name(namedata, depth) + "</li>"
    print "</ul>"
    

def generate_name(namedata, depth):
    current = ""
    name = ""
    while True:
        letter = choice(namedata[current])
        if letter == "\n":
            return name
        else:
            name += letter
            current = name[-depth:]
main()

Code: Alles auswählen

#!/usr/bin/env python
# vim: set fileencoding=utf-8 :
import pickle
import sys
def main():
    depth = 3
    if len(sys.argv) != 3:
        sys.exit("Usage: " + sys.argv[0] + " input.txt ouput.pickle")
    result = analyze(sys.argv[1], depth)
    f = open(sys.argv[2],"w")
    pickle.dump(result, f)
    f.close()

def analyze(path, depth):
    result = {}
    f = open(path)
    for line in f:
        combination = ""
        for i, letter in enumerate(line):
            result[combination] = result.get(combination, []) + [letter]
            combination = combination[-(depth-1):] +  letter
    f.close()
    return result
            
if __name__ == "__main__":
    main()

Code: Alles auswählen

# vim: set fileencoding=utf-8 :
import urllib2
import re
def main():
    category = raw_input("Kategorie:")#"Weiblicher_Vorname"
    url = "http://de.wikipedia.org/w/query.php?what=category&cptitle=%s&format=xml"\
          "&cpfrom=" % urllib2.quote(category)
    cpfrom = ""
    while True:
        u = urllib2.urlopen(url + urllib2.quote(cpfrom))
        xml = u.read()
        matches = re.findall("<title>(.*?)</title>", xml)[1:]
        for match in matches:
            print match
        next = re.search(r'<category next=\"(.*?)\"', xml)
        if next: cpfrom = next.group(1)
        else: break

if __name__ == "__main__":
    main()