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

fix snopes to work with the new page format

This commit is contained in:
Ryan Hitchman 2010-12-02 15:32:23 -06:00
parent c8b4d5e15a
commit 68f2680b54
1 changed files with 8 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
plugins/snopes.py
View File

@ -19,8 +19,14 @@ def snopes(inp):
snopes_page = http.get_html(result_urls[0]) snopes_page = http.get_html(result_urls[0])
snopes_text = snopes_page.text_content() snopes_text = snopes_page.text_content()
claim = re.search(r"Claim: .*", snopes_text).group(0) claim = re.search(r"Claim: .*", snopes_text).group(0).strip()
status = re.search(r"Status: .*", snopes_text).group(0) status = re.search(r"Status: .*", snopes_text)
if status is not None:
status = status.group(0).strip()
else: # new-style statuses
status = "Status: %s." % re.search(r"FALSE|TRUE|MIXTURE|UNDETERMINED",
snopes_text).group(0).title()
claim = re.sub(r"[\s\xa0]+", " ", claim) # compress whitespace claim = re.sub(r"[\s\xa0]+", " ", claim) # compress whitespace
status = re.sub(r"[\s\xa0]+", " ", status) status = re.sub(r"[\s\xa0]+", " ", status)