Skip to content

Instantly share code, notes, and snippets.

@melpomene
Created August 16, 2012 23:13
Show Gist options
  • Save melpomene/3374398 to your computer and use it in GitHub Desktop.
Save melpomene/3374398 to your computer and use it in GitHub Desktop.
Vad får man kommentera på DN.se
""" To run first
touch old_url.txt
touch data.txt
requires requests and feedparser (available through pip)
"""
import requests
import feedparser
rss = 'http://www.dn.se/nyheter/m/rss/senaste-nytt'
old_urls_file = 'old_url.txt'
data_file = 'data.txt'
def main():
feed = feedparser.parse(rss)
old_str = open(old_urls_file, 'r').read()
old = open(old_urls_file, "a")
new = open(data_file, 'a')
for item in feed['items']:
if item['link'] not in old_str:
comment = check_url_for_comment(item['link'])
old.write(item['link']+u"\n")
new.write((comment + u"\t " + item['title'] + u"\t " + item['date'] + u"\t " + item['link'] + "\n").encode("utf-8"))
def check_url_for_comment(url):
r = requests.get(url)
if r.status_code == 200:
body = r.content
if 'class="comments"' in body:
return u"True"
else:
return u"False"
else:
raise Exception("Unable to access DN.se")
main()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment