ChCh/CloudBot
Archived
11
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Run data through BS4 to fix the text formatting and all that crap (will optimise later)

Browse source
This commit is contained in:
Luke Rogers 2013-07-16 03:04:07 +12:00
parent 85ec22a005
commit a3669e6b50
1 changed files with 6 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

11
plugins/scp.py
View file

@ -12,15 +12,16 @@ def api_get(kind, query):
def get_info(url): def get_info(url):
try: try:
page = http.get(url) soup = http.get_soup(url)
except Exception as e: except Exception as e:
return "Could not get SCP information: Unable to fetch URL. ({})".format(e) return "Could not get SCP information: Unable to fetch URL. ({})".format(e)
contents = re.sub('<[^<]+?>', '', page) safe_html = unicode(soup)
contents = re.sub('<[^<]+?>', '', safe_html)
try: try:
item_id = http.unescape(re.findall("Item #: (.+?)\n", contents, re.S)[0]) item_id = re.findall("Item #: (.+?)\n", contents, re.S)[0]
object_class = http.unescape(re.findall("Object Class: (.+?)\n", contents, re.S)[0]) object_class = re.findall("Object Class: (.+?)\n", contents, re.S)[0]
description = http.unescape(re.findall("Description: (.+?)\n", contents, re.S)[0]) description = re.findall("Description: (.+?)\n", contents, re.S)[0]
except IndexError as e: except IndexError as e:
return "Could not get SCP information: Page was not a valid SCP page." return "Could not get SCP information: Page was not a valid SCP page."