From bb78574bc09ee2ca961b235efea82da96fa9c366 Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Thu, 31 Jan 2013 19:48:07 +0530
Subject: [PATCH] add ox.web.twitter

---
 ox/web/twitter.py | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)
 create mode 100644 ox/web/twitter.py

diff --git a/ox/web/twitter.py b/ox/web/twitter.py
new file mode 100644
index 0000000..c1e9116
--- /dev/null
+++ b/ox/web/twitter.py
@@ -0,0 +1,30 @@
+# -*- coding: utf-8 -*-
+# vi:si:et:sw=4:sts=4:ts=4
+import re
+from datetime import datetime
+from urllib import quote
+
+import lxml.html
+from ox.cache import read_url
+
+
+def find(query):
+    url = 'https://twitter.com/search/' + quote(query)
+    data = ox.cache.read_url(url, timeout=60)
+    doc = lxml.html.document_fromstring(data)
+    tweets = []
+    for e in doc.xpath("//div[contains(@class, 'original-tweet')]"):
+        t = lxml.html.tostring(e)
+        text = e.xpath(".//p[contains(@class, 'js-tweet-text')]")[0]
+        text = ox.decode_html(ox.strip_tags(lxml.html.tostring(text))).strip()
+        user = re.compile('data-name="(.*?)"').findall(t)[0]
+        user = ox.decode_html(ox.strip_tags(user)).strip()
+        tweets.append({
+            'id': re.compile('data-tweet-id="(\d+)"').findall(t)[0],
+            'user-id': re.compile('data-user-id="(\d+)"').findall(t)[0],
+            'name': re.compile('data-screen-name="(.*?)"').findall(t)[0],
+            'time': datetime.fromtimestamp(int(re.compile('data-time="(\d+)"').findall(t)[0])),
+            'user': user,
+            'text': text,
+        })
+    return tweets