]> projects.mako.cc - iron-blogger/blob - import-feeds.py
Move build products into out/
[iron-blogger] / import-feeds.py
1 from lxml import html
2 import yaml
3 import urllib2
4 import urlparse
5
6 with open('bloggers.yml') as f:
7     users = yaml.safe_load(f.read())
8
9 def fetch_links(url):
10     tree = html.fromstring(urllib2.urlopen(url).read())
11     links = tree.xpath(
12         '//link[@rel="alternate"][contains(@type, "rss") or ' +
13         'contains(@type, "atom") or contains(@type, "rdf")]')
14     candidates = [l for l in links if
15                   'atom' in l.attrib['type'] and
16                   'comments' not in l.attrib['href'].lower() and
17                   'comments' not in l.attrib.get('title','')]
18     if candidates:
19         return candidates[0].attrib['href']
20     return links[0].attrib['href']
21
22 for (name, u) in users.items():
23     print "[%s]" % name
24     for e in u['links']:
25         (title, url) = e[0:2]
26         print " - %s:" % title.strip()
27         e[0] = e[0].strip()
28         if len(e) == 3:
29             continue
30         link = fetch_links(url)
31         if not link.startswith('http:'):
32             link = urlparse.urljoin(url, link)
33         print "   %s" % (link,)
34         e.append(link)
35
36 with open('bloggers.yml', 'w') as f:
37     yaml.safe_dump(users, f)

Benjamin Mako Hill || Want to submit a patch?