cadey
/
h
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

snopes.py: search snopes and return the header of the found article

This commit is contained in:
Ryan Hitchman 2010-11-11 10:39:40 -06:00
parent 7c171959c3
commit 98709ab40c
1 changed files with 26 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
plugins/snopes.py Normal file
View File

@ -0,0 +1,26 @@
import re
from util import hook, http
search_url = "http://search.atomz.com/search/?sp_a=00062d45-sp00000000"
@hook.command
def snopes(inp):
search_page = http.get_html(search_url, sp_q=inp, sp_c="1")
result_urls = search_page.xpath("//a[@target='_self']/@href")
if not result_urls:
return "no matching pages found"
snopes_page = http.get_html(result_urls[0])
snopes_text = snopes_page.text_content()
claim = re.search(r"Claim: .*", snopes_text).group(0)
status = re.search(r"Status: .*", snopes_text).group(0)
claim = re.sub(r"[\s\xa0]+", " ", claim) # compress whitespace
status = re.sub(r"[\s\xa0]+", " ", status)
return "%s %s %s" % (claim, status, result_urls[0])