pew
/
phenny-1
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Updated etymology interface

master
Sean B. Palmer 2012-02-27 00:10:33 +00:00
parent 6198b30d76
commit c5fe137b01
1 changed files with 17 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
modules/etymology.py
View File

@ -7,17 +7,25 @@ Licensed under the Eiffel Forum License 2.
http://inamidst.com/phenny/ http://inamidst.com/phenny/
""" """
import re import re, urllib
import web import web
from tools import deprecated from tools import deprecated
etyuri = 'http://etymonline.com/?term=%s' etysite = 'http://www.etymonline.com/index.php?'
etysearch = 'http://etymonline.com/?search=%s' etyuri = etysite + 'allowed_in_frame=0&term=%s'
etysearch = etysite + 'allowed_in_frame=0&search=%s'
r_definition = re.compile(r'(?ims)<dd[^>]*>.*?</dd>') r_definition = re.compile(r'(?ims)<dd[^>]*>.*?</dd>')
r_tag = re.compile(r'<(?!!)[^>]+>') r_tag = re.compile(r'<(?!!)[^>]+>')
r_whitespace = re.compile(r'[\t\r\n ]+') r_whitespace = re.compile(r'[\t\r\n ]+')
class Grab(urllib.URLopener):
def __init__(self, *args):
self.version = 'Mozilla/5.0 (Phenny)'
urllib.URLopener.__init__(self, *args)
def http_error_default(self, url, fp, errcode, errmsg, headers):
return urllib.addinfourl(fp, [headers, errcode], "http:" + url)
abbrs = [ abbrs = [
'cf', 'lit', 'etc', 'Ger', 'Du', 'Skt', 'Rus', 'Eng', 'Amer.Eng', 'Sp', 'cf', 'lit', 'etc', 'Ger', 'Du', 'Skt', 'Rus', 'Eng', 'Amer.Eng', 'Sp',
'Fr', 'N', 'E', 'S', 'W', 'L', 'Gen', 'J.C', 'dial', 'Gk', 'Fr', 'N', 'E', 'S', 'W', 'L', 'Gen', 'J.C', 'dial', 'Gk',
@ -46,7 +54,11 @@ def etymology(word):
raise ValueError("Word too long: %s[...]" % word[:10]) raise ValueError("Word too long: %s[...]" % word[:10])
word = {'axe': 'ax/axe'}.get(word, word) word = {'axe': 'ax/axe'}.get(word, word)
grab = urllib._urlopener
urllib._urlopener = Grab()
urllib._urlopener.addheader("Referer", "http://www.etymonline.com/")
bytes = web.get(etyuri % web.urllib.quote(word)) bytes = web.get(etyuri % web.urllib.quote(word))
urllib._urlopener = grab
definitions = r_definition.findall(bytes) definitions = r_definition.findall(bytes)
if not definitions: if not definitions:
@ -62,6 +74,7 @@ def etymology(word):
sentence = unicode(sentence, 'iso-8859-1') sentence = unicode(sentence, 'iso-8859-1')
sentence = sentence.encode('utf-8') sentence = sentence.encode('utf-8')
except: pass except: pass
sentence = web.decode(sentence)
maxlength = 275 maxlength = 275
if len(sentence) > maxlength: if len(sentence) > maxlength:
@ -71,7 +84,7 @@ def etymology(word):
sentence = ' '.join(words) + ' [...]' sentence = ' '.join(words) + ' [...]'
sentence = '"' + sentence.replace('"', "'") + '"' sentence = '"' + sentence.replace('"', "'") + '"'
return sentence + ' - ' + (etyuri % word) return sentence + ' - etymonline.com'
@deprecated @deprecated
def f_etymology(self, origin, match, args): def f_etymology(self, origin, match, args):