moved strip_html from http to text
This commit is contained in:
parent
8b23ba9c12
commit
6247409906
|
@ -1,6 +1,6 @@
|
|||
# Plugin by Infinity - <https://github.com/infinitylabs/UguuBot>
|
||||
|
||||
from util import hook, http
|
||||
from util import hook, http, text
|
||||
|
||||
db_ready = False
|
||||
|
||||
|
@ -42,7 +42,7 @@ def horoscope(inp, db=None, notice=None, nick=None):
|
|||
title = soup.find_all('h1', {'class': 'h1b'})[1]
|
||||
horoscope = soup.find('div', {'class': 'fontdef1'})
|
||||
result = "\x02%s\x02 %s" % (title, horoscope)
|
||||
result = http.strip_html(result)
|
||||
result = text.strip_html(result)
|
||||
#result = unicode(result, "utf8").replace('flight ','')
|
||||
|
||||
if not title:
|
||||
|
|
|
@ -11,9 +11,6 @@ from urllib import quote, quote_plus as _quote_plus
|
|||
from lxml import etree, html
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
from HTMLParser import HTMLParser
|
||||
import htmlentitydefs
|
||||
|
||||
# used in plugins that import this
|
||||
from urllib2 import URLError, HTTPError
|
||||
|
||||
|
@ -30,26 +27,6 @@ ua_chrome = 'Mozilla/5.0 (X11; Linux i686) AppleWebKit/537.4 (KHTML, ' \
|
|||
jar = cookielib.CookieJar()
|
||||
|
||||
|
||||
class HTMLTextExtractor(HTMLParser):
|
||||
def __init__(self):
|
||||
HTMLParser.__init__(self)
|
||||
self.result = []
|
||||
|
||||
def handle_data(self, d):
|
||||
self.result.append(d)
|
||||
|
||||
def handle_charref(self, number):
|
||||
codepoint = int(number[1:], 16) if number[0] in (u'x', u'X') else int(number)
|
||||
self.result.append(unichr(codepoint))
|
||||
|
||||
def handle_entityref(self, name):
|
||||
codepoint = htmlentitydefs.name2codepoint[name]
|
||||
self.result.append(unichr(codepoint))
|
||||
|
||||
def get_text(self):
|
||||
return u''.join(self.result)
|
||||
|
||||
|
||||
def get(*args, **kwargs):
|
||||
return open(*args, **kwargs).read()
|
||||
|
||||
|
@ -133,9 +110,3 @@ def unescape(s):
|
|||
if not s.strip():
|
||||
return s
|
||||
return html.fromstring(s).text_content()
|
||||
|
||||
|
||||
def strip_html(html):
|
||||
s = HTMLTextExtractor()
|
||||
s.feed(html)
|
||||
return s.get_text()
|
||||
|
|
|
@ -6,6 +6,35 @@
|
|||
|
||||
import re
|
||||
|
||||
from HTMLParser import HTMLParser
|
||||
import htmlentitydefs
|
||||
|
||||
|
||||
class HTMLTextExtractor(HTMLParser):
|
||||
def __init__(self):
|
||||
HTMLParser.__init__(self)
|
||||
self.result = []
|
||||
|
||||
def handle_data(self, d):
|
||||
self.result.append(d)
|
||||
|
||||
def handle_charref(self, number):
|
||||
codepoint = int(number[1:], 16) if number[0] in (u'x', u'X') else int(number)
|
||||
self.result.append(unichr(codepoint))
|
||||
|
||||
def handle_entityref(self, name):
|
||||
codepoint = htmlentitydefs.name2codepoint[name]
|
||||
self.result.append(unichr(codepoint))
|
||||
|
||||
def get_text(self):
|
||||
return u''.join(self.result)
|
||||
|
||||
|
||||
def strip_html(html):
|
||||
s = HTMLTextExtractor()
|
||||
s.feed(html)
|
||||
return s.get_text()
|
||||
|
||||
|
||||
def munge(text, munge_count=0):
|
||||
"""munges up text."""
|
||||
|
|
Reference in a new issue