Scrap the tunisian constitution articles and save them to seperate CSV files in function of chapters.

dostour.py

#!/usr/bin/python
# -*- coding: utf-8 -*-

from bs4 import BeautifulSoup
import urllib2

__author__ = "Aymen Amri"
__email__ = "[email protected]"


for counter in range (1, 6):
	counter = str(counter)
	baseUrl="http://www.marsad.tn/constitution/4/chapitre/"
	url = baseUrl + counter
	constFile = urllib2.urlopen(url)
	constHtml = constFile.read()
	soup = BeautifulSoup(constHtml)
	constArt = soup.find_all("div")
	articles = soup.findAll('div', { "class" : "clear texte" })
	titles = soup.findAll('h4', { "class" : "clearfloat" })

	print "."* int(counter)

	import csv
	fileName= counter +".csv"
	w = csv.writer(open(fileName, "w"))

	for article, title in zip(articles, titles):
		textTitle = "".join(title.findAll(text=True))
		textArticle = "".join(article.findAll(text=True))
		out = [textTitle.encode('utf-8'), textArticle.encode('utf-8')]
		w.writerow(out)