aboutsummaryrefslogtreecommitdiffstats
path: root/gg_scrapper.py
diff options
context:
space:
mode:
authorMatěj Cepl <mcepl@redhat.com>2013-12-30 01:11:17 +0100
committerMatěj Cepl <mcepl@redhat.com>2013-12-30 01:11:17 +0100
commit6ce68fd69aa0403766bac31c85be6bb4a3a286cc (patch)
tree2e309158b5d86c5689ed99d04024eeced4367f89 /gg_scrapper.py
parentdfbb929e6b9985810646a19850268c382820791e (diff)
downloadgg_scraper-6ce68fd69aa0403766bac31c85be6bb4a3a286cc.tar.gz
Collect raw article
Diffstat (limited to 'gg_scrapper.py')
-rwxr-xr-xgg_scrapper.py14
1 files changed, 13 insertions, 1 deletions
diff --git a/gg_scrapper.py b/gg_scrapper.py
index f516892..13da91d 100755
--- a/gg_scrapper.py
+++ b/gg_scrapper.py
@@ -1,6 +1,7 @@
#!/usr/bin/python3
import re
+import subprocess
import urllib.request
import urllib.error
import urllib.parse
@@ -60,7 +61,17 @@ class Page(object):
class Article(Page):
def __init__(self, URL):
super(Article, self).__init__()
- self.root = URL
+ self.root = URL.replace('#!msg/', 'message/raw?msg=')
+ self.raw_message = ''
+
+ def collect_message(self):
+ with self.opener.open(self.root) as res:
+ raw_msg = res.read()
+ proc = subprocess.Popen(['/usr/bin/formail'],
+ stdin=subprocess.PIPE,
+ stdout=subprocess.PIPE)
+ result = proc.communicate(raw_msg)[0]
+ return result.decode()
class Topic(Page):
@@ -68,6 +79,7 @@ class Topic(Page):
super(Topic, self).__init__()
self.name = name
self.root = self.do_redirect(URL)
+ self.articles = []
def __unicode__(self):
return "%s: %s" % (self.root, self.name)