0x2620/python-ox
2
1
Fork 0
Code Issues Pull requests Releases Wiki Activity

net/cache readUrl->read_url / Unicode -> unicode=True

Browse source 
format replace all CammelCase with under_score
This commit is contained in:
j 2012-08-14 15:58:05 +02:00
commit 2de989e188
33 changed files with 243 additions and 254 deletions
Download patch file Download diff file Expand all files Collapse all files

8
ox/web/duckduckgo.py
View file

@ -3,9 +3,9 @@
import re
import urllib
import ox
from ox import stripTags, decodeHtml
from ox import strip_tags, decodeHtml
from ox.utils import json
from ox.cache import readUrlUnicode
from ox.cache import read_url
def find(query, timeout=ox.cache.cache_timeout):
@ -13,10 +13,10 @@ def find(query, timeout=ox.cache.cache_timeout):
query = query.encode('utf-8')
params = urllib.urlencode({'q': query})
url = 'http://duckduckgo.com/html/?' + params
data = readUrlUnicode(url, timeout=timeout)
data = read_url(url, timeout=timeout, unicode=True)
results = []
regex = '<a .*?class="l le" href="(.+?)">(.*?)</a>.*?<div class="cra">(.*?)</div>'
for r in re.compile(regex, re.DOTALL).findall(data):
results.append((stripTags(decodeHtml(r[1])), r[0], stripTags(decodeHtml(r[2]))))
results.append((strip_tags(decodeHtml(r[1])), r[0], strip_tags(decodeHtml(r[2]))))
return results