blob: 6fabcc11badef8a6bbb2208534f3d969f6ab261e (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
|
# -*- coding: utf-8 -*-
#import scraperwiki
import json
from BeautifulSoup import BeautifulSoup
import datetime
import dateutil.parser
import lxml.html
import urlparse
import re
import urllib2
frontpage = 'https://sio.no/snarveier/om-sio/rapporter-og-referater'
#scraperwiki.scrape(frontpage)
#postlistelib=scraperwiki.swimport('postliste-python-lib')
agency = 'Samskipnaden i Oslo og Akershus'
baseurl = 'https://sio.no'
response = urllib2.urlopen(frontpage)
html = response.read()
root = lxml.html.fromstring(html)
urls = root.cssselect("a.readmore")
urllist = []
for ahref in urls:
linktext = ahref.text_content()
if -1 != linktext.find('Postliste SiO'):
href = ahref.attrib['href']
print href
urllist.append(baseurl + href)
|
