deputes.py

import urllib
import os
import lxml.html
import re


doc = lxml.html.parse("http://www.assemblee-nationale.fr/qui/xml/liste_alpha.asp?legislature=11").getroot()
doc.make_links_absolute()
birth = re.compile('[0-9][0-9]?e?r? \\S+ [0-9]{4}')
name = re.compile('<[Hh]1[^>]*?>(.*?)</[Hh]1>')
for d in doc.xpath('id("deputes")/li/a'):
	str = urllib.urlopen(d.get('href')).read()
	print "%s;%s"%(name.search(str).expand("\\1"),birth.search(str).group().replace("1er ","1 "))

deputes11.py

import urllib
import os
import lxml.html
import re


doc = lxml.html.parse("http://www.assemblee-nationale.fr/qui/xml/liste_alpha.asp?legislature=11").getroot()
doc.make_links_absolute()
birth = re.compile('[0-9][0-9]?e?r? \\S+ [0-9]{4}')
name = re.compile('<TITLE>(.*?)</TITLE>')
for d in doc.xpath('id("deputes")/li/a'):
	str = urllib.urlopen(d.get('href')).read()
	try:
		strBirth = birth.search(str).group().replace("1er ","1 ")
	except:
		strBirth = "?"
	print "%s;%s"%(name.search(str).expand("\\1"),strBirth)

deputesWikipedia.py

import urllib
import os
import lxml.html
import re

os.environ['http_proxy'] = "http://<proxy-url>:<port>"
#doc = lxml.html.parse("http://fr.wikipedia.org/wiki/Liste_des_d%C3%A9put%C3%A9s_de_la_Ire_l%C3%A9gislature_de_la_Cinqui%C3%A8me_R%C3%A9publique").getroot()
#doc = lxml.html.parse("http://en.wikipedia.org/wiki/Main_Page").getroot()
#doc = lxml.html.parse("http://www.assemblee-nationale.fr/qui/xml/liste_alpha.asp?legislature=11").getroot()
str = urllib.urlopen("http://en.wikipedia.org/wiki/Main_Page").read()
print str
doc.make_links_absolute()
birth = re.compile('[0-9][0-9]?e?r? \\S+ [0-9]{4}')
name = re.compile('<[Hh]1[^>]*?>(.*?)</[Hh]1>')
for d in doc.xpath('/html/body/table/tr/td/a'):
	print d
#	str = urllib.urlopen(d.get('href')).read()
#	print "%s;%s"%(name.search(str).expand("\\1"),birth.search(str).group().replace("1er ","1 "))