|
@@ -0,0 +1,26 @@
|
|
1
|
+from urlparse import urljoin
|
|
2
|
+from urllib import urlencode
|
|
3
|
+from lxml import html
|
|
4
|
+
|
|
5
|
+categories = ['social media']
|
|
6
|
+
|
|
7
|
+base_url = 'https://twitter.com/'
|
|
8
|
+search_url = base_url+'search?'
|
|
9
|
+
|
|
10
|
+def request(query, params):
|
|
11
|
+ global search_url
|
|
12
|
+ params['url'] = search_url + urlencode({'q': query})
|
|
13
|
+ return params
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+def response(resp):
|
|
17
|
+ global base_url
|
|
18
|
+ results = []
|
|
19
|
+ dom = html.fromstring(resp.text)
|
|
20
|
+ for tweet in dom.xpath('//li[@data-item-type="tweet"]'):
|
|
21
|
+ link = tweet.xpath('.//small[@class="time"]//a')[0]
|
|
22
|
+ url = urljoin(base_url, link.attrib.get('href'))
|
|
23
|
+ title = ''.join(tweet.xpath('.//span[@class="username js-action-profile-name"]//text()'))
|
|
24
|
+ content = ''.join(map(html.tostring, tweet.xpath('.//p[@class="js-tweet-text tweet-text"]//*')))
|
|
25
|
+ results.append({'url': url, 'title': title, 'content': content})
|
|
26
|
+ return results
|